{
  "lastUpdated": "2026-10-16T06:36:43.259Z",
  "totalItems": 597,
  "items": [
    {
      "id": "6a998372c8ebe72e2d9ca4de",
      "collection": "tasks-verifiers",
      "title": "Visual STEM Q&A Pairs",
      "slug": "task-stemqa-001",
      "url": "/data-catalog/tasks-verifiers/task-stemqa-001",
      "featured": false,
      "datasetId": "TASK_STEMQA_001",
      "languages": "English",
      "description": "Visual question-and-answer pairs spanning STEM disciplines — math, physics, chemistry, biology, and engineering — requiring visual understanding and reasoning over diagrams, charts, images, scientific figures, etc. Each pair is expert-authored and verified for correctness.",
      "category": "Multimodal Q&A",
      "domainSubjectArea": [
        "STEM (Math, Physics, Chemistry, Biology, Engineering)"
      ],
      "dataCoveragePeriod": "Not Specified",
      "qtyAvailable": "100,000 Q&A pairs",
      "sourceAnnotation": "Human-Generated — Expert Authoring & Verification (Visual + Text)",
      "knownLimitations": "Not Specified",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quaterly",
      "yearOfCollection": ""
    },
    {
      "id": "6a99837131b4728186ae2d40",
      "collection": "tasks-verifiers",
      "title": "GDPVal Tasks",
      "slug": "task-gdpval-001",
      "url": "/data-catalog/tasks-verifiers/task-gdpval-001",
      "featured": false,
      "datasetId": "TASK_GDPVAL_001",
      "languages": "English",
      "description": "GDPVal-style knowledge-worker evaluation tasks of varying complexity (1–50 steps), spanning realistic professional deliverables across industries. 600 tasks available now, with 1,000+ expected by end of month.",
      "category": "Reasoning / Knowledge-Worker Tasks",
      "domainSubjectArea": [
        "Cross-Industry Knowledge Work"
      ],
      "dataCoveragePeriod": "",
      "qtyAvailable": "600 now (1,000+ expected EOM)",
      "sourceAnnotation": "Human-Generated — Expert Task Authoring",
      "knownLimitations": "Pricing tiered by task complexity (step count) — see Volume Discount for tier breakdown",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": ""
    },
    {
      "id": "6a99837031b4728186ae2cc8",
      "collection": "tasks-verifiers",
      "title": "BrowseComp / Frontend Agentic Tasks",
      "slug": "task-agentic-001",
      "url": "/data-catalog/tasks-verifiers/task-agentic-001",
      "featured": false,
      "datasetId": "TASK_AGENTIC_001",
      "languages": "English",
      "description": "Browser-use and frontend web-agent tasks for training and evaluating agentic browsing and UI-interaction capabilities. Real multi-step web tasks with verifiable outcomes.",
      "category": "Agentic / Browser & Frontend Tasks",
      "domainSubjectArea": [
        "Web Browsing / Frontend Interaction"
      ],
      "dataCoveragePeriod": "",
      "qtyAvailable": "1,500 tasks",
      "sourceAnnotation": "Human-Generated — Expert Task Authoring",
      "knownLimitations": "Not Specified",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": ""
    },
    {
      "id": "6a99836ffa9df117f356d6c9",
      "collection": "tasks-verifiers",
      "title": "Support RL Tasks & Verifiers",
      "slug": "task-support-001",
      "url": "/data-catalog/tasks-verifiers/task-support-001",
      "featured": false,
      "datasetId": "TASK_SUPPORT_001",
      "languages": "English",
      "description": "Suite of 500 verifiable customer-support tasks ranging from easy to very hard (>100 steps). Tasks include classifying and routing tickets, approving or denying refunds within policy, and preventing potential customer churn. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring.",
      "category": "Conversational",
      "domainSubjectArea": [
        "Customer Support"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "500",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a99836efa9df117f356d5e8",
      "collection": "tasks-verifiers",
      "title": "Sales & Procurement RL Tasks & Verifiers",
      "slug": "task-sales-001",
      "url": "/data-catalog/tasks-verifiers/task-sales-001",
      "featured": false,
      "datasetId": "TASK_SALES_001",
      "languages": "English",
      "description": "Suite of 500 verifiable sales and procurement tasks ranging from easy to very hard (>100 steps). Tasks include classifying inbound leads, building quotes, and assembling vendor scorecards. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring.",
      "category": "Other",
      "domainSubjectArea": [
        "Sales",
        "Procurement"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "500",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a99836deeecffe161161c13",
      "collection": "tasks-verifiers",
      "title": "Knowledge Worker RL Tasks & Verifiers",
      "slug": "task-knowledge-001",
      "url": "/data-catalog/tasks-verifiers/task-knowledge-001",
      "featured": false,
      "datasetId": "TASK_KNOWLEDGE_001",
      "languages": "English",
      "description": "Suite of 1,000 verifiable GDPVal-style knowledge-worker tasks ranging from easy to very hard (>100 steps). Tasks span management consulting deliverables, financial modeling, competitive analysis, executive presentations, and research synthesis. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring. No sandbox environment included.",
      "category": "Other",
      "domainSubjectArea": [
        "Management Consulting",
        "Finance",
        "Strategy"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "1000",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a99836dfd732217e660df4e",
      "collection": "tasks-verifiers",
      "title": "ITSM RL Tasks & Verifiers",
      "slug": "task-itsm-001",
      "url": "/data-catalog/tasks-verifiers/task-itsm-001",
      "featured": false,
      "datasetId": "TASK_ITSM_001",
      "languages": "English",
      "description": "Suite of 500 verifiable ITSM tasks ranging from easy to very hard (>100 steps). Tasks include classifying new incidents, locating relevant knowledge-base information, and determining root cause and orchestrating remediation. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring.",
      "category": "Other",
      "domainSubjectArea": [
        "IT Service Management"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "500",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a99836cfd732217e660df09",
      "collection": "tasks-verifiers",
      "title": "HR RL Tasks & Verifiers",
      "slug": "task-hr-001",
      "url": "/data-catalog/tasks-verifiers/task-hr-001",
      "featured": false,
      "datasetId": "TASK_HR_001",
      "languages": "English",
      "description": "Suite of 500 verifiable HR tasks ranging from easy to very hard (>100 steps). Tasks include reviewing new applicants, evaluating PTO requests, and resolving employee benefits questions. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring.",
      "category": "Other",
      "domainSubjectArea": [
        "Human Resources"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "500",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a99836bd3a0ae3d297717cb",
      "collection": "tasks-verifiers",
      "title": "Healthcare RL Tasks & Verifiers",
      "slug": "task-health-001",
      "url": "/data-catalog/tasks-verifiers/task-health-001",
      "featured": false,
      "datasetId": "TASK_HEALTH_001",
      "languages": "English",
      "description": "Suite of 500 verifiable healthcare tasks ranging from easy to very hard (>100 steps). Tasks include retrieving authorized patient data, verifying insurance eligibility, and resolving discrepancies. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring.",
      "category": "Medical",
      "domainSubjectArea": [
        "Healthcare"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "500",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a99836a4005faf541bada49",
      "collection": "tasks-verifiers",
      "title": "Finance RL Tasks & Verifiers",
      "slug": "task-finance-001",
      "url": "/data-catalog/tasks-verifiers/task-finance-001",
      "featured": false,
      "datasetId": "TASK_FINANCE_001",
      "languages": "English",
      "description": "Suite of 500 verifiable finance tasks ranging from easy to very hard (>100 steps). Tasks include classifying incoming invoices, producing department spend reports, and creating financial projections. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring.",
      "category": "Financial",
      "domainSubjectArea": [
        "Finance",
        "Accounting"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "500",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a99836989ead58b4c1eb365",
      "collection": "tasks-verifiers",
      "title": "Dev Ops RL Tasks & Verifiers",
      "slug": "task-devops-001",
      "url": "/data-catalog/tasks-verifiers/task-devops-001",
      "featured": false,
      "datasetId": "TASK_DEVOPS_001",
      "languages": "English",
      "description": "Suite of 500 verifiable DevOps tasks ranging from easy to very hard (>100 steps). Tasks include writing user stories, calculating sprint story points, and linking Jira Epics to Confluence PRDs. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring.",
      "category": "Other",
      "domainSubjectArea": [
        "DevOps",
        "Project Management"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "500",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a99836857206d63ef247306",
      "collection": "tasks-verifiers",
      "title": "Coding RL Tasks & Verifiers",
      "slug": "task-coding-001",
      "url": "/data-catalog/tasks-verifiers/task-coding-001",
      "featured": false,
      "datasetId": "TASK_CODING_001",
      "languages": "English",
      "description": "Suite of 500 verifiable coding tasks ranging from easy to very hard (>100 steps). Tasks include resolving open GitHub issues, writing unit tests, and implementing API endpoints. Each task ships with rule-based verifiers (golden-answer matching) and toggleable rubric-based scoring.",
      "category": "Code",
      "domainSubjectArea": [
        "Software Engineering"
      ],
      "dataCoveragePeriod": "2025 – 2026",
      "qtyAvailable": "500",
      "sourceAnnotation": "Human-Generated — Expert Authoring",
      "knownLimitations": "None noted",
      "licenseType": "Perpetual — Non-Exclusive",
      "refreshCadence": "Quarterly",
      "yearOfCollection": "2025 – 2026"
    },
    {
      "id": "6a998690f4c0365c95ae3bca",
      "collection": "code-repos",
      "title": "LEAD_MANAGEMENT_PLATFORM_001",
      "slug": "lead-management-platform-001",
      "url": "/data-catalog/code-repos/lead-management-platform-001",
      "featured": false,
      "datasetId": "CODE_DEV_085",
      "category": "Software Development Company",
      "industry": "MarTech / Lead Management",
      "yearsInBusiness": "4",
      "established": "2022",
      "closed": "",
      "employees": "",
      "contributors": "3",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "Node.js",
        "Swift"
      ],
      "totalLoc": "271385",
      "repos": "2",
      "prs": "414",
      "avgLocPerPr": "",
      "commits": "128",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868fe57f73b05ad217a2",
      "collection": "code-repos",
      "title": "CONCESSIONS_MANAGEMENT_APP_001",
      "slug": "concessions-management-app-001",
      "url": "/data-catalog/code-repos/concessions-management-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_084",
      "category": "Software Development Company",
      "industry": "Food & Beverage / Concessions Mgmt",
      "yearsInBusiness": "7",
      "established": "2019",
      "closed": "",
      "employees": "",
      "contributors": "8",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "PHP",
        "Laravel"
      ],
      "totalLoc": "221176",
      "repos": "1",
      "prs": "313",
      "avgLocPerPr": "",
      "commits": "1176",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868f9ec510f7c328a0e7",
      "collection": "code-repos",
      "title": "REAL_ESTATE_PLATFORM_001",
      "slug": "real-estate-platform-001",
      "url": "/data-catalog/code-repos/real-estate-platform-001",
      "featured": false,
      "datasetId": "CODE_DEV_083",
      "category": "Software Development Company",
      "industry": "Real Estate / PropTech",
      "yearsInBusiness": "8",
      "established": "2018",
      "closed": "",
      "employees": "",
      "contributors": "9",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "PHP",
        "Laravel"
      ],
      "totalLoc": "161072",
      "repos": "1",
      "prs": "436",
      "avgLocPerPr": "",
      "commits": "1937",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868e17956efcbddc32ef",
      "collection": "code-repos",
      "title": "LOCAL_COMMERCE_PLATFORM_001",
      "slug": "local-commerce-platform-001",
      "url": "/data-catalog/code-repos/local-commerce-platform-001",
      "featured": false,
      "datasetId": "CODE_DEV_082",
      "category": "Software Development Company",
      "industry": "Local Commerce / Deals Platform",
      "yearsInBusiness": "10",
      "established": "2016",
      "closed": "",
      "employees": "",
      "contributors": "12",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "PHP",
        "CakePHP",
        "Swift"
      ],
      "totalLoc": "287378",
      "repos": "2",
      "prs": "411",
      "avgLocPerPr": "",
      "commits": "2294",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868dc09d52aea338dcae",
      "collection": "code-repos",
      "title": "FINTECH_PLATFORM_001",
      "slug": "fintech-platform-001",
      "url": "/data-catalog/code-repos/fintech-platform-001",
      "featured": false,
      "datasetId": "CODE_DEV_081",
      "category": "Software Development Company",
      "industry": "Fintech / Fitness Funding",
      "yearsInBusiness": "7",
      "established": "2019",
      "closed": "",
      "employees": "",
      "contributors": "13",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "Node.js"
      ],
      "totalLoc": "136816",
      "repos": "2",
      "prs": "206",
      "avgLocPerPr": "",
      "commits": "2461",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868c89ead58b4c2044df",
      "collection": "code-repos",
      "title": "LEAD_CONVERSION_PLATFORM_001",
      "slug": "lead-conversion-platform-001",
      "url": "/data-catalog/code-repos/lead-conversion-platform-001",
      "featured": false,
      "datasetId": "CODE_DEV_080",
      "category": "Software Development Company",
      "industry": "MarTech / Lead Conversion",
      "yearsInBusiness": "9",
      "established": "2017",
      "closed": "",
      "employees": "",
      "contributors": "10",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "Node.js"
      ],
      "totalLoc": "276993",
      "repos": "1",
      "prs": "417",
      "avgLocPerPr": "",
      "commits": "3094",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868b834e4fbc0a91ac23",
      "collection": "code-repos",
      "title": "GOVTECH_COMPLIANCE_APP_001",
      "slug": "govtech-compliance-app-001",
      "url": "/data-catalog/code-repos/govtech-compliance-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_079",
      "category": "Software Development Company",
      "industry": "GovTech / Alarm Compliance",
      "yearsInBusiness": "7",
      "established": "2019",
      "closed": "",
      "employees": "",
      "contributors": "10",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "Node.js"
      ],
      "totalLoc": "211967",
      "repos": "1",
      "prs": "552",
      "avgLocPerPr": "",
      "commits": "3208",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868ae57f73b05ad214b8",
      "collection": "code-repos",
      "title": "TIME_MANAGEMENT_SAAS_001",
      "slug": "time-management-saas-001",
      "url": "/data-catalog/code-repos/time-management-saas-001",
      "featured": false,
      "datasetId": "CODE_DEV_078",
      "category": "Software Development Company",
      "industry": "Productivity / Time Management SaaS",
      "yearsInBusiness": "9",
      "established": "2017",
      "closed": "",
      "employees": "",
      "contributors": "14",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "Node.js",
        "Swift"
      ],
      "totalLoc": "293974",
      "repos": "2",
      "prs": "678",
      "avgLocPerPr": "",
      "commits": "4054",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998689dbd7e1180eb907cf",
      "collection": "code-repos",
      "title": "BILLING_INVOICING_SAAS_001",
      "slug": "billing-invoicing-saas-001",
      "url": "/data-catalog/code-repos/billing-invoicing-saas-001",
      "featured": false,
      "datasetId": "CODE_DEV_077",
      "category": "Software Development Company",
      "industry": "SaaS / Billing & Invoicing",
      "yearsInBusiness": "7",
      "established": "2019",
      "closed": "",
      "employees": "",
      "contributors": "10",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "PHP",
        "Laravel"
      ],
      "totalLoc": "273247",
      "repos": "1",
      "prs": "1202",
      "avgLocPerPr": "",
      "commits": "4361",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868884235eb50a0e280d",
      "collection": "code-repos",
      "title": "FIELD_SERVICES_SAAS_001",
      "slug": "field-services-saas-001",
      "url": "/data-catalog/code-repos/field-services-saas-001",
      "featured": false,
      "datasetId": "CODE_DEV_076",
      "category": "Software Development Company",
      "industry": "Environmental Services / Field SaaS",
      "yearsInBusiness": "6",
      "established": "2020",
      "closed": "",
      "employees": "",
      "contributors": "16",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Java/Kotlin",
        "JavaScript",
        "Node.js",
        "Swift"
      ],
      "totalLoc": "250234",
      "repos": "3",
      "prs": "561",
      "avgLocPerPr": "",
      "commits": "5467",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998687c8ebe72e2d9e3555",
      "collection": "code-repos",
      "title": "LEAD_MANAGEMENT_PLATFORM_002",
      "slug": "lead-management-platform-002",
      "url": "/data-catalog/code-repos/lead-management-platform-002",
      "featured": false,
      "datasetId": "CODE_DEV_075",
      "category": "Software Development Company",
      "industry": "MarTech / Lead Management",
      "yearsInBusiness": "7",
      "established": "2019",
      "closed": "",
      "employees": "",
      "contributors": "10",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "Node.js"
      ],
      "totalLoc": "474777",
      "repos": "1",
      "prs": "618",
      "avgLocPerPr": "",
      "commits": "6374",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998686f41547c318e635ff",
      "collection": "code-repos",
      "title": "TOWING_SERVICES_APP_001",
      "slug": "towing-services-app-001",
      "url": "/data-catalog/code-repos/towing-services-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_074",
      "category": "Software Development Company",
      "industry": "On-Demand Services / Towing",
      "yearsInBusiness": "6",
      "established": "2020",
      "closed": "",
      "employees": "",
      "contributors": "28",
      "engineerQuality": "Junior",
      "developmentType": "Mobile app",
      "primaryLanguages": [
        "Java/Kotlin",
        "Swift"
      ],
      "totalLoc": "449743",
      "repos": "10",
      "prs": "2438",
      "avgLocPerPr": "",
      "commits": "7358",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868531d6f8d8f3d0180f",
      "collection": "code-repos",
      "title": "MARINE_BROKERAGE_APP_001",
      "slug": "marine-brokerage-app-001",
      "url": "/data-catalog/code-repos/marine-brokerage-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_073",
      "category": "Software Development Company",
      "industry": "Marine / Yacht Brokerage",
      "yearsInBusiness": "8",
      "established": "2018",
      "closed": "",
      "employees": "",
      "contributors": "21",
      "engineerQuality": "Junior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "PHP",
        "Laravel"
      ],
      "totalLoc": "229391",
      "repos": "4",
      "prs": "1294",
      "avgLocPerPr": "",
      "commits": "8418",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986846ab94adf346e1b35",
      "collection": "code-repos",
      "title": "RECRUITMENT_SAAS_001",
      "slug": "recruitment-saas-001",
      "url": "/data-catalog/code-repos/recruitment-saas-001",
      "featured": false,
      "datasetId": "CODE_DEV_072",
      "category": "Software Development Company",
      "industry": "HR Tech / Recruitment SaaS",
      "yearsInBusiness": "6",
      "established": "2020",
      "closed": "",
      "employees": "",
      "contributors": "17",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Mobile app",
      "primaryLanguages": [
        "JavaScript",
        "React Native"
      ],
      "totalLoc": "437435",
      "repos": "3",
      "prs": "984",
      "avgLocPerPr": "",
      "commits": "8571",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99868389ead58b4c204145",
      "collection": "code-repos",
      "title": "CRM_REALESTATE_APP_001",
      "slug": "crm-realestate-app-001",
      "url": "/data-catalog/code-repos/crm-realestate-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_071",
      "category": "Software Development Company",
      "industry": "CRM / Real Estate Tech",
      "yearsInBusiness": "3",
      "established": "2023",
      "closed": "",
      "employees": "",
      "contributors": "17",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Java/Kotlin",
        "JavaScript",
        "Node.js",
        "React"
      ],
      "totalLoc": "276889",
      "repos": "5",
      "prs": "5004",
      "avgLocPerPr": "",
      "commits": "8880",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998682dbd7e1180eb901ed",
      "collection": "code-repos",
      "title": "HR_MANAGEMENT_SAAS_001",
      "slug": "hr-management-saas-001",
      "url": "/data-catalog/code-repos/hr-management-saas-001",
      "featured": false,
      "datasetId": "CODE_DEV_070",
      "category": "Software Development Company",
      "industry": "HR Management SaaS",
      "yearsInBusiness": "6",
      "established": "2020",
      "closed": "",
      "employees": "",
      "contributors": "13",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Mobile app",
      "primaryLanguages": [
        "JavaScript",
        "React Native"
      ],
      "totalLoc": "368686",
      "repos": "2",
      "prs": "3252",
      "avgLocPerPr": "",
      "commits": "9466",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998681dbd7e1180eb90097",
      "collection": "code-repos",
      "title": "VETERINARY_WELLNESS_APP_001",
      "slug": "veterinary-wellness-app-001",
      "url": "/data-catalog/code-repos/veterinary-wellness-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_069",
      "category": "Software Development Company",
      "industry": "Veterinary / Animal Wellness",
      "yearsInBusiness": "8",
      "established": "2018",
      "closed": "",
      "employees": "",
      "contributors": "17",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "PHP",
        "Laravel",
        "TypeScript",
        "Angular"
      ],
      "totalLoc": "412719",
      "repos": "3",
      "prs": "2153",
      "avgLocPerPr": "",
      "commits": "12487",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986806ab94adf346e191b",
      "collection": "code-repos",
      "title": "ON_DEMAND_SERVICES_APP_001",
      "slug": "on-demand-services-app-001",
      "url": "/data-catalog/code-repos/on-demand-services-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_068",
      "category": "Software Development Company",
      "industry": "On-Demand Services / Lawn Care",
      "yearsInBusiness": "8",
      "established": "2018",
      "closed": "",
      "employees": "",
      "contributors": "29",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Java/Kotlin",
        "JavaScript",
        "Node.js",
        "React Native",
        "Swift",
        "TypeScript",
        "Angular"
      ],
      "totalLoc": "618917",
      "repos": "6",
      "prs": "4448",
      "avgLocPerPr": "",
      "commits": "16757",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867fdbd7e1180eb8fe88",
      "collection": "code-repos",
      "title": "COMMUNITY_PLATFORM_001",
      "slug": "community-platform-001",
      "url": "/data-catalog/code-repos/community-platform-001",
      "featured": false,
      "datasetId": "CODE_DEV_067",
      "category": "Software Development Company",
      "industry": "Community / Social Platform",
      "yearsInBusiness": "9",
      "established": "2017",
      "closed": "",
      "employees": "",
      "contributors": "16",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "React Native",
        "PHP",
        "Laravel"
      ],
      "totalLoc": "1246755",
      "repos": "2",
      "prs": "6778",
      "avgLocPerPr": "",
      "commits": "17757",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867e17854c543f937065",
      "collection": "code-repos",
      "title": "MAPPING_SAAS_001",
      "slug": "mapping-saas-001",
      "url": "/data-catalog/code-repos/mapping-saas-001",
      "featured": false,
      "datasetId": "CODE_DEV_066",
      "category": "Software Development Company",
      "industry": "Location Tech / Mapping SaaS",
      "yearsInBusiness": "6",
      "established": "2020",
      "closed": "",
      "employees": "",
      "contributors": "9",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "Node.js"
      ],
      "totalLoc": "675288",
      "repos": "1",
      "prs": "6332",
      "avgLocPerPr": "",
      "commits": "21622",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867d31d6f8d8f3d01566",
      "collection": "code-repos",
      "title": "AUTH_SDK_001",
      "slug": "auth-sdk-001",
      "url": "/data-catalog/code-repos/auth-sdk-001",
      "featured": false,
      "datasetId": "CODE_DEV_065",
      "category": "Software Development Company",
      "industry": "Authentication / Cross-Platform SDK",
      "yearsInBusiness": "2",
      "established": "2024",
      "closed": "",
      "employees": "",
      "contributors": "10",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "TypeScript",
        "Kotlin",
        "Swift",
        "C++"
      ],
      "totalLoc": "36061",
      "repos": "2",
      "prs": "234",
      "avgLocPerPr": "154.1",
      "commits": "746",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867c31d6f8d8f3d01461",
      "collection": "code-repos",
      "title": "AI_RECRUITMENT_SAAS_001",
      "slug": "ai-recruitment-saas-001",
      "url": "/data-catalog/code-repos/ai-recruitment-saas-001",
      "featured": false,
      "datasetId": "CODE_DEV_064",
      "category": "Software Development Company",
      "industry": "HRTech / AI Recruitment SaaS",
      "yearsInBusiness": "2",
      "established": "2022",
      "closed": "2024",
      "employees": "",
      "contributors": "15",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JavaScript",
        "TypeScript",
        "Python"
      ],
      "totalLoc": "154596",
      "repos": "63",
      "prs": "2163",
      "avgLocPerPr": "71.5",
      "commits": "7162",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867b89ead58b4c203d4c",
      "collection": "code-repos",
      "title": "IT_MONITORING_AI_001",
      "slug": "it-monitoring-ai-001",
      "url": "/data-catalog/code-repos/it-monitoring-ai-001",
      "featured": false,
      "datasetId": "CODE_DEV_063",
      "category": "Software Development Company",
      "industry": "B2B IT Monitoring / AIOps",
      "yearsInBusiness": "2",
      "established": "2021",
      "closed": "2023",
      "employees": "",
      "contributors": "6",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Go",
        "TypeScript",
        "JavaScript",
        "Python",
        "C",
        "C++",
        "Java",
        "Ruby",
        "Scala"
      ],
      "totalLoc": "6015832",
      "repos": "168",
      "prs": "2077",
      "avgLocPerPr": "2896.4",
      "commits": "15222",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867adbd7e1180eb8f9b6",
      "collection": "code-repos",
      "title": "EDTECH_PLATFORM_001",
      "slug": "edtech-platform-001",
      "url": "/data-catalog/code-repos/edtech-platform-001",
      "featured": false,
      "datasetId": "CODE_DEV_062",
      "category": "Software Development Company",
      "industry": "Online Education / EdTech",
      "yearsInBusiness": "8",
      "established": "2010",
      "closed": "2018",
      "employees": "",
      "contributors": "10",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "PHP",
        "Python",
        "JavaScript",
        "TypeScript",
        "C#",
        "Java",
        "C"
      ],
      "totalLoc": "10110851",
      "repos": "35",
      "prs": "391",
      "avgLocPerPr": "25859",
      "commits": "47470",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986796ab94adf346e12af",
      "collection": "code-repos",
      "title": "VR_PREVIEW_APP_001",
      "slug": "vr-preview-app-001",
      "url": "/data-catalog/code-repos/vr-preview-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_061",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "3.9",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#"
      ],
      "totalLoc": "209",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "6",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986786ab94adf346e1225",
      "collection": "code-repos",
      "title": "AR_VR_READER_APP_001",
      "slug": "ar-vr-reader-app-001",
      "url": "/data-catalog/code-repos/ar-vr-reader-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_060",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET application",
      "primaryLanguages": [
        "C#"
      ],
      "totalLoc": "429",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "4",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998677f4c0365c95ae3634",
      "collection": "code-repos",
      "title": "AR_APP_001",
      "slug": "ar-app-001",
      "url": "/data-catalog/code-repos/ar-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_059",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#"
      ],
      "totalLoc": "454",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986766ab94adf346e10f1",
      "collection": "code-repos",
      "title": "AR_VR_TOOLING_002",
      "slug": "ar-vr-tooling-002",
      "url": "/data-catalog/code-repos/ar-vr-tooling-002",
      "featured": false,
      "datasetId": "CODE_DEV_058",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "3.4",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET web application or service",
      "primaryLanguages": [
        "C#"
      ],
      "totalLoc": "543",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "5",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867517956efcbddc2a52",
      "collection": "code-repos",
      "title": "AR_VR_APP_004",
      "slug": "ar-vr-app-004",
      "url": "/data-catalog/code-repos/ar-vr-app-004",
      "featured": false,
      "datasetId": "CODE_DEV_057",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Web/JavaScript application",
      "primaryLanguages": [
        "JavaScript"
      ],
      "totalLoc": "558",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "18",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867413e9a932dc46cf2d",
      "collection": "code-repos",
      "title": "AUDIO_BACKEND_001",
      "slug": "audio-backend-001",
      "url": "/data-catalog/code-repos/audio-backend-001",
      "featured": false,
      "datasetId": "CODE_DEV_056",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.4",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Web/JavaScript application",
      "primaryLanguages": [
        "TypeScript",
        "HTML",
        "JavaScript"
      ],
      "totalLoc": "900",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "16",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998673040b228014994340",
      "collection": "code-repos",
      "title": "MOBILE_TOOL_APP_001",
      "slug": "mobile-tool-app-001",
      "url": "/data-catalog/code-repos/mobile-tool-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_055",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "3.7",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Windows (UWP) desktop application",
      "primaryLanguages": [
        "TypeScript",
        "C++",
        "C/C++ Header",
        "Java"
      ],
      "totalLoc": "1192",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867284235eb50a0e12d9",
      "collection": "code-repos",
      "title": "VR_HEALTHCARE_APP_001",
      "slug": "vr-healthcare-app-001",
      "url": "/data-catalog/code-repos/vr-healthcare-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_054",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "1333",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99867117956efcbddc2515",
      "collection": "code-repos",
      "title": "PRODUCTIVITY_ANDROID_APP_001",
      "slug": "productivity-android-app-001",
      "url": "/data-catalog/code-repos/productivity-android-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_053",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "3",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Native Android application",
      "primaryLanguages": [
        "Java"
      ],
      "totalLoc": "1451",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "61",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998670d3f7db2e71793c42",
      "collection": "code-repos",
      "title": "AR_VR_RELEASE_TOOL_001",
      "slug": "ar-vr-release-tool-001",
      "url": "/data-catalog/code-repos/ar-vr-release-tool-001",
      "featured": false,
      "datasetId": "CODE_DEV_052",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.2",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET web application or service",
      "primaryLanguages": [
        "C#"
      ],
      "totalLoc": "2352",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "44",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998670834e4fbc0a91a58e",
      "collection": "code-repos",
      "title": "AUDIO_VR_APP_001",
      "slug": "audio-vr-app-001",
      "url": "/data-catalog/code-repos/audio-vr-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_051",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "ShaderLab",
        "C#"
      ],
      "totalLoc": "3102",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866f17854c543f936bd0",
      "collection": "code-repos",
      "title": "HEALTHCARE_APP_002",
      "slug": "healthcare-app-002",
      "url": "/data-catalog/code-repos/healthcare-app-002",
      "featured": false,
      "datasetId": "CODE_DEV_050",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "4091",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "62",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866e31d6f8d8f3d00953",
      "collection": "code-repos",
      "title": "REAL_ESTATE_VR_APP_001",
      "slug": "real-estate-vr-app-001",
      "url": "/data-catalog/code-repos/real-estate-vr-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_049",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#"
      ],
      "totalLoc": "4170",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866df41547c318e62b0b",
      "collection": "code-repos",
      "title": "AR_VR_SERVER_001",
      "slug": "ar-vr-server-001",
      "url": "/data-catalog/code-repos/ar-vr-server-001",
      "featured": false,
      "datasetId": "CODE_DEV_048",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Windows (UWP) desktop application",
      "primaryLanguages": [
        "C#",
        "CSS",
        "JavaScript",
        "HTML"
      ],
      "totalLoc": "4440",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "10",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866c6ab94adf346e0bd2",
      "collection": "code-repos",
      "title": "AR_VR_TOOLING_001",
      "slug": "ar-vr-tooling-001",
      "url": "/data-catalog/code-repos/ar-vr-tooling-001",
      "featured": false,
      "datasetId": "CODE_DEV_047",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "0.7",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET application",
      "primaryLanguages": [
        "C#"
      ],
      "totalLoc": "4663",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866b31d6f8d8f3d007e6",
      "collection": "code-repos",
      "title": "AR_VR_APP_008",
      "slug": "ar-vr-app-008",
      "url": "/data-catalog/code-repos/ar-vr-app-008",
      "featured": false,
      "datasetId": "CODE_DEV_046",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET web application or service",
      "primaryLanguages": [
        "C#",
        "CSS"
      ],
      "totalLoc": "4756",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "2",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866ae924c86953f89dca",
      "collection": "code-repos",
      "title": "AR_VR_APP_017",
      "slug": "ar-vr-app-017",
      "url": "/data-catalog/code-repos/ar-vr-app-017",
      "featured": false,
      "datasetId": "CODE_DEV_045",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "4",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Windows (UWP) desktop application",
      "primaryLanguages": [
        "C#"
      ],
      "totalLoc": "5757",
      "repos": "1",
      "prs": "12",
      "avgLocPerPr": "778.1",
      "commits": "101",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998669f4ac0d8edcf345ab",
      "collection": "code-repos",
      "title": "AR_VR_APP_003",
      "slug": "ar-vr-app-003",
      "url": "/data-catalog/code-repos/ar-vr-app-003",
      "featured": false,
      "datasetId": "CODE_DEV_044",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "6945",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998668dbd7e1180eb8e929",
      "collection": "code-repos",
      "title": "UNITY_PACKAGE_001",
      "slug": "unity-package-001",
      "url": "/data-catalog/code-repos/unity-package-001",
      "featured": false,
      "datasetId": "CODE_DEV_043",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "6",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "6951",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "8",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866731d6f8d8f3d00501",
      "collection": "code-repos",
      "title": "SERVER_TOOL_001",
      "slug": "server-tool-001",
      "url": "/data-catalog/code-repos/server-tool-001",
      "featured": false,
      "datasetId": "CODE_DEV_042",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.2",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "3",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Windows (UWP) desktop application",
      "primaryLanguages": [
        "C#",
        "CSS"
      ],
      "totalLoc": "7349",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "47",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998666e57f73b05ad20476",
      "collection": "code-repos",
      "title": "ORDER_ASSISTANT_IOS_001",
      "slug": "order-assistant-ios-001",
      "url": "/data-catalog/code-repos/order-assistant-ios-001",
      "featured": false,
      "datasetId": "CODE_DEV_041",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.6",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Native iOS application",
      "primaryLanguages": [
        "Objective-C",
        "C/C++ Header"
      ],
      "totalLoc": "9140",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "74",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866589ead58b4c202f7c",
      "collection": "code-repos",
      "title": "AR_VR_APP_015",
      "slug": "ar-vr-app-015",
      "url": "/data-catalog/code-repos/ar-vr-app-015",
      "featured": false,
      "datasetId": "CODE_DEV_040",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "2.6",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET application",
      "primaryLanguages": [
        "C#",
        "TypeScript",
        "CSS",
        "HTML"
      ],
      "totalLoc": "12397",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "6",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99866413e9a932dc46cb18",
      "collection": "code-repos",
      "title": "AR_VR_APP_014",
      "slug": "ar-vr-app-014",
      "url": "/data-catalog/code-repos/ar-vr-app-014",
      "featured": false,
      "datasetId": "CODE_DEV_039",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET application",
      "primaryLanguages": [
        "C#",
        "TypeScript",
        "CSS",
        "HTML"
      ],
      "totalLoc": "12655",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "4",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998663e6ee6e81af9aa4d8",
      "collection": "code-repos",
      "title": "MOBILE_PROMO_APP_001",
      "slug": "mobile-promo-app-001",
      "url": "/data-catalog/code-repos/mobile-promo-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_038",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.7",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "13989",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998661dbd7e1180eb8e334",
      "collection": "code-repos",
      "title": "AR_VR_APP_007",
      "slug": "ar-vr-app-007",
      "url": "/data-catalog/code-repos/ar-vr-app-007",
      "featured": false,
      "datasetId": "CODE_DEV_037",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.6",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C/C++ Header project",
      "primaryLanguages": [
        "C/C++ Header",
        "Objective-C"
      ],
      "totalLoc": "15635",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "29",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986606ab94adf346e092e",
      "collection": "code-repos",
      "title": "EDTECH_HEALTH_APP_001",
      "slug": "edtech-health-app-001",
      "url": "/data-catalog/code-repos/edtech-health-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_036",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.8",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "3",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "PHP web application",
      "primaryLanguages": [
        "PHP",
        "JavaScript",
        "SQL"
      ],
      "totalLoc": "19106",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "131",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99865ffd732217e6614f83",
      "collection": "code-repos",
      "title": "PRODUCTIVITY_MOBILE_APP_001",
      "slug": "productivity-mobile-app-001",
      "url": "/data-catalog/code-repos/productivity-mobile-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_035",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "7",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Web frontend application",
      "primaryLanguages": [
        "Vue",
        "TypeScript",
        "HTML",
        "CSS"
      ],
      "totalLoc": "20061",
      "repos": "1",
      "prs": "1",
      "avgLocPerPr": "260",
      "commits": "804",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99865e834e4fbc0a919fc4",
      "collection": "code-repos",
      "title": "AR_VR_APP_016",
      "slug": "ar-vr-app-016",
      "url": "/data-catalog/code-repos/ar-vr-app-016",
      "featured": false,
      "datasetId": "CODE_DEV_034",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "7.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "3",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab",
        "Objective-C",
        "HLSL"
      ],
      "totalLoc": "20185",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "116",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99865d834e4fbc0a919f8b",
      "collection": "code-repos",
      "title": "VR_SCENE_REPO_001",
      "slug": "vr-scene-repo-001",
      "url": "/data-catalog/code-repos/vr-scene-repo-001",
      "featured": false,
      "datasetId": "CODE_DEV_033",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.8",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "8",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "HLSL",
        "ShaderLab"
      ],
      "totalLoc": "20788",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "164",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99865df4ac0d8edcf33c8c",
      "collection": "code-repos",
      "title": "AR_VR_APP_010",
      "slug": "ar-vr-app-010",
      "url": "/data-catalog/code-repos/ar-vr-app-010",
      "featured": false,
      "datasetId": "CODE_DEV_032",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.9",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET web application or service",
      "primaryLanguages": [
        "C#",
        "TypeScript",
        "Vue",
        "HTML"
      ],
      "totalLoc": "21111",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "4",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99865c834e4fbc0a919e75",
      "collection": "code-repos",
      "title": "PRODUCTIVITY_IOS_APP_001",
      "slug": "productivity-ios-app-001",
      "url": "/data-catalog/code-repos/productivity-ios-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_031",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Native iOS application",
      "primaryLanguages": [
        "Objective-C",
        "C/C++ Header"
      ],
      "totalLoc": "21378",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "71",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99865b946e817c7d637eba",
      "collection": "code-repos",
      "title": "AR_VR_ANDROID_APP_001",
      "slug": "ar-vr-android-app-001",
      "url": "/data-catalog/code-repos/ar-vr-android-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_030",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "7.8",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "5",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Native Android application",
      "primaryLanguages": [
        "Java"
      ],
      "totalLoc": "23690",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "70",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99865aeeecffe16117d3d4",
      "collection": "code-repos",
      "title": "ORDER_ASSISTANT_WEB_001",
      "slug": "order-assistant-web-001",
      "url": "/data-catalog/code-repos/order-assistant-web-001",
      "featured": false,
      "datasetId": "CODE_DEV_029",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.6",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "5",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Web frontend application",
      "primaryLanguages": [
        "CSS",
        "Vue",
        "JavaScript",
        "SCSS"
      ],
      "totalLoc": "24982",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "124",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986596d858e464b660b71",
      "collection": "code-repos",
      "title": "AR_VR_IOS_APP_001",
      "slug": "ar-vr-ios-app-001",
      "url": "/data-catalog/code-repos/ar-vr-ios-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_028",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.2",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C/C++ Header project",
      "primaryLanguages": [
        "C/C++ Header",
        "Objective-C",
        "Swift"
      ],
      "totalLoc": "27168",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "10",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998658d3f7db2e71793580",
      "collection": "code-repos",
      "title": "AR_VR_READER_APP_002",
      "slug": "ar-vr-reader-app-002",
      "url": "/data-catalog/code-repos/ar-vr-reader-app-002",
      "featured": false,
      "datasetId": "CODE_DEV_027",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "7.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C/C++ Header project",
      "primaryLanguages": [
        "C/C++ Header",
        "Objective-C",
        "HTML"
      ],
      "totalLoc": "27206",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "22",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998658946e817c7d637e49",
      "collection": "code-repos",
      "title": "HEALTHCARE_APP_001",
      "slug": "healthcare-app-001",
      "url": "/data-catalog/code-repos/healthcare-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_026",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "27207",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "2",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998657811b8e5d73614501",
      "collection": "code-repos",
      "title": "AR_VR_APP_011",
      "slug": "ar-vr-app-011",
      "url": "/data-catalog/code-repos/ar-vr-app-011",
      "featured": false,
      "datasetId": "CODE_DEV_025",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "4.4",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "PHP/Laravel web backend",
      "primaryLanguages": [
        "PHP",
        "Blade",
        "JavaScript",
        "SCSS"
      ],
      "totalLoc": "32037",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "5",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998656f4ac0d8edcf33bf5",
      "collection": "code-repos",
      "title": "AVATAR_APP_001",
      "slug": "avatar-app-001",
      "url": "/data-catalog/code-repos/avatar-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_024",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "2.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "JavaScript",
        "HTML",
        "CSS"
      ],
      "totalLoc": "33118",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "6",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998655d3a0ae3d297887c2",
      "collection": "code-repos",
      "title": "AR_VR_DASHBOARD_001",
      "slug": "ar-vr-dashboard-001",
      "url": "/data-catalog/code-repos/ar-vr-dashboard-001",
      "featured": false,
      "datasetId": "CODE_DEV_023",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "7",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET web application or service",
      "primaryLanguages": [
        "C#",
        "CSS",
        "HTML",
        "JavaScript"
      ],
      "totalLoc": "38040",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "260",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998654e57f73b05ad1fa85",
      "collection": "code-repos",
      "title": "AR_VR_APP_001",
      "slug": "ar-vr-app-001",
      "url": "/data-catalog/code-repos/ar-vr-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_022",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "39202",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998653040b2280149934d9",
      "collection": "code-repos",
      "title": "MULTIPLAYER_VR_SDK_001",
      "slug": "multiplayer-vr-sdk-001",
      "url": "/data-catalog/code-repos/multiplayer-vr-sdk-001",
      "featured": false,
      "datasetId": "CODE_DEV_021",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "2.9",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "3",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "40072",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "31",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986529ec510f7c3287787",
      "collection": "code-repos",
      "title": "COMPUTER_VISION_POC_001",
      "slug": "computer-vision-poc-001",
      "url": "/data-catalog/code-repos/computer-vision-poc-001",
      "featured": false,
      "datasetId": "CODE_DEV_020",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "3.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "C/C++ Header",
        "C++",
        "ShaderLab"
      ],
      "totalLoc": "41647",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "5",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998651e6ee6e81af9a98cd",
      "collection": "code-repos",
      "title": "RETAIL_VISION_POC_001",
      "slug": "retail-vision-poc-001",
      "url": "/data-catalog/code-repos/retail-vision-poc-001",
      "featured": false,
      "datasetId": "CODE_DEV_019",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "3.4",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "ShaderLab",
        "C#"
      ],
      "totalLoc": "45393",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "12",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998650c8ebe72e2d9e192f",
      "collection": "code-repos",
      "title": "AR_VR_APP_012",
      "slug": "ar-vr-app-012",
      "url": "/data-catalog/code-repos/ar-vr-app-012",
      "featured": false,
      "datasetId": "CODE_DEV_018",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "7.6",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "5",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET web application or service",
      "primaryLanguages": [
        "C#",
        "TypeScript",
        "HTML",
        "CSS"
      ],
      "totalLoc": "51088",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "142",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864ff41547c318e61e29",
      "collection": "code-repos",
      "title": "AR_VR_SERVER_002",
      "slug": "ar-vr-server-002",
      "url": "/data-catalog/code-repos/ar-vr-server-002",
      "featured": false,
      "datasetId": "CODE_DEV_017",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.5",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "9",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET web application or service",
      "primaryLanguages": [
        "C#",
        "HTML",
        "CSS",
        "JavaScript"
      ],
      "totalLoc": "59484",
      "repos": "1",
      "prs": "2",
      "avgLocPerPr": "26.5",
      "commits": "492",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864f17956efcbddc1549",
      "collection": "code-repos",
      "title": "VR_ASSET_REPO_001",
      "slug": "vr-asset-repo-001",
      "url": "/data-catalog/code-repos/vr-asset-repo-001",
      "featured": false,
      "datasetId": "CODE_DEV_016",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.8",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "7",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab",
        "HLSL"
      ],
      "totalLoc": "63241",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "176",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864e29d74d9309f33ebc",
      "collection": "code-repos",
      "title": "DATA_LABELING_TEMPLATES_001",
      "slug": "data-labeling-templates-001",
      "url": "/data-catalog/code-repos/data-labeling-templates-001",
      "featured": false,
      "datasetId": "CODE_DEV_015",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.7",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "3",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Web frontend application",
      "primaryLanguages": [
        "Python",
        "JavaScript",
        "SCSS",
        "TypeScript"
      ],
      "totalLoc": "75015",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "20",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864d29d74d9309f33e60",
      "collection": "code-repos",
      "title": "RETAIL_TRAINING_APP_001",
      "slug": "retail-training-app-001",
      "url": "/data-catalog/code-repos/retail-training-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_014",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "3.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C project",
      "primaryLanguages": [
        "C",
        "C/C++ Header",
        "Shell",
        "Python"
      ],
      "totalLoc": "92002",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "2",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864ce57f73b05ad1f4cb",
      "collection": "code-repos",
      "title": "VR_WEB_CLIENT_001",
      "slug": "vr-web-client-001",
      "url": "/data-catalog/code-repos/vr-web-client-001",
      "featured": false,
      "datasetId": "CODE_DEV_013",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "6",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "5",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "TypeScript",
        "ShaderLab",
        "HLSL"
      ],
      "totalLoc": "108849",
      "repos": "1",
      "prs": "1",
      "avgLocPerPr": "12442",
      "commits": "424",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864b84235eb50a0df9be",
      "collection": "code-repos",
      "title": "VR_APP_001",
      "slug": "vr-app-001",
      "url": "/data-catalog/code-repos/vr-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_012",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab",
        "JavaScript"
      ],
      "totalLoc": "122769",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864a57206d63ef25825c",
      "collection": "code-repos",
      "title": "PRODUCTIVITY_WEB_APP_001",
      "slug": "productivity-web-app-001",
      "url": "/data-catalog/code-repos/productivity-web-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_011",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.5",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "7",
      "engineerQuality": "Non-Vibecoders",
      "developmentType": "C# / .NET web application or service",
      "primaryLanguages": [
        "C#",
        "Vue",
        "TypeScript",
        "SCSS"
      ],
      "totalLoc": "147631",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1415",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998649e6ee6e81af9a9278",
      "collection": "code-repos",
      "title": "AR_VR_APP_006",
      "slug": "ar-vr-app-006",
      "url": "/data-catalog/code-repos/ar-vr-app-006",
      "featured": false,
      "datasetId": "CODE_DEV_010",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.5",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "16",
      "engineerQuality": "Non-Vibecoders",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab",
        "JavaScript",
        "HLSL"
      ],
      "totalLoc": "156539",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "2425",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864917376764883d8fd1",
      "collection": "code-repos",
      "title": "AR_VR_APP_005",
      "slug": "ar-vr-app-005",
      "url": "/data-catalog/code-repos/ar-vr-app-005",
      "featured": false,
      "datasetId": "CODE_DEV_009",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "2.2",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "PHP",
        "C#",
        "CSS",
        "ShaderLab"
      ],
      "totalLoc": "194182",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "7",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998648991d16e5e66de44b",
      "collection": "code-repos",
      "title": "HEALTHCARE_APP_003",
      "slug": "healthcare-app-003",
      "url": "/data-catalog/code-repos/healthcare-app-003",
      "featured": false,
      "datasetId": "CODE_DEV_008",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "7.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab",
        "HTML",
        "C/C++ Header"
      ],
      "totalLoc": "237389",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "2",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998647e6ee6e81af9a9108",
      "collection": "code-repos",
      "title": "AR_VR_APP_013",
      "slug": "ar-vr-app-013",
      "url": "/data-catalog/code-repos/ar-vr-app-013",
      "featured": false,
      "datasetId": "CODE_DEV_007",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "0.7",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET application",
      "primaryLanguages": [
        "C#",
        "C",
        "SQL",
        "HTML"
      ],
      "totalLoc": "274717",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "2",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99864617956efcbddc0e8c",
      "collection": "code-repos",
      "title": "AR_VR_APP_009",
      "slug": "ar-vr-app-009",
      "url": "/data-catalog/code-repos/ar-vr-app-009",
      "featured": false,
      "datasetId": "CODE_DEV_006",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "10.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "3",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Web/JavaScript application",
      "primaryLanguages": [
        "JavaScript",
        "CSS",
        "HTML",
        "SCSS"
      ],
      "totalLoc": "286685",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "18",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986456d858e464b6600e0",
      "collection": "code-repos",
      "title": "HEALTHCARE_VR_APP_001",
      "slug": "healthcare-vr-app-001",
      "url": "/data-catalog/code-repos/healthcare-vr-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_005",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "347254",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998644dbd7e1180eb8cfa9",
      "collection": "code-repos",
      "title": "AR_VR_DESIGNER_APP_001",
      "slug": "ar-vr-designer-app-001",
      "url": "/data-catalog/code-repos/ar-vr-designer-app-001",
      "featured": false,
      "datasetId": "CODE_DEV_004",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "6.3",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "C# / .NET application",
      "primaryLanguages": [
        "C#",
        "PHP",
        "CSS",
        "HTML"
      ],
      "totalLoc": "377259",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "5",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998642eeecffe16117c871",
      "collection": "code-repos",
      "title": "VR_TRAINING_APP_002",
      "slug": "vr-training-app-002",
      "url": "/data-catalog/code-repos/vr-training-app-002",
      "featured": false,
      "datasetId": "CODE_DEV_003",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "6.9",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "2",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab",
        "JavaScript",
        "HTML"
      ],
      "totalLoc": "523619",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "6",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998641d3a0ae3d29787fe8",
      "collection": "code-repos",
      "title": "AR_VR_APP_002",
      "slug": "ar-vr-app-002",
      "url": "/data-catalog/code-repos/ar-vr-app-002",
      "featured": false,
      "datasetId": "CODE_DEV_002",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab",
        "JavaScript",
        "HTML"
      ],
      "totalLoc": "526952",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "2",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998640bc894a1ebfd3ed41",
      "collection": "code-repos",
      "title": "AR_VR_GAME_001",
      "slug": "ar-vr-game-001",
      "url": "/data-catalog/code-repos/ar-vr-game-001",
      "featured": false,
      "datasetId": "CODE_DEV_001",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "1.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "1",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab",
        "HTML",
        "CSS"
      ],
      "totalLoc": "8723234",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "1",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863f29d74d9309f33565",
      "collection": "code-repos",
      "title": "MEDIA_ENTERTAINMENT_CODEBASE_001",
      "slug": "media-entertainment-codebase-001",
      "url": "/data-catalog/code-repos/media-entertainment-codebase-001",
      "featured": false,
      "datasetId": "CODE_MEDIA_001",
      "category": "Digital Media / Entertainment Databases",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "11",
      "established": "2012",
      "closed": "2023",
      "employees": "",
      "contributors": "50",
      "engineerQuality": "Non-Vibecoders",
      "developmentType": "PHP, Ruby, JavaScript, TypeScript, Python, C, C++",
      "primaryLanguages": [],
      "totalLoc": "10393679",
      "repos": "55",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "21257",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863eeeecffe16117c4ea",
      "collection": "code-repos",
      "title": "VR_TRAINING_APP_001",
      "slug": "vr-training-app-001",
      "url": "/data-catalog/code-repos/vr-training-app-001",
      "featured": false,
      "datasetId": "VR_TRAINING_APP_001",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "6.6",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "3",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "C#",
        "ShaderLab"
      ],
      "totalLoc": "n/a (large asset repo, not LoC-counted)",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "492",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863d17956efcbddc0786",
      "collection": "code-repos",
      "title": "AR_VR_ASSET_REPO_001",
      "slug": "ar-vr-asset-repo-001",
      "url": "/data-catalog/code-repos/ar-vr-asset-repo-001",
      "featured": false,
      "datasetId": "AR_VR_ASSET_REPO_001",
      "category": "Software Development Company",
      "industry": "Software development (AR/VR, web, mobile)",
      "yearsInBusiness": "5.1",
      "established": "2005",
      "closed": "",
      "employees": "5",
      "contributors": "13",
      "engineerQuality": "Specialized Development Agency",
      "developmentType": "Unity 3D / AR-VR application",
      "primaryLanguages": [
        "ShaderLab",
        "C#",
        "HLSL"
      ],
      "totalLoc": "n/a (large asset repo, not LoC-counted)",
      "repos": "1",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "736",
      "testCoverage": "",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863b9ec510f7c3286d33",
      "collection": "code-repos",
      "title": "RECRUITMENT_EDTECH_PLATFORM_001",
      "slug": "recruitment-edtech-platform-001",
      "url": "/data-catalog/code-repos/recruitment-edtech-platform-001",
      "featured": false,
      "datasetId": "RECRUITMENT_EDTECH_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "Recruitment & Education",
      "yearsInBusiness": "8",
      "established": "2015",
      "closed": "2023",
      "employees": "",
      "contributors": "20",
      "engineerQuality": "Non-Vibecoders",
      "developmentType": "",
      "primaryLanguages": [
        "C#",
        "JavaScript",
        "PHP",
        "Java",
        "Kotlin",
        "C",
        "C++"
      ],
      "totalLoc": "1303828",
      "repos": "12",
      "prs": "98",
      "avgLocPerPr": "13304.4",
      "commits": "9596",
      "testCoverage": "455",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863b040b228014992837",
      "collection": "code-repos",
      "title": "HEALTHCARE_SOCIAL_PLATFORM_001",
      "slug": "healthcare-social-platform-001",
      "url": "/data-catalog/code-repos/healthcare-social-platform-001",
      "featured": false,
      "datasetId": "HEALTHCARE_SOCIAL_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "Healthcare",
      "yearsInBusiness": "4",
      "established": "2016",
      "closed": "2020",
      "employees": "40+",
      "contributors": "10",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Ruby"
      ],
      "totalLoc": "101000",
      "repos": "1",
      "prs": "1600+",
      "avgLocPerPr": "63.1",
      "commits": "6200",
      "testCoverage": "10%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863a8afbba395744dcae",
      "collection": "code-repos",
      "title": "SHOPPABLE_UGC_PLATFORM_001",
      "slug": "shoppable-ugc-platform-001",
      "url": "/data-catalog/code-repos/shoppable-ugc-platform-001",
      "featured": false,
      "datasetId": "SHOPPABLE_UGC_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "Media",
      "yearsInBusiness": "2",
      "established": "2022",
      "closed": "2024",
      "employees": "10+",
      "contributors": "6",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Ruby",
        "TypeScript"
      ],
      "totalLoc": "25000",
      "repos": "2",
      "prs": "1500+",
      "avgLocPerPr": "16.7",
      "commits": "4500",
      "testCoverage": "30%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863931d6f8d8f3cff23d",
      "collection": "code-repos",
      "title": "CLOUD_LOGS_PLATFORM_001",
      "slug": "cloud-logs-platform-001",
      "url": "/data-catalog/code-repos/cloud-logs-platform-001",
      "featured": false,
      "datasetId": "CLOUD_LOGS_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "SaaS",
      "yearsInBusiness": "9",
      "established": "2011",
      "closed": "2020",
      "employees": "20+",
      "contributors": "4",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Java"
      ],
      "totalLoc": "84000",
      "repos": "1",
      "prs": "250+",
      "avgLocPerPr": "336",
      "commits": "13000",
      "testCoverage": "35%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863817956efcbddc05e6",
      "collection": "code-repos",
      "title": "POS_PLATFORM_001",
      "slug": "pos-platform-001",
      "url": "/data-catalog/code-repos/pos-platform-001",
      "featured": false,
      "datasetId": "POS_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "Consumer Web",
      "yearsInBusiness": "3",
      "established": "2015",
      "closed": "2018",
      "employees": "30+",
      "contributors": "8",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "TypeScript"
      ],
      "totalLoc": "25000",
      "repos": "1",
      "prs": "300+",
      "avgLocPerPr": "83.3",
      "commits": "3000",
      "testCoverage": "40%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863784235eb50a0dec4d",
      "collection": "code-repos",
      "title": "ECOMMERCE_PLATFORM_001",
      "slug": "ecommerce-platform-001",
      "url": "/data-catalog/code-repos/ecommerce-platform-001",
      "featured": false,
      "datasetId": "ECOMMERCE_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "E-commerce",
      "yearsInBusiness": "2",
      "established": "2016",
      "closed": "2018",
      "employees": "30+",
      "contributors": "6",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Ruby",
        "Swift"
      ],
      "totalLoc": "75000",
      "repos": "2",
      "prs": "7000+",
      "avgLocPerPr": "10.7",
      "commits": "22000",
      "testCoverage": "51%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986369ec510f7c32869a6",
      "collection": "code-repos",
      "title": "KPI_OKR_PLATFORM_001",
      "slug": "kpi-okr-platform-001",
      "url": "/data-catalog/code-repos/kpi-okr-platform-001",
      "featured": false,
      "datasetId": "KPI_OKR_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "SaaS",
      "yearsInBusiness": "7",
      "established": "2019",
      "closed": "2026",
      "employees": "40+",
      "contributors": "10",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Ruby",
        "JS"
      ],
      "totalLoc": "400000",
      "repos": "3",
      "prs": "11000+",
      "avgLocPerPr": "36.4",
      "commits": "22000",
      "testCoverage": "75%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998635040b2280149924e9",
      "collection": "code-repos",
      "title": "WEB_PLATFORM_001",
      "slug": "web-platform-001",
      "url": "/data-catalog/code-repos/web-platform-001",
      "featured": false,
      "datasetId": "WEB_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "Web Platform",
      "yearsInBusiness": "6",
      "established": "2018",
      "closed": "2024",
      "employees": "15+",
      "contributors": "5",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        ".NET"
      ],
      "totalLoc": "200000",
      "repos": "1",
      "prs": "700+",
      "avgLocPerPr": "285.7",
      "commits": "3000",
      "testCoverage": "83%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998634e6ee6e81af9a84fd",
      "collection": "code-repos",
      "title": "DATA_TRANSFORMATION_PLATFORM_001",
      "slug": "data-transformation-platform-001",
      "url": "/data-catalog/code-repos/data-transformation-platform-001",
      "featured": false,
      "datasetId": "DATA_TRANSFORMATION_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "Data",
      "yearsInBusiness": "4",
      "established": "2020",
      "closed": "2025",
      "employees": "20+",
      "contributors": "6",
      "engineerQuality": "Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Python",
        "JS"
      ],
      "totalLoc": "57000",
      "repos": "3",
      "prs": "800+",
      "avgLocPerPr": "71.2",
      "commits": "10000",
      "testCoverage": "84%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998633e924c86953f880cf",
      "collection": "code-repos",
      "title": "CONSUMER_WEB_PLATFORM_001",
      "slug": "consumer-web-platform-001",
      "url": "/data-catalog/code-repos/consumer-web-platform-001",
      "featured": false,
      "datasetId": "CONSUMER_WEB_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "Consumer Web",
      "yearsInBusiness": "3",
      "established": "2021",
      "closed": "2024",
      "employees": "6+",
      "contributors": "3",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "JS",
        "Python"
      ],
      "totalLoc": "19000",
      "repos": "1",
      "prs": "200+",
      "avgLocPerPr": "95",
      "commits": "300",
      "testCoverage": "90%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863389ead58b4c2013c1",
      "collection": "code-repos",
      "title": "EDI_PLATFORM_001",
      "slug": "edi-platform-001",
      "url": "/data-catalog/code-repos/edi-platform-001",
      "featured": false,
      "datasetId": "EDI_PLATFORM_001",
      "category": "Software Development Company",
      "industry": "SaaS",
      "yearsInBusiness": "5",
      "established": "2020",
      "closed": "2025",
      "employees": "20+",
      "contributors": "6",
      "engineerQuality": "Mid to Senior",
      "developmentType": "Full-Stack",
      "primaryLanguages": [
        "Python",
        "JS"
      ],
      "totalLoc": "140000",
      "repos": "2",
      "prs": "250+",
      "avgLocPerPr": "560",
      "commits": "1800",
      "testCoverage": "90%",
      "codeAvailability": "Available on request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99863273f796e25925f16a",
      "collection": "code-repos",
      "title": "AI_LEAD_GEN_CODEBASE_001",
      "slug": "ai-lead-gen-codebase-001",
      "url": "/data-catalog/code-repos/ai-lead-gen-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_034",
      "category": "Private Codebase",
      "industry": "AI lead generation / social listening",
      "yearsInBusiness": "0.1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "15",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Python",
        "TypeScript",
        "JavaScript",
        "HTML",
        "CSS",
        "Shell",
        "Dockerfile"
      ],
      "totalLoc": "85348",
      "repos": "2",
      "prs": "189",
      "avgLocPerPr": "451.6",
      "commits": "568",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998630991d16e5e66ddd51",
      "collection": "code-repos",
      "title": "DATA_ANALYTICS_CODEBASE_001",
      "slug": "data-analytics-codebase-001",
      "url": "/data-catalog/code-repos/data-analytics-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_033",
      "category": "Private Codebase",
      "industry": "Data analytics / BI (natural-language DB querying)",
      "yearsInBusiness": "0.4",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "14",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Python",
        "TypeScript",
        "JavaScript",
        "HTML",
        "CSS",
        "Shell",
        "Dockerfile",
        "Makefile"
      ],
      "totalLoc": "58088",
      "repos": "2",
      "prs": "15",
      "avgLocPerPr": "3872.5",
      "commits": "113",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99862fdbd7e1180eb8c098",
      "collection": "code-repos",
      "title": "WAREHOUSE_MANAGEMENT_CODEBASE_001",
      "slug": "warehouse-management-codebase-001",
      "url": "/data-catalog/code-repos/warehouse-management-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_032",
      "category": "Private Codebase",
      "industry": "Warehouse Management System (Logistics & Supply Chain)",
      "yearsInBusiness": "1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "1",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Laravel",
        "PHP",
        "Inventrory",
        "Bootstrap"
      ],
      "totalLoc": "97134",
      "repos": "1",
      "prs": "126",
      "avgLocPerPr": "770.9",
      "commits": "255",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99862dd80c25273cfedd11",
      "collection": "code-repos",
      "title": "REAL_ESTATE_CODEBASE_001",
      "slug": "real-estate-codebase-001",
      "url": "/data-catalog/code-repos/real-estate-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_031",
      "category": "Private Codebase",
      "industry": "Real Estate / Property Management",
      "yearsInBusiness": "2",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "1",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "TypeScript",
        "JavaScript",
        "HTML",
        "CSS",
        "Prisma Schema",
        "EJS"
      ],
      "totalLoc": "25545",
      "repos": "5",
      "prs": "0",
      "avgLocPerPr": "",
      "commits": "4733",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99862c57206d63ef2573d3",
      "collection": "code-repos",
      "title": "HR_CODEBASE_003",
      "slug": "hr-codebase-003",
      "url": "/data-catalog/code-repos/hr-codebase-003",
      "featured": false,
      "datasetId": "CODE_PRIVATE_030",
      "category": "Private Codebase",
      "industry": "Human Resources",
      "yearsInBusiness": "1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "8",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "PHP",
        "CSS",
        "JavaScript",
        "HTML"
      ],
      "totalLoc": "251066",
      "repos": "1",
      "prs": "124",
      "avgLocPerPr": "2024.7",
      "commits": "271",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99862b834e4fbc0a918ca2",
      "collection": "code-repos",
      "title": "CRM_PLATFORM_002",
      "slug": "crm-platform-002",
      "url": "/data-catalog/code-repos/crm-platform-002",
      "featured": false,
      "datasetId": "CODE_PRIVATE_029",
      "category": "Private Codebase",
      "industry": "Customer Relationship Management (Sales & Customer Service)",
      "yearsInBusiness": "2",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "11",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "PHP",
        "CSS",
        "JavaScript",
        "HTML",
        "Dart"
      ],
      "totalLoc": "223691",
      "repos": "1",
      "prs": "149",
      "avgLocPerPr": "1501.3",
      "commits": "305",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99862adbd7e1180eb8be1f",
      "collection": "code-repos",
      "title": "HOSPITALITY_CODEBASE_001",
      "slug": "hospitality-codebase-001",
      "url": "/data-catalog/code-repos/hospitality-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_028",
      "category": "Private Codebase",
      "industry": "Hospitality (Hotels, Restaurants, Travel)",
      "yearsInBusiness": "1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "11",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "CSS",
        "Blade",
        "PHP",
        "JavaScript"
      ],
      "totalLoc": "66702",
      "repos": "1",
      "prs": "194",
      "avgLocPerPr": "343.8",
      "commits": "398",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998629991d16e5e66ddb2d",
      "collection": "code-repos",
      "title": "MARKETING_CODEBASE_001",
      "slug": "marketing-codebase-001",
      "url": "/data-catalog/code-repos/marketing-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_027",
      "category": "Private Codebase",
      "industry": "Marketing & Advertising",
      "yearsInBusiness": "1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "7",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Blade",
        "PHP",
        "CSS",
        "JavaScript"
      ],
      "totalLoc": "1322393",
      "repos": "1",
      "prs": "108",
      "avgLocPerPr": "12244.4",
      "commits": "21121",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998628e57f73b05ad1e3a9",
      "collection": "code-repos",
      "title": "CRM_PLATFORM_001",
      "slug": "crm-platform-001",
      "url": "/data-catalog/code-repos/crm-platform-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_026",
      "category": "Private Codebase",
      "industry": "Customer Relationship Management (Sales & Customer Service)",
      "yearsInBusiness": "1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "6",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "PHP",
        "CSS",
        "JavaScript",
        "HTML"
      ],
      "totalLoc": "345368",
      "repos": "1",
      "prs": "202",
      "avgLocPerPr": "1709.7",
      "commits": "424",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998627fa9df117f3584861",
      "collection": "code-repos",
      "title": "BUSINESS_OPS_CODEBASE_006",
      "slug": "business-ops-codebase-006",
      "url": "/data-catalog/code-repos/business-ops-codebase-006",
      "featured": false,
      "datasetId": "CODE_PRIVATE_025",
      "category": "Private Codebase",
      "industry": "Business Operations",
      "yearsInBusiness": "3",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "9",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "CSS",
        "HTML",
        "C#",
        "Razor",
        "MSBuild script",
        "C# Designer",
        "Visual Studio Solution",
        "Ruby",
        "ASP.NET"
      ],
      "totalLoc": "729693",
      "repos": "1",
      "prs": "219",
      "avgLocPerPr": "3331.9",
      "commits": "483",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986266ab94adf346dec1c",
      "collection": "code-repos",
      "title": "INVENTORY_SUPPLY_CHAIN_001",
      "slug": "inventory-supply-chain-001",
      "url": "/data-catalog/code-repos/inventory-supply-chain-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_024",
      "category": "Private Codebase",
      "industry": "Inventory Management / Supply Chain",
      "yearsInBusiness": "1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "15",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Blade",
        "PHP",
        "CSS",
        "JavaScript"
      ],
      "totalLoc": "213930",
      "repos": "1",
      "prs": "504",
      "avgLocPerPr": "424.5",
      "commits": "975",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998625040b228014992034",
      "collection": "code-repos",
      "title": "HR_CODEBASE_002",
      "slug": "hr-codebase-002",
      "url": "/data-catalog/code-repos/hr-codebase-002",
      "featured": false,
      "datasetId": "CODE_PRIVATE_023",
      "category": "Private Codebase",
      "industry": "HR & Workforce Management",
      "yearsInBusiness": "3",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "9",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "CSS",
        "C#",
        "HTML",
        "Razor",
        "MSBuild script",
        "C# Designer",
        "Visual Studio Solution",
        "Ruby",
        "ASP.NET"
      ],
      "totalLoc": "842187",
      "repos": "1",
      "prs": "661",
      "avgLocPerPr": "1274.1",
      "commits": "1105",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998624e6ee6e81af9a7f9e",
      "collection": "code-repos",
      "title": "HEALTHCARE_CODEBASE_003",
      "slug": "healthcare-codebase-003",
      "url": "/data-catalog/code-repos/healthcare-codebase-003",
      "featured": false,
      "datasetId": "CODE_PRIVATE_022",
      "category": "Private Codebase",
      "industry": "Healthcare & Wellness",
      "yearsInBusiness": "1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "9",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Blade",
        "PHP",
        "CSS",
        "JavaScript"
      ],
      "totalLoc": "44866",
      "repos": "1",
      "prs": "533",
      "avgLocPerPr": "84.2",
      "commits": "2023",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99862373f796e25925ead1",
      "collection": "code-repos",
      "title": "HEALTHCARE_CODEBASE_002",
      "slug": "healthcare-codebase-002",
      "url": "/data-catalog/code-repos/healthcare-codebase-002",
      "featured": false,
      "datasetId": "CODE_PRIVATE_021",
      "category": "Private Codebase",
      "industry": "Healthcare & Wellness",
      "yearsInBusiness": "8",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "18",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "TypeScript",
        "HTML",
        "CSS",
        "JavaScript",
        "PHP",
        "Blade"
      ],
      "totalLoc": "412719",
      "repos": "3",
      "prs": "2211",
      "avgLocPerPr": "186.7",
      "commits": "12675",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998621e924c86953f87b98",
      "collection": "code-repos",
      "title": "BUSINESS_OPS_CODEBASE_005",
      "slug": "business-ops-codebase-005",
      "url": "/data-catalog/code-repos/business-ops-codebase-005",
      "featured": false,
      "datasetId": "CODE_PRIVATE_020",
      "category": "Private Codebase",
      "industry": "Business Operations Platforms",
      "yearsInBusiness": "4.2",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "18",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "Handlebars",
        "CSS",
        "LuaSwift",
        "Objective-C",
        "C++",
        "C",
        "Objective-C++",
        "HTML"
      ],
      "totalLoc": "293974",
      "repos": "2",
      "prs": "716",
      "avgLocPerPr": "410.6",
      "commits": "4089",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998620e924c86953f87b54",
      "collection": "code-repos",
      "title": "ERP_CODEBASE_003",
      "slug": "erp-codebase-003",
      "url": "/data-catalog/code-repos/erp-codebase-003",
      "featured": false,
      "datasetId": "CODE_PRIVATE_019",
      "category": "Private Codebase",
      "industry": "ERP Systems",
      "yearsInBusiness": "8.1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "14",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "PHP",
        "JavaScript",
        "CSS",
        "HTML",
        "Objective-C",
        "Swift",
        "C++",
        "Objective-C++"
      ],
      "totalLoc": "287378",
      "repos": "2",
      "prs": "430",
      "avgLocPerPr": "668.3",
      "commits": "1565",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99862013e9a932dc46bf15",
      "collection": "code-repos",
      "title": "ERP_CODEBASE_002",
      "slug": "erp-codebase-002",
      "url": "/data-catalog/code-repos/erp-codebase-002",
      "featured": false,
      "datasetId": "CODE_PRIVATE_018",
      "category": "Private Codebase",
      "industry": "ERP Systems",
      "yearsInBusiness": "5.2",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "18",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "TypeScript",
        "HTML",
        "LuaSwift",
        "Objective-C",
        "C++",
        "C",
        "Objective-C++",
        "Kotlin",
        "Java"
      ],
      "totalLoc": "250234",
      "repos": "3",
      "prs": "573",
      "avgLocPerPr": "436.7",
      "commits": "5224",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861f17956efcbddbfe10",
      "collection": "code-repos",
      "title": "BUSINESS_OPS_CODEBASE_004",
      "slug": "business-ops-codebase-004",
      "url": "/data-catalog/code-repos/business-ops-codebase-004",
      "featured": false,
      "datasetId": "CODE_PRIVATE_017",
      "category": "Private Codebase",
      "industry": "Business Operations Platforms",
      "yearsInBusiness": "7.2",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "24",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Handlebars",
        "JavaScript",
        "CSS",
        "HTML",
        "CoffeeScript"
      ],
      "totalLoc": "211967",
      "repos": "1",
      "prs": "561",
      "avgLocPerPr": "377.8",
      "commits": "2748",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861e57206d63ef256bd3",
      "collection": "code-repos",
      "title": "BUSINESS_OPS_CODEBASE_003",
      "slug": "business-ops-codebase-003",
      "url": "/data-catalog/code-repos/business-ops-codebase-003",
      "featured": false,
      "datasetId": "CODE_PRIVATE_016",
      "category": "Private Codebase",
      "industry": "Business Operations Platforms",
      "yearsInBusiness": "5.8",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "46",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "CSS",
        "Handlebars",
        "HTML",
        "PHP"
      ],
      "totalLoc": "675288",
      "repos": "1",
      "prs": "6678",
      "avgLocPerPr": "101.1",
      "commits": "21622",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861d5605ae5a9d9ecf4a",
      "collection": "code-repos",
      "title": "COMMERCE_CODEBASE_002",
      "slug": "commerce-codebase-002",
      "url": "/data-catalog/code-repos/commerce-codebase-002",
      "featured": false,
      "datasetId": "CODE_PRIVATE_015",
      "category": "Private Codebase",
      "industry": "Marketplaces, Commerce & Delivery",
      "yearsInBusiness": "4.9",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "15",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "CSS",
        "Blade",
        "PHP",
        "HTML",
        "CoffeeScript",
        "Vuejs Component"
      ],
      "totalLoc": "221176",
      "repos": "1",
      "prs": "324",
      "avgLocPerPr": "682.6",
      "commits": "1176",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861c6ab94adf346de815",
      "collection": "code-repos",
      "title": "CRM_MARTECH_CODEBASE_003",
      "slug": "crm-martech-codebase-003",
      "url": "/data-catalog/code-repos/crm-martech-codebase-003",
      "featured": false,
      "datasetId": "CODE_PRIVATE_014",
      "category": "Private Codebase",
      "industry": "CRM, Sales & Marketing Technology",
      "yearsInBusiness": "6.9",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "18",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Pkl",
        "JavaScript",
        "CSS",
        "Handlebars",
        "HTML",
        "PHP",
        "Python"
      ],
      "totalLoc": "474777",
      "repos": "1",
      "prs": "815",
      "avgLocPerPr": "582.5",
      "commits": "6468",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861beeecffe16117b05d",
      "collection": "code-repos",
      "title": "CRM_MARTECH_CODEBASE_004",
      "slug": "crm-martech-codebase-004",
      "url": "/data-catalog/code-repos/crm-martech-codebase-004",
      "featured": false,
      "datasetId": "CODE_PRIVATE_013",
      "category": "Private Codebase",
      "industry": "CRM, Sales & Marketing Technology",
      "yearsInBusiness": "2.1",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "14",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "CSS",
        "JavaScript",
        "Handlebars",
        "HTML",
        "LuaSwift",
        "C++",
        "Objective-C"
      ],
      "totalLoc": "271385",
      "repos": "2",
      "prs": "436",
      "avgLocPerPr": "622.4",
      "commits": "1723",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861ae924c86953f8783e",
      "collection": "code-repos",
      "title": "ERP_CODEBASE_001",
      "slug": "erp-codebase-001",
      "url": "/data-catalog/code-repos/erp-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_012",
      "category": "Private Codebase",
      "industry": "ERP Systems",
      "yearsInBusiness": "6.5",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "37",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "PHP",
        "CSS",
        "Blade",
        "HTML",
        "Vuejs Component"
      ],
      "totalLoc": "273247",
      "repos": "1",
      "prs": "1273",
      "avgLocPerPr": "214.6",
      "commits": "4361",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986194005faf541baf863",
      "collection": "code-repos",
      "title": "HR_CODEBASE_001",
      "slug": "hr-codebase-001",
      "url": "/data-catalog/code-repos/hr-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_011",
      "category": "Private Codebase",
      "industry": "HR & Workforce Management",
      "yearsInBusiness": "6.2",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "30",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "Blade",
        "CSS",
        "PHP",
        "HTML",
        "TypeScript",
        "Java",
        "Objective-C",
        "Objective-C++",
        "C++"
      ],
      "totalLoc": "368686",
      "repos": "2",
      "prs": "3438",
      "avgLocPerPr": "107.2",
      "commits": "9532",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986195605ae5a9d9ecd3d",
      "collection": "code-repos",
      "title": "COMMERCE_CODEBASE_001",
      "slug": "commerce-codebase-001",
      "url": "/data-catalog/code-repos/commerce-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_010",
      "category": "Private Codebase",
      "industry": "Marketplaces, Commerce & Delivery",
      "yearsInBusiness": "4.6",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "16",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "CSS",
        "PHP",
        "JavaScript",
        "Blade",
        "HTML",
        "Vuejs Component",
        "EJS"
      ],
      "totalLoc": "276993",
      "repos": "1",
      "prs": "473",
      "avgLocPerPr": "585.6",
      "commits": "1945",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998618c471bbf46c9f4942",
      "collection": "code-repos",
      "title": "CRM_MARTECH_CODEBASE_002",
      "slug": "crm-martech-codebase-002",
      "url": "/data-catalog/code-repos/crm-martech-codebase-002",
      "featured": false,
      "datasetId": "CODE_PRIVATE_009",
      "category": "Private Codebase",
      "industry": "CRM, Sales & Marketing Technology",
      "yearsInBusiness": "9.8",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "26",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "CSS",
        "Handlebars",
        "HTML",
        "Groovy",
        "Lua"
      ],
      "totalLoc": "161072",
      "repos": "1",
      "prs": "513",
      "avgLocPerPr": "314",
      "commits": "4325",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861717854c543f936904",
      "collection": "code-repos",
      "title": "HEALTHCARE_CODEBASE_001",
      "slug": "healthcare-codebase-001",
      "url": "/data-catalog/code-repos/healthcare-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_008",
      "category": "Private Codebase",
      "industry": "Healthcare & Wellness",
      "yearsInBusiness": "6.9",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "44",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "Handlebars",
        "CSS",
        "HTML"
      ],
      "totalLoc": "136816",
      "repos": "2",
      "prs": "230",
      "avgLocPerPr": "594.9",
      "commits": "2462",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998616e57f73b05ad1da48",
      "collection": "code-repos",
      "title": "BUSINESS_OPS_CODEBASE_001",
      "slug": "business-ops-codebase-001",
      "url": "/data-catalog/code-repos/business-ops-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_007",
      "category": "Private Codebase",
      "industry": "Business Operations Platforms",
      "yearsInBusiness": "6.3",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "55",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "CSS",
        "Handlebars",
        "TypeScript",
        "HTML",
        "PHP",
        "Java",
        "Objective-C",
        "Objective-C++",
        "C++"
      ],
      "totalLoc": "437435",
      "repos": "3",
      "prs": "1107",
      "avgLocPerPr": "395.2",
      "commits": "8576",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998615e57f73b05ad1d954",
      "collection": "code-repos",
      "title": "CONSTRUCTION_PROPTECH_CODEBASE_001",
      "slug": "construction-proptech-codebase-001",
      "url": "/data-catalog/code-repos/construction-proptech-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_006",
      "category": "Private Codebase",
      "industry": "Construction & Property Technology",
      "yearsInBusiness": "8.3",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "8",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "CSS",
        "TypeScript",
        "HTML",
        "ColdFusion CFScript",
        "ColdFusion",
        "Perl",
        "PHP",
        "ASP",
        "Python",
        "ASP.NET",
        "GroovyKotlin",
        "Java",
        "Swift",
        "Objective-C",
        "C++"
      ],
      "totalLoc": "333780",
      "repos": "3",
      "prs": "111",
      "avgLocPerPr": "3007",
      "commits": "4499",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998614e57f73b05ad1d8c4",
      "collection": "code-repos",
      "title": "TRAVEL_CODEBASE_001",
      "slug": "travel-codebase-001",
      "url": "/data-catalog/code-repos/travel-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_005",
      "category": "Private Codebase",
      "industry": "Travel, Hospitality & Events",
      "yearsInBusiness": "9.7",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "12",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "PHP",
        "HTML",
        "CSS",
        "Blade",
        "JavaScript",
        "XSLTPHP",
        "XSLTJavaScript"
      ],
      "totalLoc": "229391",
      "repos": "4",
      "prs": "1328",
      "avgLocPerPr": "172.7",
      "commits": "8418",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861384235eb50a0dd4a8",
      "collection": "code-repos",
      "title": "CRM_MARTECH_CODEBASE_001",
      "slug": "crm-martech-codebase-001",
      "url": "/data-catalog/code-repos/crm-martech-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_004",
      "category": "Private Codebase",
      "industry": "CRM, Sales & Marketing Technology",
      "yearsInBusiness": "2.9",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "20",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "JavaScript",
        "EJS",
        "CSS",
        "Handlebars",
        "HTML",
        "Kotlin"
      ],
      "totalLoc": "276889",
      "repos": "5",
      "prs": "5056",
      "avgLocPerPr": "54.8",
      "commits": "12698",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998612e57f73b05ad1d7f4",
      "collection": "code-repos",
      "title": "INDUSTRIAL_CODEBASE_001",
      "slug": "industrial-codebase-001",
      "url": "/data-catalog/code-repos/industrial-codebase-001",
      "featured": false,
      "datasetId": "CODE_PRIVATE_003",
      "category": "Private Codebase",
      "industry": "Industrial, Manufacturing & Sustainability",
      "yearsInBusiness": "7.6",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "15",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Kotlin",
        "TypeScript",
        "HTML",
        "CSS",
        "JavaScript",
        "PHP",
        "Web Services Description",
        "XSDSwiftJavaScript",
        "Swift",
        "C++"
      ],
      "totalLoc": "618917",
      "repos": "6",
      "prs": "4601",
      "avgLocPerPr": "134.5",
      "commits": "17225",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a99861131d6f8d8f3cfe0f2",
      "collection": "code-repos",
      "title": "COMMERCE_CODEBASE_003",
      "slug": "commerce-codebase-003",
      "url": "/data-catalog/code-repos/commerce-codebase-003",
      "featured": false,
      "datasetId": "CODE_PRIVATE_002",
      "category": "Private Codebase",
      "industry": "Marketplaces, Commerce & Delivery",
      "yearsInBusiness": "6",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "24",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "Kotlin",
        "Swift",
        "Objective-C",
        "C++"
      ],
      "totalLoc": "449743",
      "repos": "10",
      "prs": "2735",
      "avgLocPerPr": "164.4",
      "commits": "7679",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a998610f41547c318e5d4ee",
      "collection": "code-repos",
      "title": "BUSINESS_OPS_CODEBASE_002",
      "slug": "business-ops-codebase-002",
      "url": "/data-catalog/code-repos/business-ops-codebase-002",
      "featured": false,
      "datasetId": "CODE_PRIVATE_001",
      "category": "Private Codebase",
      "industry": "Business Operations Platforms",
      "yearsInBusiness": "8.6",
      "established": "Not Specified",
      "closed": "Not Specified",
      "employees": "Not Specified",
      "contributors": "40",
      "engineerQuality": "",
      "developmentType": "",
      "primaryLanguages": [
        "PHP",
        "JavaScript",
        "CSS",
        "Blade",
        "HTML",
        "TypeScript",
        "Kotlin",
        "Swift",
        "Objective-C",
        "C++"
      ],
      "totalLoc": "1246755",
      "repos": "2",
      "prs": "6937",
      "avgLocPerPr": "179.7",
      "commits": "17758",
      "testCoverage": "Not Specified",
      "codeAvailability": "Private — Available on Request",
      "yearOfCollection": ""
    },
    {
      "id": "6a9986bee924c86953f8c055",
      "collection": "book-corpora",
      "title": "Quantum Science and Technology Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-quantum-001-v1",
      "url": "/data-catalog/book-corpora/textbook-quantum-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_QUANTUM_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "quantum mechanics",
        "quantum optics",
        "quantum information science",
        "quantum technologies"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "53",
      "unitType": "titles",
      "datasetDescription": "A corpus of 53 course texts and research references in quantum mechanics, quantum optics, quantum information science, and quantum technologies | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9986befa9df117f358606f",
      "collection": "book-corpora",
      "title": "Plasma Science Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-plasma-001-v1",
      "url": "/data-catalog/book-corpora/textbook-plasma-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_PLASMA_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "plasma physics",
        "space plasmas",
        "fusion."
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "32",
      "unitType": "titles",
      "datasetDescription": "A corpus of 32 research references and selected course materials in plasma physics, space plasmas, discharges, fusion, and turbulence | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9986bb84235eb50a0e4faa",
      "collection": "book-corpora",
      "title": "Particle and Nuclear Physics Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-partnucphys-001-v1",
      "url": "/data-catalog/book-corpora/textbook-partnucphys-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_PARTNUCPHYS_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "particle physics",
        "nuclear physics",
        "collider physics",
        "quantum field theory"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "48",
      "unitType": "titles",
      "datasetDescription": "A corpus of 48 course texts and reference materials across particle physics, nuclear physics, collider physics, and quantum field theory foundations | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9986b84005faf541bb2a42",
      "collection": "book-corpora",
      "title": "Optics and Photonics Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-optics-001-v1",
      "url": "/data-catalog/book-corpora/textbook-optics-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_OPTICS_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "optical science",
        "photonics",
        "laser systems",
        "imaging",
        "applied optical engineering"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "113",
      "unitType": "titles",
      "datasetDescription": "A corpus of 113 research reference works and course texts in optical science, photonics, laser systems, imaging, and applied optical engineering | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9986b7f4ac0d8edcf3730a",
      "collection": "book-corpora",
      "title": "Medical Physics and Biophysics Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-medphys-001-v1",
      "url": "/data-catalog/book-corpora/textbook-medphys-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_MEDPHYS_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "medical imaging",
        "radiation physics",
        "biophysical modelling"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "87",
      "unitType": "titles",
      "datasetDescription": "A corpus of 87 research references and course texts covering medical imaging, radiation physics, biophysical modelling, and diagnostic/therapeutic technologies | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9986b6f4ac0d8edcf37210",
      "collection": "book-corpora",
      "title": "Mathematics and Computation Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-mathcomp-001-v1",
      "url": "/data-catalog/book-corpora/textbook-mathcomp-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_MATHCOMP_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "mathematics",
        "mathematical methods",
        "numerical modelling",
        "computational science",
        "applied mathematics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "79",
      "unitType": "titles",
      "datasetDescription": "A corpus of 79 course texts and research references in mathematical methods, numerical modelling, computational science, and applied mathematics | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9986b5f4ac0d8edcf37149",
      "collection": "book-corpora",
      "title": "Materials Science Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-matsci-001-v1",
      "url": "/data-catalog/book-corpora/textbook-matsci-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_MATSCI_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "materials science",
        "physics",
        "semiconductors",
        "nanomaterials",
        "applied materials engineering"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "122",
      "unitType": "titles",
      "datasetDescription": "A corpus of 122 titles including research references and course texts on materials properties, semiconductors, nanomaterials, composites, and applied materials engineering | Publication years covered: 2013–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2013-2024"
    },
    {
      "id": "6a9986b4e57f73b05ad22d64",
      "collection": "book-corpora",
      "title": "Instrumentation and Measurement Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-instr-001-v1",
      "url": "/data-catalog/book-corpora/textbook-instr-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_INSTR_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "instrumentation",
        "measurement methodologies",
        "physics",
        "sensing technologies",
        "imaging systems"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "77",
      "unitType": "titles",
      "datasetDescription": "A corpus of 77 titles including research references and course texts covering scientific instrumentation, sensing technologies, imaging systems, and measurement methodologies | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9986b3dbd7e1180eb92964",
      "collection": "book-corpora",
      "title": "Environment and Energy Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-enviro-001-v1",
      "url": "/data-catalog/book-corpora/textbook-enviro-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_ENVIRO_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "environmental science",
        "energy systems",
        "physics",
        "sustainability",
        "environmental modelling"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "47",
      "unitType": "titles",
      "datasetDescription": "A corpus of 47 titles including research references, broad‑interest texts, and selected course materials focused on energy systems, sustainability, atmospheric physics, and environmental modelling | Publication years covered: 2013–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2013-2024"
    },
    {
      "id": "6a9985d4946e817c7d6368c1",
      "collection": "book-corpora",
      "title": "Engineering Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-engine-001-v1",
      "url": "/data-catalog/book-corpora/textbook-engine-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_ENGINE_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "engineering",
        "physics",
        "electronics",
        "electrodynamics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "26",
      "unitType": "titles",
      "datasetDescription": "A corpus of 26 titles including course‑level and research‑level engineering texts across electronics, electrodynamics, systems engineering, and emerging technology domains | Publication years covered: 2019–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2019-2024"
    },
    {
      "id": "6a9985d3eeecffe1611782d8",
      "collection": "book-corpora",
      "title": "Education and Outreach Broad Interest and Research Reference Text Corpusq",
      "slug": "textbook-educom-001-v1",
      "url": "/data-catalog/book-corpora/textbook-educom-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_EDUCOM_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "science education",
        "science communication",
        "pedagogy",
        "learning design",
        "professional development for scientists"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "25",
      "unitType": "titles",
      "datasetDescription": "A corpus of 25 texts on physics education, science communication, pedagogy, learning design, and professional development for scientists | Publication years covered: 2015–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2015-2024"
    },
    {
      "id": "6a9985d2f4ac0d8edcf329ee",
      "collection": "book-corpora",
      "title": "Culture, History and Society Broad Interest Text and Research Reference Text Corpus",
      "slug": "textbook-culhissoc-001-v1",
      "url": "/data-catalog/book-corpora/textbook-culhissoc-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_CULHISSOC_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "culture, history, and society",
        "history of science"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "25",
      "unitType": "titles",
      "datasetDescription": "A corpus of 25 titles including broad‑interest and selected reference texts exploring the intersections of physics, history, culture, ethics, and society | Publication years covered: 2015–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2015-2024"
    },
    {
      "id": "6a9985d16d858e464b65ec35",
      "collection": "book-corpora",
      "title": "Condensed Matter Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-condmat-001-v1",
      "url": "/data-catalog/book-corpora/textbook-condmat-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_CONDMAT_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "condensed matter",
        "materials properties"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "36",
      "unitType": "titles",
      "datasetDescription": "A corpus of 36 titles including reference works and course texts in condensed matter physics, including materials properties, low‑temperature physics, and many‑body theory | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9985d09ec510f7c32836d0",
      "collection": "book-corpora",
      "title": "Classical Physics Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-clasphys-001-v1",
      "url": "/data-catalog/book-corpora/textbook-clasphys-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_CLASPHYS_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "classical physics",
        "mechanics",
        "acoustics",
        "statistical physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "45",
      "unitType": "titles",
      "datasetDescription": "A corpus of 45 educational and reference texts in mechanics, thermodynamics, acoustics, and statistical physics | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9985cff4c0365c95ae0fc5",
      "collection": "book-corpora",
      "title": "Biomedical Engineering Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-biomed-001-v1",
      "url": "/data-catalog/book-corpora/textbook-biomed-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_BIOMED_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "biomedical engineering",
        "biophysics",
        "imaging sciences"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "50",
      "unitType": "titles",
      "datasetDescription": "A corpus of 50 titles including research references and course texts across biomedical engineering, biophysics, imaging sciences, and biosystems modelling | Publication years covered: 2014–2024",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2024"
    },
    {
      "id": "6a9985cf57206d63ef253148",
      "collection": "book-corpora",
      "title": "Atomic and Molecular Physics Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-atom-001-v1",
      "url": "/data-catalog/book-corpora/textbook-atom-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_ATOM_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "atomic and molecular physics",
        "spectroscopy",
        "molecular theory"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "32",
      "unitType": "titles",
      "datasetDescription": "A corpus of 32 titles including textbooks and research references covering AMO physics, spectroscopy, and molecular theory | Publication years covered: 2014–2023",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2023"
    },
    {
      "id": "6a9985cdeeecffe161178046",
      "collection": "book-corpora",
      "title": "Astronomy and Astrophysics Course Textbook and Research Reference Text Corpus",
      "slug": "textbook-astro-001-v1",
      "url": "/data-catalog/book-corpora/textbook-astro-001-v1",
      "featured": false,
      "datasetId": "TEXTBOOK_ASTRO_001_v1",
      "language": "English",
      "productType": "Academic Course Textbooks and Research Reference Texts",
      "domains": [
        "astronomy",
        "astrophysics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "37",
      "unitType": "titles",
      "datasetDescription": "A corpus of 37 titles including course‑level textbooks, research references, and broad‑interest works in astronomy and astrophysics | Includes materials spanning cosmology, stellar and galactic physics, and gravitational theory | Publication years covered: 2014–2022",
      "source": "Third Party Vendor",
      "yearOfCollection": "2014-2022"
    },
    {
      "id": "6a9985cdf4c0365c95ae0ede",
      "collection": "book-corpora",
      "title": "Quantum Science and Technology Academic Journal Corpus",
      "slug": "journ-quantum-001-v1",
      "url": "/data-catalog/book-corpora/journ-quantum-001-v1",
      "featured": false,
      "datasetId": "JOURN_QUANTUM_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "quantum science and technology",
        "plasma science",
        "optics and photonics",
        "atomic and molecular physics",
        "mathematical physics",
        "particle physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "214704292",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 214.7 million words | Primary content delivered in XML with accompanying PDF text | Contains research across quantum science, quantum information, and quantum technologies | Publication years covered: 1986–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1986-2025"
    },
    {
      "id": "6a9985ccc471bbf46c9f3adc",
      "collection": "book-corpora",
      "title": "Plasma Science Academic Journal Corpus",
      "slug": "journ-plasma-001-v1",
      "url": "/data-catalog/book-corpora/journ-plasma-001-v1",
      "featured": false,
      "datasetId": "JOURN_PLASMA_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "plasma science"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "47230514",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 47.2 million words | Primary content delivered in XML with accompanying PDF text | Contains research across plasma physics and fusion science | Publication years covered: 1959–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1959-2025"
    },
    {
      "id": "6a9985cbbc894a1ebfd3dd73",
      "collection": "book-corpora",
      "title": "Particle Physics Academic Journal Corpus",
      "slug": "journ-partphys-001-v1",
      "url": "/data-catalog/book-corpora/journ-partphys-001-v1",
      "featured": false,
      "datasetId": "JOURN_PARTPHYS_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "particle physics",
        "nuclear physics",
        "plasma science",
        "atomic and molecular physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "153733987",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 153.7 million words | Primary content delivered in XML with accompanying PDF text | Contains research across particle physics and high‑energy interactions | Publication years covered: 1968–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1968-2025"
    },
    {
      "id": "6a9985cad3a0ae3d29784521",
      "collection": "book-corpora",
      "title": "Optics and Photonics Academic Journal Corpus",
      "slug": "journ-optics-001-v1",
      "url": "/data-catalog/book-corpora/journ-optics-001-v1",
      "featured": false,
      "datasetId": "JOURN_OPTICS_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "optics and photonics",
        "nanoscience",
        "materials science",
        "atomic and molecular physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "224120477",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 224.1 million words | Primary content delivered in XML with accompanying PDF text | Contains research in optics, photonics, and laser science | Publication years covered: 1962–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1962-2025"
    },
    {
      "id": "6a9985c95605ae5a9d9ebc59",
      "collection": "book-corpora",
      "title": "Nuclear Physics Academic Journal Corpus",
      "slug": "journ-nucphys-001-v1",
      "url": "/data-catalog/book-corpora/journ-nucphys-001-v1",
      "featured": false,
      "datasetId": "JOURN_NUCPHYS_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "nuclear physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "9637070",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 9.6 million words | Primary content delivered in XML with accompanying PDF text | Contains research across nuclear physics, nuclear structure, and heavy‑ion science | Publication years covered: 1970–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1970-2025"
    },
    {
      "id": "6a9985c8c471bbf46c9f3936",
      "collection": "book-corpora",
      "title": "Nanoscience Academic Journal Corpus",
      "slug": "journ-nano-001-v1",
      "url": "/data-catalog/book-corpora/journ-nano-001-v1",
      "featured": false,
      "datasetId": "JOURN_NANO_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "nanoscience",
        "materials science",
        "engineering",
        "optics and photonics",
        "quantum science",
        "condensed matter"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "181373387",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 181.4 million words | Primary content delivered in XML with accompanying PDF text | Contains nanoscale science and nanotechnology research | Publication years covered: 1990–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1990-2025"
    },
    {
      "id": "6a9985c7afc3cfd64e660739",
      "collection": "book-corpora",
      "title": "Medical Physics Academic Journal Corpus",
      "slug": "journ-medphys-001-v1",
      "url": "/data-catalog/book-corpora/journ-medphys-001-v1",
      "featured": false,
      "datasetId": "JOURN_MEDPHYS_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "medical physics",
        "bioengineering",
        "instrumentation and measurement",
        "biophysics",
        "machine learning and AI",
        "materials science"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "200978032",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 200.9 million words | Primary content delivered in XML with accompanying PDF text | Contains research across medical physics, diagnostic imaging, and therapeutic applications | Publication years covered: 1956–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1956-2025"
    },
    {
      "id": "6a9985c6e6ee6e81af9a4374",
      "collection": "book-corpora",
      "title": "Mathematical Physics Academic Journal Corpus",
      "slug": "journ-matphys-001-v1",
      "url": "/data-catalog/book-corpora/journ-matphys-001-v1",
      "featured": false,
      "datasetId": "JOURN_MATPHYS_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "mathematical physics",
        "computational science",
        "materials science"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "247742408",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 247.7 million words | Primary content delivered in XML with accompanying PDF text | Contains research across mathematical and theoretical physics | Publication years covered: 1971–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1971-2025"
    },
    {
      "id": "6a9985c5d80c25273cfea29b",
      "collection": "book-corpora",
      "title": "Materials Science Academic Journal Corpus",
      "slug": "journ-matsci-001-v1",
      "url": "/data-catalog/book-corpora/journ-matsci-001-v1",
      "featured": false,
      "datasetId": "JOURN_MATSCI_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "material science",
        "engineering",
        "condensed matter",
        "mathematical physics",
        "quantum science",
        "nanoscience",
        "computational science"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "480523734",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 480.5 million words | Primary content delivered in XML with accompanying PDF text | Contains peer‑reviewed research across materials science and applied materials engineering | Publication years covered: 1986–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1986-2025"
    },
    {
      "id": "6a9985c4e57f73b05ad1a982",
      "collection": "book-corpora",
      "title": "Machine Learning and AI Academic Journal Corpus",
      "slug": "journ-mlai-001-v1",
      "url": "/data-catalog/book-corpora/journ-mlai-001-v1",
      "featured": false,
      "datasetId": "JOURN_MLAI_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "machine learning and AI",
        "computational science"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "121772",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 121,772 words | Primary content delivered in XML with accompanying PDF text | Contains research across machine learning, applied AI, and computational intelligence | Publication years covered: 1985–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1985-2025"
    },
    {
      "id": "6a9985c317956efcbddbda0a",
      "collection": "book-corpora",
      "title": "Instrumentation and Measurement Academic Journal Corpus",
      "slug": "journ-instr-001-v1",
      "url": "/data-catalog/book-corpora/journ-instr-001-v1",
      "featured": false,
      "datasetId": "JOURN_INSTR_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "instrumentation and measurement",
        "engineering,"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "105557571",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 105.5 million words | Primary content delivered in XML with accompanying PDF text | Contains research across scientific instrumentation, measurement science, and sensor technologies | Publication years covered: 1970–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1970-2025"
    },
    {
      "id": "6a9985c257206d63ef252837",
      "collection": "book-corpora",
      "title": "Environmental and Earth Science Academic Journal Corpus",
      "slug": "journ-enviro-001-v1",
      "url": "/data-catalog/book-corpora/journ-enviro-001-v1",
      "featured": false,
      "datasetId": "JOURN_ENVIRO_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "environmental and earth science",
        "mathematical physics",
        "nuclear physics",
        "machine learning and AI",
        "energy and sustainability",
        "engineering",
        "quantum science",
        "instrumentation and measurement",
        "computational science",
        "medical physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "523060382",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 523 million words | Primary content delivered in XML with accompanying PDF text | Contains research across environmental science, climate science, and earth systems | Publication years covered: 1981–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1981-2025"
    },
    {
      "id": "6a9985c1040b22801498e5ab",
      "collection": "book-corpora",
      "title": "Engineering Academic Journal Corpus",
      "slug": "journ-engine-001-v1",
      "url": "/data-catalog/book-corpora/journ-engine-001-v1",
      "featured": false,
      "datasetId": "JOURN_ENGINE_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "engineering",
        "instrumentation and measurement",
        "materials science",
        "computational science",
        "machine learning and AI",
        "mathematical physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "220209447",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 220.2 million words | Primary content delivered in XML with accompanying PDF text | Contains research across applied engineering and scientific instrumentation | Publication years covered: 1973–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1973-2025"
    },
    {
      "id": "6a9985c084235eb50a0d991f",
      "collection": "book-corpora",
      "title": "Education and Communication Academic Journal Corpus",
      "slug": "journ-educom-001-v1",
      "url": "/data-catalog/book-corpora/journ-educom-001-v1",
      "featured": false,
      "datasetId": "JOURN_EDUCOM_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "education and communication",
        "mathematical physics",
        "quantum science"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "46781341",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 46.7 million words | Primary content delivered in XML with accompanying PDF text | Contains research in physics education, pedagogy, and scientific communication | Publication years covered: 1966–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1966-2025"
    },
    {
      "id": "6a9985bf57206d63ef2522ff",
      "collection": "book-corpora",
      "title": "Condensed Matter Academic Journal Corpus",
      "slug": "journ-condmat-001-v1",
      "url": "/data-catalog/book-corpora/journ-condmat-001-v1",
      "featured": false,
      "datasetId": "JOURN_CONDMAT_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "condensed matter",
        "atomic and molecular physics",
        "quantum science",
        "materials science",
        "nanoscience",
        "environmental and earth science",
        "particle physics",
        "optics and photonics",
        "plasma science",
        "instrumentation and measurement",
        "energy and sustainability"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "1182510615",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 1.1 billion words | Primary content delivered in XML with accompanying PDF text | Contains peer‑reviewed research in condensed matter and solid‑state physics | Publication years covered: 1930–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1930-2025"
    },
    {
      "id": "6a9985bed3f7db2e71792013",
      "collection": "book-corpora",
      "title": "Computational Science Academic Journal Corpus",
      "slug": "journ-compsci-001-v1",
      "url": "/data-catalog/book-corpora/journ-compsci-001-v1",
      "featured": false,
      "datasetId": "JOURN_COMPSCI_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "computational science",
        "mathematical physics",
        "machine learning and AI",
        "quantum science"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "177177662",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 117.1 million words | Primary content delivered in XML with accompanying PDF text | Contains research across computational modelling, numerical analysis, and scientific computing | Publication years covered: 1985–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1985-2025"
    },
    {
      "id": "6a9985bdf4c0365c95ae087b",
      "collection": "book-corpora",
      "title": "Bioengineering Academic Journal Corpus",
      "slug": "journ-bioeng-001-v1",
      "url": "/data-catalog/book-corpora/journ-bioeng-001-v1",
      "featured": false,
      "datasetId": "JOURN_BIOENG_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "bioengineering",
        "medical physics",
        "materials science",
        "biophysics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "95477487",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 95.4 million words |Primary content delivered in XML with accompanying PDF text | Contains research across biomedical engineering, biophysics, and biological instrumentation | Publication years covered: 1956–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1956-2025"
    },
    {
      "id": "6a9985bce57f73b05ad1a50b",
      "collection": "book-corpora",
      "title": "Atomic and Molecular Physics Academic Journal Corpus",
      "slug": "journ-atom-001-v1",
      "url": "/data-catalog/book-corpora/journ-atom-001-v1",
      "featured": false,
      "datasetId": "JOURN_ATOM_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "atomic and molecular physics",
        "quantum science",
        "mathematical physics",
        "optics and photonics",
        "particle physics",
        "nuclear physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "1101573069",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 1.1 billion words | Primary content delivered in XML with accompanying PDF text | Contains research in atomic, molecular, and optical physics | Publication years covered: 1899–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1899-2025"
    },
    {
      "id": "6a9985bbf41547c318e59454",
      "collection": "book-corpora",
      "title": "Astronomy and Astrophysics Academic Journal Corpus",
      "slug": "journ-astro-001-v1",
      "url": "/data-catalog/book-corpora/journ-astro-001-v1",
      "featured": false,
      "datasetId": "JOURN_ASTRO_001_v1",
      "language": "English",
      "productType": "Academic Journals",
      "domains": [
        "astronomy",
        "astrophysics",
        "particle physics",
        "nuclear physics",
        "quantum science",
        "mathematical physics"
      ],
      "dataFormat": [
        "XML",
        "PDF",
        "jpg"
      ],
      "volume": "320785427",
      "unitType": "words",
      "datasetDescription": "A corpus of academic journals containing 320.7 million words | Primary content delivered in XML with accompanying PDF text | Contains peer‑reviewed research in astronomy, astrophysics, and cosmology | Publication years covered: 1984–2025",
      "source": "Third Party Vendor",
      "yearOfCollection": "1984-2025"
    },
    {
      "id": "6a998785811b8e5d7361bafb",
      "collection": "audio-catalogue",
      "title": "English (United States) conversational smartphone",
      "slug": "use-asr008",
      "url": "/data-catalog/audio-catalogue/use-asr008",
      "featured": true,
      "datasetId": "USE_ASR008",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "2.53",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Two participants recorded themselves on a smartphone having a 10-15 minute natural conversation on a selected topic, e.g. Hobbies, History. Includes some AAVE participants and some toxic speech.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a998784834e4fbc0a91d49c",
      "collection": "audio-catalogue",
      "title": "English (United States) answers to questions",
      "slug": "use-asr007",
      "url": "/data-catalog/audio-catalogue/use-asr007",
      "featured": true,
      "datasetId": "USE_ASR007",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "50.4",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Participants recorded themselves on a smartphone answering prompted questions, e.g. \"What's your favourite food?\". There were 100 prompts per session, and 1000 unique prompts across the whole collection.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a99878317956efcbddcb4c3",
      "collection": "audio-catalogue",
      "title": "English (United States) device commands",
      "slug": "use-asr006",
      "url": "/data-catalog/audio-catalogue/use-asr006",
      "featured": true,
      "datasetId": "USE_ASR006",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "30.89",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Participants recorded themselves on a smartphone saying device commands in response to a prompt, e.g. \"Tell the device to disable shuffle mode\". There were 94 prompts per session, and 280 unique prompts across the whole collection.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a998782e924c86953f93bc7",
      "collection": "audio-catalogue",
      "title": "English (United States) scripted sentences",
      "slug": "use-asr005",
      "url": "/data-catalog/audio-catalogue/use-asr005",
      "featured": true,
      "datasetId": "USE_ASR005",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "244.09",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Participants recorded themselves on a smartphone reading out prompted sentences. There were 96 prompts per session, and 9000 unique sentences across the whole collection.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a998781bc894a1ebfd41fda",
      "collection": "audio-catalogue",
      "title": "Cantonese (China) business dialogues",
      "slug": "yydh-asr001-cn",
      "url": "/data-catalog/audio-catalogue/yydh-asr001-cn",
      "featured": false,
      "datasetId": "YYDH_ASR001_CN",
      "locale": [
        "yhu-CN"
      ],
      "country": "China",
      "languageGroup": "Cantonese",
      "audioType": "Conversational Speech",
      "domainContent": [
        "Business Meetings"
      ],
      "volume": "98.35",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Business meetings and conversations audio with transcription and timestamping, from a variety of industries. ; 30% male participants, 70% female",
      "source": "Appen China",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a99878017956efcbddcb406",
      "collection": "audio-catalogue",
      "title": "Arabic (Levantine) scripted microphone",
      "slug": "aru-asr002",
      "url": "/data-catalog/audio-catalogue/aru-asr002",
      "featured": false,
      "datasetId": "ARU_ASR002",
      "locale": [
        "ar-AR"
      ],
      "country": "United Arab Emirates",
      "languageGroup": "Arabic",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "32",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Studio-recording scripted audio with corresponding text prompts. Sessions were approx 20 mins long with 210 prompts per session. Levantine Arabic speakers from Syria, Lebanon, Palestine and Jordan. Prompts include yes/no questions and answers, open-ended questions and answers, brand/company names, addresses, points of interest, medicine/disease names, synthetic person names, media names (TV, movies, books etc), synthesised digit strings (phone number, credit card, PIN number, time, date), and phonetically rich sentences. Transcription can be developed upon request.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2023"
      ]
    },
    {
      "id": "6a99877faa89b6c9886e0702",
      "collection": "audio-catalogue",
      "title": "Russian + German Female TTS",
      "slug": "ed-tts001-cn",
      "url": "/data-catalog/audio-catalogue/ed-tts001-cn",
      "featured": false,
      "datasetId": "ED_TTS001_CN",
      "locale": [
        "ru-RU",
        "de-DE"
      ],
      "country": "Russia/Germany",
      "languageGroup": "Russian/German",
      "audioType": "TTS Scripted Speech",
      "domainContent": [
        "Text-to-Speech Voice Talent"
      ],
      "volume": "2.32",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "microphone",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Audio with transcription. Female voice talent recorded in a professional studio on a Neumann U87 microphone; SNR of 40-50dB",
      "source": "Appen China",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a99877e6ab94adf346eae84",
      "collection": "audio-catalogue",
      "title": "Indonesian (Indonesia) conversational telephony",
      "slug": "ind-dh-asr001-cn",
      "url": "/data-catalog/audio-catalogue/ind-dh-asr001-cn",
      "featured": false,
      "datasetId": "IND_DH_ASR001_CN",
      "locale": [
        "id-ID"
      ],
      "country": "Indonesia",
      "languageGroup": "Indonesian",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "150",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Audio with transcription and timestamping.",
      "source": "Appen China",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a99877ec8ebe72e2d9e9a33",
      "collection": "audio-catalogue",
      "title": "Turkish (Turkey) scripted smartphone",
      "slug": "tur-asr003-cn",
      "url": "/data-catalog/audio-catalogue/tur-asr003-cn",
      "featured": false,
      "datasetId": "TUR_ASR003_CN",
      "locale": [
        "tr-TR"
      ],
      "country": "Turkey",
      "languageGroup": "Turkish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "738",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Audio with corresponding text prompts. Participants recorded on mobile phone reading aloud about 40 sentence prompts each.",
      "source": "Appen China",
      "yearOfCollection": [
        "2023"
      ]
    },
    {
      "id": "6a99877ce6ee6e81af9b274a",
      "collection": "audio-catalogue",
      "title": "GlobalPhone Multilingual Text & Speech Database",
      "slug": "globalphone",
      "url": "/data-catalog/audio-catalogue/globalphone",
      "featured": false,
      "datasetId": "GLOBALPHONE",
      "locale": [],
      "country": "Global coverage",
      "languageGroup": "Multilanguage",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech, national/international political and economic news articles)"
      ],
      "volume": "450",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Global Phone multilingual corpus, languages can be sold separately or in multi-language packages. Tiered package pricing available. ; GLOBALPHONE provides multilingual speech and text data in 20 Languages: Arabic, Bulgarian, Chinese-Mandarin, Chinese-Shanghai, Croatian, Czech, French, German, Hausa, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Swedish, Tamil, Thai, Turkish, and Vietnamese. ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form; In each language, news article sentences were read by about 100 native speakers. The articles cover national and international political news, as well as economic news from 1995-2011. The speech is available in 16bit, 16kHz mono quality recorded with a close-speaking microphone and the same recording equipment was used for all languages. ; Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996",
        "1997",
        "1998",
        "1999",
        "2000",
        "2001",
        "2002",
        "2003",
        "2004",
        "2005",
        "2006",
        "2007",
        "2008",
        "2009",
        "2010",
        "2011"
      ]
    },
    {
      "id": "6a99877baa89b6c9886e0587",
      "collection": "audio-catalogue",
      "title": "English (United States) Ultra High-Volume labeled speech",
      "slug": "use-uhv001",
      "url": "/data-catalog/audio-catalogue/use-uhv001",
      "featured": false,
      "datasetId": "USE_UHV001",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Broadcast Speech",
      "domainContent": [
        "Agriculture & plants",
        "Animals & Pets",
        "Art & Culture",
        "Beauty & Fashion",
        "Career",
        "Clothing",
        "Education",
        "Entertainment",
        "Family & Relationships",
        "Finance & Insurance",
        "Food",
        "Health",
        "History",
        "Hospitality",
        "Legal",
        "Leisure",
        "News & Politics",
        "Religion & Spirituality",
        "Retail",
        "Science & Technology",
        "Social Networks",
        "Sports",
        "Telecom",
        "Travel",
        "Weather",
        "Others"
      ],
      "volume": "1196",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Customised packaging available ;High quality labelled speech datasets of web-sourced licensable broadcast audio data, curated to ensure representative speaker demographic distributions, and filtered through human quality checks. ; 12.6M total words ; Utterance-level labelling includes: speech transcription, accent identification, speaker identification, verification, gender and age-group detection, domain classification. ;Domains include: Agriculture & plants, Animals & Pets, Art & Culture, Beauty & Fashion, Career, Clothing, Education, Entertainment, Family & Relationships, Finance & Insurance, Food, Health, History, Hospitality, Legal, Leisure, News & Politics, Religion & Spirituality, Retail, Science & Technology, Social Networks, Sports, Telecom, Travel, Weather, Others",
      "source": "Appen Global",
      "yearOfCollection": [
        "2022"
      ]
    },
    {
      "id": "6a99877a84235eb50a0ee185",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) conversational smartphone",
      "slug": "ita-asr005",
      "url": "/data-catalog/audio-catalogue/ita-asr005",
      "featured": false,
      "datasetId": "ITA_ASR005",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "Conversational Speech",
      "domainContent": [
        "clothing",
        "culture",
        "education",
        "finance",
        "food",
        "health",
        "history",
        "hospitality",
        "insurance",
        "media/entertainment",
        "sports",
        "travel/holiday",
        "weather and work"
      ],
      "volume": "256",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed (home, car, public place, outdoor)",
      "datasetDescription": "Dataset is fully transcribed and time stamped ; Two person conversations covering a broad range of generic topics including clothing, culture, education, finance, food, health, history, hospitality, insurance, media/entertainment, sports, travel/holiday, weather and work. ; Each speaker participates in up to 12 conversations that are 5-15 minutes long. ;Pronunciation lexicon not currently available but can be developed upon request",
      "source": "Appen Global",
      "yearOfCollection": [
        "2021"
      ]
    },
    {
      "id": "6a9987799ec510f7c328e318",
      "collection": "audio-catalogue",
      "title": "French (France) conversational smartphone",
      "slug": "frf-asr004",
      "url": "/data-catalog/audio-catalogue/frf-asr004",
      "featured": false,
      "datasetId": "FRF_ASR004",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "audioType": "Conversational Speech",
      "domainContent": [
        "clothing",
        "culture",
        "education",
        "finance",
        "food",
        "health",
        "history",
        "hospitality",
        "insurance",
        "media/entertainment",
        "sports",
        "travel/holiday",
        "weather and work"
      ],
      "volume": "159",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed (home, car, public place, outdoor)",
      "datasetDescription": "Dataset is fully transcribed and time stamped ; Two person conversations covering a broad range of generic topics including clothing, culture, education, finance, food, health, history, hospitality, insurance, media/entertainment, sports, travel/holiday, weather and work. ; Each speaker participates in up to 12 conversations that are 5-15 minutes long. ;Pronunciation lexicon not currently available but can be developed upon request",
      "source": "Appen Global",
      "yearOfCollection": [
        "2021"
      ]
    },
    {
      "id": "6a998778d3a0ae3d297911ee",
      "collection": "audio-catalogue",
      "title": "Spanish (Spain) conversational smartphone",
      "slug": "esp-asr003",
      "url": "/data-catalog/audio-catalogue/esp-asr003",
      "featured": false,
      "datasetId": "ESP_ASR003",
      "locale": [
        "es-ES"
      ],
      "country": "Spain",
      "languageGroup": "Spanish",
      "audioType": "Conversational Speech",
      "domainContent": [
        "clothing",
        "culture",
        "education",
        "finance",
        "food",
        "health",
        "history",
        "hospitality",
        "insurance",
        "media/entertainment",
        "sports",
        "travel/holiday",
        "weather and work"
      ],
      "volume": "223",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed (home, car, public place, outdoor)",
      "datasetDescription": "Dataset is fully transcribed and time stamped ; Two person conversations covering a broad range of generic topics including clothing, culture, education, finance, food, health, history, hospitality, insurance, media/entertainment, sports, travel/holiday, weather and work. ; Each speaker participates in up to 12 conversations that are 5-15 minutes long. ;Pronunciation lexicon not currently available but can be developed upon request",
      "source": "Appen Global",
      "yearOfCollection": [
        "2021"
      ]
    },
    {
      "id": "6a99877717854c543f93cca3",
      "collection": "audio-catalogue",
      "title": "German (Germany) conversational smartphone",
      "slug": "deu-asr004",
      "url": "/data-catalog/audio-catalogue/deu-asr004",
      "featured": false,
      "datasetId": "DEU_ASR004",
      "locale": [
        "de-DE"
      ],
      "country": "Germany",
      "languageGroup": "German",
      "audioType": "Conversational Speech",
      "domainContent": [
        "clothing",
        "culture",
        "education",
        "finance",
        "food",
        "health",
        "history",
        "hospitality",
        "insurance",
        "media/entertainment",
        "sports",
        "travel/holiday",
        "weather and work"
      ],
      "volume": "104",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed (home, car, public place, outdoor)",
      "datasetDescription": "Dataset is fully transcribed and time stamped ; Two person conversations covering a broad range of generic topics including clothing, culture, education, finance, food, health, history, hospitality, insurance, media/entertainment, sports, travel/holiday, weather and work. ; Each speaker participates in up to 12 conversations that are 5-15 minutes long. ;Pronunciation lexicon not currently available but can be developed upon request",
      "source": "Appen Global",
      "yearOfCollection": [
        "2021"
      ]
    },
    {
      "id": "6a998776f5674eee522c7e64",
      "collection": "audio-catalogue",
      "title": "English (United States - African American) conversational smartphone",
      "slug": "use-asr004",
      "url": "/data-catalog/audio-catalogue/use-asr004",
      "featured": false,
      "datasetId": "USE_ASR004",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "clothing",
        "culture",
        "education",
        "finance",
        "food",
        "health",
        "history",
        "hospitality",
        "insurance",
        "media/entertainment",
        "sports",
        "travel/holiday",
        "weather and work"
      ],
      "volume": "50",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed (home, car, public place, outdoor)",
      "datasetDescription": "Dataset is fully transcribed and time stamped ; Two person conversations recorded on a smartphone covering a broad range of generic topics including clothing, culture, education, finance, food, health, history, hospitality, insurance, media/entertainment, sports, travel/holiday, weather and work. ; Each speaker participates in up to 12 conversations that are 5-15 minutes long. ;Pronunciation lexicon not currently available but can be developed upon request",
      "source": "Appen Global",
      "yearOfCollection": [
        "2021"
      ]
    },
    {
      "id": "6a998776040b22801499d9e2",
      "collection": "audio-catalogue",
      "title": "English (India) conversational smartphone",
      "slug": "eni-asr003",
      "url": "/data-catalog/audio-catalogue/eni-asr003",
      "featured": false,
      "datasetId": "ENI_ASR003",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "clothing",
        "culture",
        "education",
        "finance",
        "food",
        "health",
        "history",
        "hospitality",
        "insurance",
        "media/entertainment",
        "sports",
        "travel/holiday",
        "weather and work"
      ],
      "volume": "143",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed (home, car, public place, outdoor)",
      "datasetDescription": "Dataset is fully transcribed and time stamped ; Two person conversations covering a broad range of generic topics including clothing, culture, education, finance, food, health, history, hospitality, insurance, media/entertainment, sports, travel/holiday, weather and work. ; Each speaker participates in up to 12 conversations that are 5-15 minutes long. ;Pronunciation lexicon not currently available but can be developed upon request",
      "source": "Appen Global",
      "yearOfCollection": [
        "2021"
      ]
    },
    {
      "id": "6a998775811b8e5d7361b8ec",
      "collection": "audio-catalogue",
      "title": "Chinese (multinational foreigner) scripted smartphone",
      "slug": "foreigner-asr001-cn",
      "url": "/data-catalog/audio-catalogue/foreigner-asr001-cn",
      "featured": false,
      "datasetId": "FOREIGNER_ASR001_CN",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Mandarin Chinese",
      "audioType": "Scripted Speech",
      "domainContent": [
        "Non-native Chinese Speech"
      ],
      "volume": "200",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset contains audio with corresponding text prompts. ; This database contains 200 hours of foreigners speaking Chinese from the following countries: Argentina, Egypt, Australia, Russia, the Philippines, Kazakhstan, Korea, Kyrgyzstan, Canada, Kuala Lumpur, Kenya, Laos, Malaysia, Mauritius, the United States, Mongolia, South Africa, Japan, Tajikistan, Thailand, Turkey, Hong Kong, Singapore, India, Indonesia, Vietnam ; There is no data from South Korea, Brazil, or data recorded by minors.; Each session lasts about an hour; sentence duration ranges between 3-10 seconds ; The content is in the form of an individual reading while being recorded on a mobile phone in a home/office environment. ; Sensitive data and personal information has been scrubbed.",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a9987744005faf541bb3dd1",
      "collection": "audio-catalogue",
      "title": "Wuhan dialect (China) Conversational Speech",
      "slug": "wuhan-asr002-cn",
      "url": "/data-catalog/audio-catalogue/wuhan-asr002-cn",
      "featured": false,
      "datasetId": "WUHAN_ASR002_CN",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Wuhan dialect",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General Conversational Speech"
      ],
      "volume": "58.6",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Audio with transcription. ; Audio recordings cover 5 districts of Wuhan: Jiang 'an, Jianghan, Qiao Kou, Hanyang and Wuchang ;Northeast suburb accents not included, and no minors were recorded. ; Each recording session contains 20-30 minutes of free dialogue between 2-5 people.; Sensitive data and personal information has been scrubbed.",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a9987736ab94adf346ea8d2",
      "collection": "audio-catalogue",
      "title": "Wuhan dialect (China) Conversational Speech",
      "slug": "wuhan-asr001-cn",
      "url": "/data-catalog/audio-catalogue/wuhan-asr001-cn",
      "featured": false,
      "datasetId": "WUHAN_ASR001_CN",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Wuhan dialect",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General Conversational Speech"
      ],
      "volume": "44.71",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Recording pen/microphone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Audio with transcription. ; Audio recordings cover 5 districts of Wuhan: Jiang 'an, Jianghan, Qiao Kou, Hanyang and Wuchang ;Northeast suburb accents not included, and no minors were recorded. ; Each recording session contains 20-30 minutes of free dialogue between 2-5 people.; Sensitive data and personal information has been scrubbed.",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a998772991d16e5e66e3dd7",
      "collection": "audio-catalogue",
      "title": "Dongbei dialect (China) Conversational Speech",
      "slug": "dongbei-asr002-cn",
      "url": "/data-catalog/audio-catalogue/dongbei-asr002-cn",
      "featured": false,
      "datasetId": "DONGBEI_ASR002_CN",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Dongbei dialect",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General Conversational Speech"
      ],
      "volume": "75.2",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Audio with transcription. ; Audio recordings cover 19 districts: Shenyang Heping District, Shenhe District, Huanggu District, Dadong District, Tiexi District, Lvyuan District, Chaoyang District, Kuancheng District, Erdao District, Nanguan District, Daoli District, Nangang District, Daowai District, Pingfang District, Songbei District, Xiangfang District, Hulan District, Acheng District and Shuangcheng District ;Northeast suburb accents not included, and no minors were recorded. ; Each recording session contains 20-30 minutes of free dialogue between 2-5 people.; Sensitive data and personal information has been scrubbed.",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a99877131b4728186af16ed",
      "collection": "audio-catalogue",
      "title": "Dongbei dialect (China) Conversational Speech",
      "slug": "dongbei-asr001-cn",
      "url": "/data-catalog/audio-catalogue/dongbei-asr001-cn",
      "featured": false,
      "datasetId": "DONGBEI_ASR001_CN",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Dongbei dialect",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General Conversational Speech"
      ],
      "volume": "84.6",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Recording pen/microphone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Audio with transcription ; Audio recordings cover 19 districts: Shenyang Heping District, Shenhe District, Huanggu District, Dadong District, Tiexi District, Lvyuan District, Chaoyang District, Kuancheng District, Erdao District, Nanguan District, Daoli District, Nangang District, Daowai District, Pingfang District, Songbei District, Xiangfang District, Hulan District, Acheng District and Shuangcheng District ;Northeast suburb accents not included, and no minors were recorded. ; Each recording session contains 20-30 minutes of free dialogue between 2-5 people.; Sensitive data and personal information has been scrubbed.",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a9987709ec510f7c328e10e",
      "collection": "audio-catalogue",
      "title": "Shanghai dialect (China) Conversational Speech",
      "slug": "shanghai-asr002-cn",
      "url": "/data-catalog/audio-catalogue/shanghai-asr002-cn",
      "featured": false,
      "datasetId": "SHANGHAI_ASR002_CN",
      "locale": [
        "wuu-CN"
      ],
      "country": "China",
      "languageGroup": "Shanghai dialect",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General Conversational Speech"
      ],
      "volume": "4.5",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Audio with transcription. ; Audio recordings cover the following districts: Shanghai Huangpu District, Xuhui District, Changning District, Jing 'an District, Putuo District, Hongkou District, Yangpu District, Pudong New Area ; Shanghai suburb accents not included, and no minors were recorded. ; Each recording session contains 20-30 minutes of free dialogue between 2-5 people.; Sensitive data and personal information has been scrubbed.",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a99876fb779334273e9283e",
      "collection": "audio-catalogue",
      "title": "Shanghai dialect (China) Conversational Speech",
      "slug": "shanghai-asr001-cn",
      "url": "/data-catalog/audio-catalogue/shanghai-asr001-cn",
      "featured": false,
      "datasetId": "SHANGHAI_ASR001_CN",
      "locale": [
        "wuu-CN"
      ],
      "country": "China",
      "languageGroup": "Shanghai dialect",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General Conversational Speech"
      ],
      "volume": "21",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Recording pen/microphone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Audio with transcription.; Audio recordings cover the following districts: Shanghai Huangpu District, Xuhui District, Changning District, Jing 'an District, Putuo District, Hongkou District, Yangpu District, Pudong New Area ; Shanghai suburb accents not included, and no minors were recorded. ; Each recording session contains 20-30 minutes of free dialogue between 2-5 people.; Sensitive data and personal information has been scrubbed.",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a99876e6ab94adf346ea609",
      "collection": "audio-catalogue",
      "title": "English (United Kingdom) conversational telephony",
      "slug": "uke-asr001b",
      "url": "/data-catalog/audio-catalogue/uke-asr001b",
      "featured": false,
      "datasetId": "UKE_ASR001B",
      "locale": [
        "en-GB"
      ],
      "country": "United Kingdom",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "50",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;This version contains full 5-minute calls - there is an expanded version with 15 min calls named UKE_ASR001.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a99876d811b8e5d7361b670",
      "collection": "audio-catalogue",
      "title": "Baby crying audio",
      "slug": "cry-asr001-cn",
      "url": "/data-catalog/audio-catalogue/cry-asr001-cn",
      "featured": false,
      "datasetId": "CRY_ASR001_CN",
      "locale": [
        "NA"
      ],
      "country": "China",
      "languageGroup": "N/A",
      "audioType": "Human Sound",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "70",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Crying sound of babies 0-3 years old, each lasting around 2 minutes. Audio only.",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a99876c89ead58b4c2073ff",
      "collection": "audio-catalogue",
      "title": "Arabic (United Arab Emirates (UAE)) scripted smartphone",
      "slug": "aru-asr001-cn",
      "url": "/data-catalog/audio-catalogue/aru-asr001-cn",
      "featured": false,
      "datasetId": "ARU_ASR001_CN",
      "locale": [
        "ar-AE"
      ],
      "country": "United Arab Emirates (UAE)",
      "languageGroup": "Arabic",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "170",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset contains audio with corresponding text prompts ; Text prompts are not vowelised",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a99876b6d858e464b6647d1",
      "collection": "audio-catalogue",
      "title": "Polish (Poland) scripted smartphone",
      "slug": "pol-asr002-cn",
      "url": "/data-catalog/audio-catalogue/pol-asr002-cn",
      "featured": false,
      "datasetId": "POL_ASR002_CN",
      "locale": [
        "pl-PL"
      ],
      "country": "Poland",
      "languageGroup": "Polish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "293",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset contains audio with corresponding text prompts",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a99876aaefba034e024f169",
      "collection": "audio-catalogue",
      "title": "Hungarian (Hungary) scripted smartphone",
      "slug": "hun-asr001-cn",
      "url": "/data-catalog/audio-catalogue/hun-asr001-cn",
      "featured": false,
      "datasetId": "HUN_ASR001_CN",
      "locale": [
        "hu-HU"
      ],
      "country": "Hungary",
      "languageGroup": "Hungarian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "286",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset contains audio with corresponding text prompts",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a99876af4c0365c95ae7f53",
      "collection": "audio-catalogue",
      "title": "Greek (Greece) scripted smartphone",
      "slug": "gre-asr001-cn",
      "url": "/data-catalog/audio-catalogue/gre-asr001-cn",
      "featured": false,
      "datasetId": "GRE_ASR001_CN",
      "locale": [
        "el-GR"
      ],
      "country": "Greece",
      "languageGroup": "Greek",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "191",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset contains audio with corresponding text prompts",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a998769bc894a1ebfd41515",
      "collection": "audio-catalogue",
      "title": "Croatian (Croatia) scripted smartphone",
      "slug": "cro-asr003-cn",
      "url": "/data-catalog/audio-catalogue/cro-asr003-cn",
      "featured": false,
      "datasetId": "CRO_ASR003_CN",
      "locale": [
        "hr-HR"
      ],
      "country": "Croatia",
      "languageGroup": "Croatian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "263",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset contains audio with corresponding text prompts",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a99876817854c543f93c65d",
      "collection": "audio-catalogue",
      "title": "Arabic (Saudi Arabia) scripted smartphone",
      "slug": "ars-asr001-cn",
      "url": "/data-catalog/audio-catalogue/ars-asr001-cn",
      "featured": false,
      "datasetId": "ARS_ASR001_CN",
      "locale": [
        "ar-SA"
      ],
      "country": "Saudi Arabia",
      "languageGroup": "Arabic",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "322",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset contains audio with corresponding text prompts ; Text prompts are not vowelised ; 300-1000 prompts per speaker covering general content including education, sports, entertainment, travel, culture and technology",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a9987676ab94adf346ea3b8",
      "collection": "audio-catalogue",
      "title": "Arabic (Egypt) scripted smartphone",
      "slug": "are-asr001-cn",
      "url": "/data-catalog/audio-catalogue/are-asr001-cn",
      "featured": false,
      "datasetId": "ARE_ASR001_CN",
      "locale": [
        "ar-EG"
      ],
      "country": "Egypt",
      "languageGroup": "Arabic",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "352",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset contains audio with corresponding text prompts ; Text prompts are not vowelised",
      "source": "Appen China",
      "yearOfCollection": [
        "2020"
      ]
    },
    {
      "id": "6a998766d3a0ae3d29790a29",
      "collection": "audio-catalogue",
      "title": "Arabic (Morocco) conversational telephony",
      "slug": "ary-asr001",
      "url": "/data-catalog/audio-catalogue/ary-asr001",
      "featured": false,
      "datasetId": "ARY_ASR001",
      "locale": [
        "ar-MA"
      ],
      "country": "Morocco",
      "languageGroup": "Arabic",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "33",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Each speaker participated in 1 to 4 conversations. Speakers are identified by a unique 4-digit speaker ID which is recorded in the demographic file ;Transcription is available in original script and fully reversible Romanised version with accompanying pronunciation lexicon;English translation of product transcription is available (ARY_MT001, ARY_ASRMT001)",
      "source": "Appen Global",
      "yearOfCollection": [
        "2019"
      ]
    },
    {
      "id": "6a9987656ab94adf346ea324",
      "collection": "audio-catalogue",
      "title": "Bulgarian (Bulgaria) scripted microphone",
      "slug": "bul-asr002",
      "url": "/data-catalog/audio-catalogue/bul-asr002",
      "featured": false,
      "datasetId": "BUL_ASR002",
      "locale": [
        "bg-BG"
      ],
      "country": "Bulgaria",
      "languageGroup": "Bulgarian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "22",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "2005"
      ]
    },
    {
      "id": "6a998764f4c0365c95ae7dda",
      "collection": "audio-catalogue",
      "title": "Marathi (India) conversational telephony",
      "slug": "mar-asr001a",
      "url": "/data-catalog/audio-catalogue/mar-asr001a",
      "featured": false,
      "datasetId": "MAR_ASR001A",
      "locale": [
        "mr-IN"
      ],
      "country": "India",
      "languageGroup": "Marathi",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "52",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Approx 29% of the dataset sessions are transcribed and time stamped - full transcripts can be made available;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;16% landline, 84% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2015"
      ]
    },
    {
      "id": "6a99876384235eb50a0ed2ba",
      "collection": "audio-catalogue",
      "title": "Kannada (India) conversational telephony",
      "slug": "kan-asr001a",
      "url": "/data-catalog/audio-catalogue/kan-asr001a",
      "featured": false,
      "datasetId": "KAN_ASR001A",
      "locale": [
        "kn-IN"
      ],
      "country": "India",
      "languageGroup": "Kannada",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "57",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Approx. 25% of the dataset sessions are transcribed and time stamped - full transcripts can be made available;Database is accompanied by a pronunciation lexicon containing all transcribed words;16% Hands-Free car, 16% Landline quiet, 15% Mobile quiet, 17% Moving vehicle, 19% Public place, 17% Roadside",
      "source": "Appen Global",
      "yearOfCollection": [
        "2015"
      ]
    },
    {
      "id": "6a9987629ec510f7c328df7f",
      "collection": "audio-catalogue",
      "title": "Vietnamese (Vietnam) microphone",
      "slug": "vie-asr001",
      "url": "/data-catalog/audio-catalogue/vie-asr001",
      "featured": false,
      "datasetId": "VIE_ASR001",
      "locale": [
        "vi-VN"
      ],
      "country": "Vietnam",
      "languageGroup": "Vietnamese",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "19",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a99876189ead58b4c206ef6",
      "collection": "audio-catalogue",
      "title": "English (United States) conversational smartphone",
      "slug": "use-asr003",
      "url": "/data-catalog/audio-catalogue/use-asr003",
      "featured": false,
      "datasetId": "USE_ASR003",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "study/major/work",
        "hometown",
        "living arrangements",
        "weather and seasons",
        "punctuality",
        "TV programs/film)"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;Conversations cover a wide variety of topics including: study/major/work, hometown, living arrangements, weather and seasons, punctuality, TV programs/film);",
      "source": "Appen Global",
      "yearOfCollection": [
        "2018"
      ]
    },
    {
      "id": "6a998760fa9df117f358c019",
      "collection": "audio-catalogue",
      "title": "English (United States) scripted microphone",
      "slug": "use-asr001",
      "url": "/data-catalog/audio-catalogue/use-asr001",
      "featured": false,
      "datasetId": "USE_ASR001",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "62",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "raw PCM or wav PCM",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is formatted according to SALA II/SpeechDAT style conventions;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;Each speaker read 400 prompts including digits, natural numbers, personal and city names, telephone numbers, generic command and control items, phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a99875fd3a0ae3d29790721",
      "collection": "audio-catalogue",
      "title": "Urdu (India/ Pakistan) conversational telephony",
      "slug": "urd-asr001",
      "url": "/data-catalog/audio-catalogue/urd-asr001",
      "featured": false,
      "datasetId": "URD_ASR001",
      "locale": [
        "ur-IN",
        "ur-PK"
      ],
      "country": "India - Pakistan",
      "languageGroup": "Urdu",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "47.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words ; Environments: 9% Hands-free car, 7% Landline quiet, 34% mobile quiet, 29% public place, 16% roadside",
      "source": "Appen Global",
      "yearOfCollection": [
        "2014"
      ]
    },
    {
      "id": "6a99875e4005faf541bb399a",
      "collection": "audio-catalogue",
      "title": "English (United Kingdom) conversational telephony",
      "slug": "uke-asr001",
      "url": "/data-catalog/audio-catalogue/uke-asr001",
      "featured": false,
      "datasetId": "UKE_ASR001",
      "locale": [
        "en-GB"
      ],
      "country": "United Kingdom",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "150",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;This version contains full 15-minute calls - there is a reduced version with 5 min calls named UKE_ASR001B.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a99875d8afbba39574513dc",
      "collection": "audio-catalogue",
      "title": "Turkish (Turkey) microphone",
      "slug": "tur-asr002",
      "url": "/data-catalog/audio-catalogue/tur-asr002",
      "featured": false,
      "datasetId": "TUR_ASR002",
      "locale": [
        "tr-TR"
      ],
      "country": "Turkey",
      "languageGroup": "Turkish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "17",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996"
      ]
    },
    {
      "id": "6a99875c17956efcbddca7ab",
      "collection": "audio-catalogue",
      "title": "Turkish (Turkey) conversational telephony",
      "slug": "tur-asr001",
      "url": "/data-catalog/audio-catalogue/tur-asr001",
      "featured": false,
      "datasetId": "TUR_ASR001",
      "locale": [
        "tr-TR"
      ],
      "country": "Turkey",
      "languageGroup": "Turkish",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "41.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers ; 48% landline, 52% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2010"
      ]
    },
    {
      "id": "6a99875c8afbba3957451348",
      "collection": "audio-catalogue",
      "title": "Thai (Thailand) microphone",
      "slug": "tha-asr001",
      "url": "/data-catalog/audio-catalogue/tha-asr001",
      "featured": false,
      "datasetId": "THA_ASR001",
      "locale": [
        "th-TH"
      ],
      "country": "Thailand",
      "languageGroup": "Thai",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "28.2",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "2003"
      ]
    },
    {
      "id": "6a99875b17956efcbddca743",
      "collection": "audio-catalogue",
      "title": "English (United Kingdom) TTS male scripted microphone",
      "slug": "tc-star-male-baseline-voice-ian",
      "url": "/data-catalog/audio-catalogue/tc-star-male-baseline-voice-ian",
      "featured": false,
      "datasetId": "TC-STAR male baseline voice Ian",
      "locale": [
        "en-GB"
      ],
      "country": "United Kingdom",
      "languageGroup": "English",
      "audioType": "TTS Scripted Speech",
      "domainContent": [
        "Text-to-Speech Voice Talent"
      ],
      "volume": "10",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "96"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Headset microphone",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Dataset includes manual orthographic transcription, automatic segmentation into phonemes, automatic generation of pitch marks (where a certain percentage of phonetic segments and pitch marks has been manually checked);Dataset is accompanied by a pronunciation lexicon with POS, lemma and phonetic transcription",
      "source": "Nuance",
      "yearOfCollection": [
        "2005"
      ]
    },
    {
      "id": "6a99875a57206d63ef26137f",
      "collection": "audio-catalogue",
      "title": "English (United Kingdom) TTS female scripted microphone",
      "slug": "tc-star-female-baseline-voice-laura",
      "url": "/data-catalog/audio-catalogue/tc-star-female-baseline-voice-laura",
      "featured": false,
      "datasetId": "TC-STAR female baseline voice Laura",
      "locale": [
        "en-GB"
      ],
      "country": "United Kingdom",
      "languageGroup": "English",
      "audioType": "TTS Scripted Speech",
      "domainContent": [
        "Text-to-Speech Voice Talent"
      ],
      "volume": "10",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "96"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Headset microphone",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Dataset includes manual orthographic transcription, automatic segmentation into phonemes, automatic generation of pitch marks (where a certain percentage of phonetic segments and pitch marks has been manually checked);Dataset is accompanied by a pronunciation lexicon with POS, lemma and phonetic transcription",
      "source": "Nuance",
      "yearOfCollection": [
        "2005"
      ]
    },
    {
      "id": "6a998759f5674eee522c7763",
      "collection": "audio-catalogue",
      "title": "Swedish (Sweden/ Finland) microphone",
      "slug": "swe-asr001",
      "url": "/data-catalog/audio-catalogue/swe-asr001",
      "featured": false,
      "datasetId": "SWE_ASR001",
      "locale": [
        "sv-SE",
        "sv-FI"
      ],
      "country": "Sweden - Finland",
      "languageGroup": "Swedish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "30",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1997"
      ]
    },
    {
      "id": "6a99875884235eb50a0ec95b",
      "collection": "audio-catalogue",
      "title": "Spanish (Spain) scripted microphone",
      "slug": "speecon-spanish-database",
      "url": "/data-catalog/audio-catalogue/speecon-spanish-database",
      "featured": false,
      "datasetId": "Speecon Spanish Database",
      "locale": [
        "es-ES"
      ],
      "country": "Spain",
      "languageGroup": "Spanish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "46.25",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (office, entertainment, car, public place)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;290 prompts per adult speaker and 210 prompts per child speaker including digits, natural numbers, letter strings, personal, place and business names, application words for adult speakers, command (toy, phone and general) for child speakers, phonetically rich words and sentences and free and elicited spontaneous responses for adult speakers",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a998756f4ac0d8edcf3aef4",
      "collection": "audio-catalogue",
      "title": "Russian (Russia) scripted microphone",
      "slug": "speecon-russian-database",
      "url": "/data-catalog/audio-catalogue/speecon-russian-database",
      "featured": false,
      "datasetId": "Speecon Russian Database",
      "locale": [
        "ru-RU"
      ],
      "country": "Russia",
      "languageGroup": "Russian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "46.67",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (office, entertainment, car, public place)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;290 prompts per adult speaker and 210 prompts per child speaker including digits, natural numbers, letter strings, personal, place and business names, application words for adult speakers, command (toy, phone and general) for child speakers, phonetically rich words and sentences and free and elicited spontaneous responses for adult speakers",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99875584235eb50a0ec76e",
      "collection": "audio-catalogue",
      "title": "Japanese (Japan) scripted microphone",
      "slug": "speecon-japanese",
      "url": "/data-catalog/audio-catalogue/speecon-japanese",
      "featured": false,
      "datasetId": "Speecon Japanese",
      "locale": [
        "ja-JP"
      ],
      "country": "Japan",
      "languageGroup": "Japanese",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "57.5",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (office, entertainment, car, public place)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;290 prompts per adult speaker and 210 prompts per child speaker including digits, natural numbers, letter strings, personal, place and business names, application words for adult speakers, command (toy, phone and general) for child speakers, phonetically rich words and sentences and free and elicited spontaneous responses for adult speakers",
      "source": "Nuance",
      "yearOfCollection": [
        "2001",
        "2002",
        "2003"
      ]
    },
    {
      "id": "6a998754811b8e5d7361afcc",
      "collection": "audio-catalogue",
      "title": "German (Switzerland) scripted microphone",
      "slug": "speecon-german-switzerland-database",
      "url": "/data-catalog/audio-catalogue/speecon-german-switzerland-database",
      "featured": false,
      "datasetId": "Speecon German (Switzerland) database",
      "locale": [
        "de-CH"
      ],
      "country": "Switzerland",
      "languageGroup": "German",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "53.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (office, entertainment, car, public place)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;290 prompts per adult speaker and 210 prompts per child speaker including digits, natural numbers, letter strings, personal, place and business names, application words for adult speakers, command (toy, phone and general) for child speakers, phonetically rich words and sentences and free and elicited spontaneous responses for adult speakers",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a998753aa89b6c9886dfb3f",
      "collection": "audio-catalogue",
      "title": "English (United States) scripted microphone",
      "slug": "speecon-english-usa-database",
      "url": "/data-catalog/audio-catalogue/speecon-english-usa-database",
      "featured": false,
      "datasetId": "Speecon English (USA) database",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "53.75",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (office, entertainment, car, public place)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;290 prompts per adult speaker and 210 prompts per child speaker including digits, natural numbers, letter strings, personal, place and business names, application words for adult speakers, command (toy, phone and general) for child speakers, phonetically rich words and sentences and free and elicited spontaneous responses for adult speakers",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a998752f5674eee522c75ef",
      "collection": "audio-catalogue",
      "title": "Dutch (Netherlands) scripted microphone",
      "slug": "speecon-dutch-from-the-netherlands",
      "url": "/data-catalog/audio-catalogue/speecon-dutch-from-the-netherlands",
      "featured": false,
      "datasetId": "Speecon Dutch from the Netherlands",
      "locale": [
        "nl-NL"
      ],
      "country": "Netherlands",
      "languageGroup": "Dutch",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "68.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (office, entertainment, car, public place)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;290 prompts per adult speaker and 210 prompts per child speaker including digits, natural numbers, letter strings, personal, place and business names, application words for adult speakers, command (toy, phone and general) for child speakers, phonetically rich words and sentences and free and elicited spontaneous responses for adult speakers",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99875131b4728186af1391",
      "collection": "audio-catalogue",
      "title": "Dutch (Belgium) scripted microphone",
      "slug": "speecon-dutch-from-belgium",
      "url": "/data-catalog/audio-catalogue/speecon-dutch-from-belgium",
      "featured": false,
      "datasetId": "Speecon Dutch from Belgium",
      "locale": [
        "nl-BE"
      ],
      "country": "Belgium",
      "languageGroup": "Dutch",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "47.92",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (office, entertainment, car, public place)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;290 prompts per adult speaker and 210 prompts per child speaker including digits, natural numbers, letter strings, personal, place and business names, application words for adult speakers, command (toy, phone and general) for child speakers, phonetically rich words and sentences and free and elicited spontaneous responses for adult speakers",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99875117854c543f93c0db",
      "collection": "audio-catalogue",
      "title": "Danish (Denmark) scripted microphone",
      "slug": "speecon-danish",
      "url": "/data-catalog/audio-catalogue/speecon-danish",
      "featured": false,
      "datasetId": "Speecon Danish",
      "locale": [
        "da-DK"
      ],
      "country": "Denmark",
      "languageGroup": "Danish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "53.3",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (office, entertainment, car, public place)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;290 prompts per adult speaker and 210 prompts per child speaker including digits, natural numbers, letter strings, personal, place and business names, application words for adult speakers, command (toy, phone and general) for child speakers, phonetically rich words and sentences and free and elicited spontaneous responses for adult speakers",
      "source": "Nuance",
      "yearOfCollection": [
        "2002",
        "2003"
      ]
    },
    {
      "id": "6a99874ff5674eee522c74f4",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) telephony",
      "slug": "speechdat-m-italian-mobile-network-speech-database",
      "url": "/data-catalog/audio-catalogue/speechdat-m-italian-mobile-network-speech-database",
      "featured": false,
      "datasetId": "SpeechDat(M) Italian Mobile Network Speech Database",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "13.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;40 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99874eeaf7c7f9ff5188b3",
      "collection": "audio-catalogue",
      "title": "Sorani (Kurdish) conversational telephony",
      "slug": "sor-asr001",
      "url": "/data-catalog/audio-catalogue/sor-asr001",
      "featured": false,
      "datasetId": "SOR_ASR001",
      "locale": [
        "ku-IQ"
      ],
      "country": "Iran",
      "languageGroup": "Central Kurdish (Iran)",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "5.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;For a large proportion of calls, only one half of the conversation was collected and transcribed",
      "source": "Appen Global",
      "yearOfCollection": [
        "2005"
      ]
    },
    {
      "id": "6a99874deeecffe161183852",
      "collection": "audio-catalogue",
      "title": "Somali (Somalia) conversational telephony",
      "slug": "som-asr001",
      "url": "/data-catalog/audio-catalogue/som-asr001",
      "featured": false,
      "datasetId": "SOM_ASR001",
      "locale": [
        "so-SO"
      ],
      "country": "Somalia",
      "languageGroup": "Somali",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "50.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;1% landline, 99% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2011"
      ]
    },
    {
      "id": "6a99874c6ab94adf346e957d",
      "collection": "audio-catalogue",
      "title": "Slovenian (Slovenian) telephony",
      "slug": "slovenian-speechdat-ii-fdb-1000",
      "url": "/data-catalog/audio-catalogue/slovenian-speechdat-ii-fdb-1000",
      "featured": false,
      "datasetId": "Slovenian SpeechDat(II) FDB-1000",
      "locale": [
        "sl-SI"
      ],
      "country": "Slovenia",
      "languageGroup": "Slovenian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "76.67",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;Approximately 40 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99874b84235eb50a0ebf8e",
      "collection": "audio-catalogue",
      "title": "Slovak (Slovakia) scripted telephony",
      "slug": "slovak-speechdat-e-database",
      "url": "/data-catalog/audio-catalogue/slovak-speechdat-e-database",
      "featured": false,
      "datasetId": "Slovak SpeechDat(E) Database",
      "locale": [
        "sk-SK"
      ],
      "country": "Slovakia",
      "languageGroup": "Slovak",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "65",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;48 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99874a84235eb50a0ebecb",
      "collection": "audio-catalogue",
      "title": "Russian (Russia) scripted telephony",
      "slug": "russian-speechdat-e-database",
      "url": "/data-catalog/audio-catalogue/russian-speechdat-e-database",
      "featured": false,
      "datasetId": "Russian SpeechDat(E) Database",
      "locale": [
        "ru-RU"
      ],
      "country": "Russia",
      "languageGroup": "Russian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "180",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;45 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": [
        "2000"
      ]
    },
    {
      "id": "6a998749f4c0365c95ae7635",
      "collection": "audio-catalogue",
      "title": "Russian (Russia) scripted microphone",
      "slug": "rus-asr002",
      "url": "/data-catalog/audio-catalogue/rus-asr002",
      "featured": false,
      "datasetId": "RUS_ASR002",
      "locale": [
        "ru-RU"
      ],
      "country": "Russia",
      "languageGroup": "Russian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "31",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1997"
      ]
    },
    {
      "id": "6a998748fa9df117f358b9d1",
      "collection": "audio-catalogue",
      "title": "Russian (Russia) conversational telephony",
      "slug": "rus-asr001",
      "url": "/data-catalog/audio-catalogue/rus-asr001",
      "featured": false,
      "datasetId": "RUS_ASR001",
      "locale": [
        "ru-RU"
      ],
      "country": "Russia",
      "languageGroup": "Russian",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "37",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers;50% landline, 50% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a99874729d74d9309f36be9",
      "collection": "audio-catalogue",
      "title": "Romanian (Romania) conversational telephony",
      "slug": "rom-asr001",
      "url": "/data-catalog/audio-catalogue/rom-asr001",
      "featured": false,
      "datasetId": "ROM_ASR001",
      "locale": [
        "ro-RO"
      ],
      "country": "Romania",
      "languageGroup": "Romanian",
      "audioType": "Conversational Speech",
      "domainContent": [
        "Leisure",
        "Work and Sport"
      ],
      "volume": "37",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers;50% landline, 50% mobile;Conversations cover a range of topics including: Leisure, Work and Sport.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a9987468dcd14d10a928e91",
      "collection": "audio-catalogue",
      "title": "Panjabi (Pakistan) conversational telephony",
      "slug": "pap-asr001",
      "url": "/data-catalog/audio-catalogue/pap-asr001",
      "featured": false,
      "datasetId": "PAP_ASR001",
      "locale": [
        "pa-PK"
      ],
      "country": "Pakistan",
      "languageGroup": "Panjabi",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "20",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and time-stamped ; Dataset is accompanied by a pronunciation lexicon containing all transcribed words;71% of calls, both speakers (in-line/out-line) were collected and transcribed, however, for 29% calls, only one half of the conversation was collected and transcribed;20% landline, 80% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2017"
      ]
    },
    {
      "id": "6a99874557206d63ef260b52",
      "collection": "audio-catalogue",
      "title": "Portuguese (Portugal) conversational telephony",
      "slug": "ptp-asr001",
      "url": "/data-catalog/audio-catalogue/ptp-asr001",
      "featured": false,
      "datasetId": "PTP_ASR001",
      "locale": [
        "pt-PT"
      ],
      "country": "Portugal",
      "languageGroup": "Portuguese",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "36",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a998744d3a0ae3d2978facb",
      "collection": "audio-catalogue",
      "title": "Portuguese (Brazil) conversational telephony",
      "slug": "ptb-asr002",
      "url": "/data-catalog/audio-catalogue/ptb-asr002",
      "featured": false,
      "datasetId": "PTB_ASR002",
      "locale": [
        "pr-BR"
      ],
      "country": "Brazil",
      "languageGroup": "Portuguese",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "33",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words ; 63% landline, 38% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2013"
      ]
    },
    {
      "id": "6a998743c471bbf46c9f6c8a",
      "collection": "audio-catalogue",
      "title": "Portuguese (Brazil) microphone",
      "slug": "ptb-asr001",
      "url": "/data-catalog/audio-catalogue/ptb-asr001",
      "featured": false,
      "datasetId": "PTB_ASR001",
      "locale": [
        "pt-BR"
      ],
      "country": "Brazil",
      "languageGroup": "Portuguese",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "26",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996",
        "1997"
      ]
    },
    {
      "id": "6a99874229d74d9309f36abe",
      "collection": "audio-catalogue",
      "title": "Polish (Poland) scripted telephony",
      "slug": "polish-speechdat-e-database",
      "url": "/data-catalog/audio-catalogue/polish-speechdat-e-database",
      "featured": false,
      "datasetId": "Polish SpeechDat(E) Database",
      "locale": [
        "pl-PL"
      ],
      "country": "Poland",
      "languageGroup": "Polish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "78.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;48 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99874117956efcbddc9cef",
      "collection": "audio-catalogue",
      "title": "Polish (Poland) scripted microphone",
      "slug": "pol-asr001",
      "url": "/data-catalog/audio-catalogue/pol-asr001",
      "featured": false,
      "datasetId": "POL_ASR001",
      "locale": [
        "pl-PL"
      ],
      "country": "Poland",
      "languageGroup": "Polish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "25",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996",
        "1997"
      ]
    },
    {
      "id": "6a99874117956efcbddc9c91",
      "collection": "audio-catalogue",
      "title": "Pashto (Afghanistan) broadcast",
      "slug": "pas-brc001",
      "url": "/data-catalog/audio-catalogue/pas-brc001",
      "featured": false,
      "datasetId": "PAS_BRC001",
      "locale": [
        "ps-AF"
      ],
      "country": "Afghanistan",
      "languageGroup": "Northern Pashto - Southern Pashto",
      "audioType": "Broadcast Speech",
      "domainContent": [
        "Broadcast Media (talk shows, interviews, news)"
      ],
      "volume": "51",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "32",
        "44",
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Pronunciation lexicon not currently available but can be developed upon request;Dataset is largely speech only and does not include music or advertisements;Data types include: talk shows, interviews, news broadcasts (excluding news reading by anchors)",
      "source": "Appen Global",
      "yearOfCollection": [
        "2013"
      ]
    },
    {
      "id": "6a99873f84235eb50a0eb824",
      "collection": "audio-catalogue",
      "title": "Pashto (Afghanistan) conversational microphone",
      "slug": "pas-asr002",
      "url": "/data-catalog/audio-catalogue/pas-asr002",
      "featured": false,
      "datasetId": "PAS_ASR002",
      "locale": [
        "ps-AF"
      ],
      "country": "Afghanistan",
      "languageGroup": "Northern Pashto - Southern Pashto",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "39",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;A full translation of the transcripts into French is also available as an optional additional purchase;Average length of calls: 120 mins where one speaker acts as an interviewer and the other as the interviewee for scenarios similar to TransTAC style (e.g. civil affairs, checkpoints etc.);The interviewer appears in more than one set of dialogues but the interviewee is unique for each set;",
      "source": "Appen Global",
      "yearOfCollection": [
        "2014"
      ]
    },
    {
      "id": "6a99873efa9df117f358b674",
      "collection": "audio-catalogue",
      "title": "Pashto (Afghanistan) conversational telephony",
      "slug": "pas-asr001",
      "url": "/data-catalog/audio-catalogue/pas-asr001",
      "featured": false,
      "datasetId": "PAS_ASR001",
      "locale": [
        "ps-AF"
      ],
      "country": "Afghanistan",
      "languageGroup": "Northern Pashto - Southern Pashto",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "55.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;For the majority of calls, both speakers (in-line/out-line) were collected and transcribed, however, for a smaller number of calls, only one half of the conversation was collected and transcribed;25% landline, 75% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2005"
      ]
    },
    {
      "id": "6a99873df4ac0d8edcf3a848",
      "collection": "audio-catalogue",
      "title": "Arabic (United Arab Emirates (UAE)) scripted telephony",
      "slug": "orientel-united-arab-emirates-msa-modern-standard-arabic",
      "url": "/data-catalog/audio-catalogue/orientel-united-arab-emirates-msa-modern-standard-arabic",
      "featured": false,
      "datasetId": "OrienTel United Arab Emirates MSA (Modern Standard Arabic)",
      "locale": [
        "ar-AE"
      ],
      "country": "United Arab Emirates (UAE)",
      "languageGroup": "Arabic",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "31.66",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;49 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words and spontaneous items for control",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99873b9ec510f7c328d772",
      "collection": "audio-catalogue",
      "title": "Arabic (United Arab Emirates (UAE)) scripted telephony",
      "slug": "orientel-united-arab-emirates-mca-modern-colloquial-arabic",
      "url": "/data-catalog/audio-catalogue/orientel-united-arab-emirates-mca-modern-colloquial-arabic",
      "featured": false,
      "datasetId": "OrienTel United Arab Emirates MCA (Modern Colloquial Arabic)",
      "locale": [
        "ar-AE"
      ],
      "country": "United Arab Emirates (UAE)",
      "languageGroup": "Arabic",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "48.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;49 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words and spontaneous items for control",
      "source": "Nuance",
      "yearOfCollection": [
        "2006"
      ]
    },
    {
      "id": "6a99873a9ec510f7c328d738",
      "collection": "audio-catalogue",
      "title": "Turkish (Turkey) telephony",
      "slug": "orientel-turkish-database",
      "url": "/data-catalog/audio-catalogue/orientel-turkish-database",
      "featured": false,
      "datasetId": "OrienTel Turkish Database",
      "locale": [
        "tr-TR"
      ],
      "country": "Turkey",
      "languageGroup": "Turkish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "118.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;45 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a998739e924c86953f90ee1",
      "collection": "audio-catalogue",
      "title": "German (Turkey) telephony",
      "slug": "orientel-german-spoken-by-turkish",
      "url": "/data-catalog/audio-catalogue/orientel-german-spoken-by-turkish",
      "featured": false,
      "datasetId": "OrienTel German Spoken by Turkish",
      "locale": [
        "de-TR"
      ],
      "country": "Turkey",
      "languageGroup": "German",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "31.66",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;52 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a998738f41547c318e677c7",
      "collection": "audio-catalogue",
      "title": "English (United Arab Emirates (UAE)) scripted telephony",
      "slug": "orientel-english-as-spoken-in-the-united-arab-emirates",
      "url": "/data-catalog/audio-catalogue/orientel-english-as-spoken-in-the-united-arab-emirates",
      "featured": false,
      "datasetId": "OrienTel English as spoken in the United Arab Emirates",
      "locale": [
        "en-AE"
      ],
      "country": "United Arab Emirates (UAE)",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "33.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;51 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words and spontaneous items for control",
      "source": "Nuance",
      "yearOfCollection": [
        "2003",
        "2004",
        "2005"
      ]
    },
    {
      "id": "6a998738fa9df117f358b192",
      "collection": "audio-catalogue",
      "title": "Dutch (Netherlands) conversational telephony",
      "slug": "nld-asr001",
      "url": "/data-catalog/audio-catalogue/nld-asr001",
      "featured": false,
      "datasetId": "NLD_ASR001",
      "locale": [
        "nl-NL"
      ],
      "country": "Netherlands",
      "languageGroup": "Dutch",
      "audioType": "Conversational Speech",
      "domainContent": [
        "Holiday/Leisure",
        "Work and Sport"
      ],
      "volume": "36.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers;51% landline, 49% mobile;Conversations cover a range of topics including: Holiday/Leisure, Work and Sport.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a998737e6ee6e81af9b02b1",
      "collection": "audio-catalogue",
      "title": "Arabic (Modern Standard Arabic) scripted microphone",
      "slug": "msa-asr001",
      "url": "/data-catalog/audio-catalogue/msa-asr001",
      "featured": false,
      "datasetId": "MSA_ASR001",
      "locale": [
        "ar-TN"
      ],
      "country": "Tunisia",
      "languageGroup": "Arabic",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "12",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996",
        "1997",
        "1998",
        "1999",
        "2000"
      ]
    },
    {
      "id": "6a998736811b8e5d73619c9e",
      "collection": "audio-catalogue",
      "title": "Marathi (India) conversational telephony",
      "slug": "mar-asr001",
      "url": "/data-catalog/audio-catalogue/mar-asr001",
      "featured": false,
      "datasetId": "MAR_ASR001",
      "locale": [
        "mr-IN"
      ],
      "country": "India",
      "languageGroup": "Marathi",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "15",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;17% Hands-Free car, 16% Landline quiet, 19% Mobile quiet, 16% Moving vehicle, 16% Public place, 17% Roadside",
      "source": "Appen Global",
      "yearOfCollection": [
        "2015"
      ]
    },
    {
      "id": "6a9987358dcd14d10a928b68",
      "collection": "audio-catalogue",
      "title": "Mandarin Chinese (China) scripted microphone",
      "slug": "mac-asr002",
      "url": "/data-catalog/audio-catalogue/mac-asr002",
      "featured": false,
      "datasetId": "MAC_ASR002",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Mandarin Chinese",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "26",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996"
      ]
    },
    {
      "id": "6a99873473f796e259268bfe",
      "collection": "audio-catalogue",
      "title": "Mandarin Chinese (China) scripted telephony",
      "slug": "mac-asr001",
      "url": "/data-catalog/audio-catalogue/mac-asr001",
      "featured": false,
      "datasetId": "MAC_ASR001",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Mandarin Chinese",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "323.3",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon [SAMPA] containing all transcribed words;98 prompts per speaker including digits, natural numbers, letter strings, personal, place, and business names, confirmation items (yes, no + fuzzy), generic command and control items (from a set of 215), phonetically rich sentences and words;100% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2007"
      ]
    },
    {
      "id": "6a99873357206d63ef26067d",
      "collection": "audio-catalogue",
      "title": "German (Luxembourg) telephony",
      "slug": "luxembourgish-german-speechdat-ii-fdb-500-fixed1lg",
      "url": "/data-catalog/audio-catalogue/luxembourgish-german-speechdat-ii-fdb-500-fixed1lg",
      "featured": false,
      "datasetId": "Luxembourgish German SpeechDat(II) FDB-500 (FIXED1LG)",
      "locale": [
        "de-LU"
      ],
      "country": "Luxembourg",
      "languageGroup": "German",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "33.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;53 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99873229d74d9309f3664a",
      "collection": "audio-catalogue",
      "title": "French (Luxembourg) telephony",
      "slug": "luxembourgish-french-speechdat-ii-fdb-500-fixed1lf",
      "url": "/data-catalog/audio-catalogue/luxembourgish-french-speechdat-ii-fdb-500-fixed1lf",
      "featured": false,
      "datasetId": "Luxembourgish French SpeechDat(II) FDB-500 (FIXED1LF)",
      "locale": [
        "fr-LU"
      ],
      "country": "Luxembourg",
      "languageGroup": "French",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "45",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;53 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a998731d3a0ae3d2978ee90",
      "collection": "audio-catalogue",
      "title": "Korean (South Korea) scripted microphone",
      "slug": "kor-asr001",
      "url": "/data-catalog/audio-catalogue/kor-asr001",
      "featured": false,
      "datasetId": "KOR_ASR001",
      "locale": [
        "ko-KR"
      ],
      "country": "South Korea",
      "languageGroup": "Korean",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "20",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996"
      ]
    },
    {
      "id": "6a998730d3a0ae3d2978ee0c",
      "collection": "audio-catalogue",
      "title": "Kannada (India) conversational telephony",
      "slug": "kan-asr001",
      "url": "/data-catalog/audio-catalogue/kan-asr001",
      "featured": false,
      "datasetId": "KAN_ASR001",
      "locale": [
        "kn-IN"
      ],
      "country": "India",
      "languageGroup": "Kannada",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "15",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;15% landline, 85% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2015"
      ]
    },
    {
      "id": "6a99872f17956efcbddc97c8",
      "collection": "audio-catalogue",
      "title": "Japanese (Japan) scripted microphone",
      "slug": "jpn-asr001",
      "url": "/data-catalog/audio-catalogue/jpn-asr001",
      "featured": false,
      "datasetId": "JPN_ASR001",
      "locale": [
        "ja-JP"
      ],
      "country": "Japan",
      "languageGroup": "Japanese",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996",
        "1997",
        "1998"
      ]
    },
    {
      "id": "6a99872e8afbba39574503c6",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) telephony",
      "slug": "italian-speechdat-ii-mdb-250",
      "url": "/data-catalog/audio-catalogue/italian-speechdat-ii-mdb-250",
      "featured": false,
      "datasetId": "Italian SpeechDat(II) MDB-250",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "103.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;51 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99872d811b8e5d73619650",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) telephony",
      "slug": "italian-speechdat-ii-fdb-3000",
      "url": "/data-catalog/audio-catalogue/italian-speechdat-ii-fdb-3000",
      "featured": false,
      "datasetId": "Italian SpeechDat(II) FDB-3000",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "228.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;44 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99872d17956efcbddc9643",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) telephony",
      "slug": "italian-fixed-network-speech-speechdat-m-corpus",
      "url": "/data-catalog/audio-catalogue/italian-fixed-network-speech-speechdat-m-corpus",
      "featured": false,
      "datasetId": "Italian Fixed Network Speech SpeechDat(M) Corpus",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "38.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;39 prompts per speaker including isolated and connected digits, natural numbers, money amounts, spelled words, time and date phrases, yes/no questions, city names, common application words, application words in phrases and phonetically rich sentences",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99872cf41547c318e6742d",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) TTS male scripted microphone",
      "slug": "ita-tts001",
      "url": "/data-catalog/audio-catalogue/ita-tts001",
      "featured": false,
      "datasetId": "ITA_TTS001",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "TTS Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "3",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "22"
      ],
      "dataFormat": "raw PCM",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Dataset is accompanied by a pronunciation lexicon containing all words spoken in the Dataset;3,300 prompts per speaker including phonetically rich sentences",
      "source": "Appen Global",
      "yearOfCollection": [
        "2002"
      ]
    },
    {
      "id": "6a99872b31d6f8d8f3d089c6",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) conversational telephony",
      "slug": "ita-asr003",
      "url": "/data-catalog/audio-catalogue/ita-asr003",
      "featured": false,
      "datasetId": "ITA_ASR003",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "Conversational Speech",
      "domainContent": [
        "Travel",
        "Family and Holidays"
      ],
      "volume": "36",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers;50% landline, 50% mobile;Conversations cover a range of topics including: Travel, Family and Holidays.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a99872af41547c318e67376",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) scripted microphone in-car",
      "slug": "ita-asr002",
      "url": "/data-catalog/audio-catalogue/ita-asr002",
      "featured": false,
      "datasetId": "ITA_ASR002",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "47.25",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "raw PCM",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (in-car)",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;350 prompts per speaker including digits, street names, generic command and control items, phonetically rich sentences and words;Each speaker recorded 1or 2 sessions including Session 1 in a parked vehicle with the engine running and Session 2 in a vehicle travelling at 60 mph (100 km/h)",
      "source": "Appen Global",
      "yearOfCollection": [
        "2008"
      ]
    },
    {
      "id": "6a99872984235eb50a0eabe3",
      "collection": "audio-catalogue",
      "title": "Italian (Italy) scripted microphone",
      "slug": "ita-asr001",
      "url": "/data-catalog/audio-catalogue/ita-asr001",
      "featured": false,
      "datasetId": "ITA_ASR001",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "44.25",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "22"
      ],
      "dataFormat": "raw PCM",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 prompts per speaker including 100 command and control type items and 100 phonetically rich sentences",
      "source": "Appen Global",
      "yearOfCollection": [
        "2002"
      ]
    },
    {
      "id": "6a99872873f796e259268371",
      "collection": "audio-catalogue",
      "title": "Hungarian (Hungary) scripted telephony",
      "slug": "hungarian-speechdat-e",
      "url": "/data-catalog/audio-catalogue/hungarian-speechdat-e",
      "featured": false,
      "datasetId": "Hungarian SpeechDat(E)",
      "locale": [
        "hu-HU"
      ],
      "country": "Hungary",
      "languageGroup": "Hungarian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "65",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;48 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99872717956efcbddc91a3",
      "collection": "audio-catalogue",
      "title": "Hindi (India) conversational telephony",
      "slug": "hin-asr002",
      "url": "/data-catalog/audio-catalogue/hin-asr002",
      "featured": false,
      "datasetId": "HIN_ASR002",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "32.25",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;For the majority of calls, both speakers (in-line/out-line) were collected and transcribed, however, for a smaller number of calls, only one half of the conversation was collected and transcribed;29% landline, 71% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2006"
      ]
    },
    {
      "id": "6a99872684235eb50a0ea74c",
      "collection": "audio-catalogue",
      "title": "Hindi (India) scripted telephony",
      "slug": "hin-asr001",
      "url": "/data-catalog/audio-catalogue/hin-asr001",
      "featured": false,
      "datasetId": "HIN_ASR001",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "224",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon [SAMPA] containing all transcribed words;50 prompts per speaker including digits, natural numbers, personal, business and place names, web addresses, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2006"
      ]
    },
    {
      "id": "6a998725d3a0ae3d2978e88a",
      "collection": "audio-catalogue",
      "title": "Hebrew (Israel) conversational telephony",
      "slug": "heb-asr001",
      "url": "/data-catalog/audio-catalogue/heb-asr001",
      "featured": false,
      "datasetId": "HEB_ASR001",
      "locale": [
        "he-IL"
      ],
      "country": "Israel",
      "languageGroup": "Hebrew",
      "audioType": "Conversational Speech",
      "domainContent": [
        "Friends",
        "Family and Studies"
      ],
      "volume": "34.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers;50% landline, 50% mobile;Conversations cover a range of topics including: Friends, Family and Studies.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a998724eaf7c7f9ff516cf7",
      "collection": "audio-catalogue",
      "title": "Hausa (Nigeria) conversational telephony",
      "slug": "hau-asr002",
      "url": "/data-catalog/audio-catalogue/hau-asr002",
      "featured": false,
      "datasetId": "HAU_ASR002",
      "locale": [
        "ha-NG"
      ],
      "country": "Nigeria",
      "languageGroup": "Hausa",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "33",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers",
      "source": "Appen Global",
      "yearOfCollection": [
        "2015"
      ]
    },
    {
      "id": "6a99872273f796e259267f2e",
      "collection": "audio-catalogue",
      "title": "Hausa scripted microphone",
      "slug": "hau-asr001",
      "url": "/data-catalog/audio-catalogue/hau-asr001",
      "featured": false,
      "datasetId": "HAU_ASR001",
      "locale": [
        "ha-CM"
      ],
      "country": "Cameroon",
      "languageGroup": "Hausa",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "20",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "2010"
      ]
    },
    {
      "id": "6a99872284235eb50a0ea443",
      "collection": "audio-catalogue",
      "title": "German (Germany) telephony",
      "slug": "german-speechdat-ii-fdb-4000",
      "url": "/data-catalog/audio-catalogue/german-speechdat-ii-fdb-4000",
      "featured": false,
      "datasetId": "German SpeechDat(II) FDB-4000",
      "locale": [
        "de-DE"
      ],
      "country": "Germany",
      "languageGroup": "German",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "268.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;40 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99872084235eb50a0ea363",
      "collection": "audio-catalogue",
      "title": "German (Germany) telephony",
      "slug": "german-speechdat-ii-fdb-1000",
      "url": "/data-catalog/audio-catalogue/german-speechdat-ii-fdb-1000",
      "featured": false,
      "datasetId": "German SpeechDat (II) FDB-1000",
      "locale": [
        "de-DE"
      ],
      "country": "Germany",
      "languageGroup": "German",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "31.67",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;44 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99871ff4c0365c95ae66b0",
      "collection": "audio-catalogue",
      "title": "French (France) scripted microphone",
      "slug": "frf-asr003",
      "url": "/data-catalog/audio-catalogue/frf-asr003",
      "featured": false,
      "datasetId": "FRF_ASR003",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "26",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "2000",
        "2001"
      ]
    },
    {
      "id": "6a99871ed3a0ae3d2978e364",
      "collection": "audio-catalogue",
      "title": "French (France) conversational telephony",
      "slug": "frf-asr001",
      "url": "/data-catalog/audio-catalogue/frf-asr001",
      "featured": false,
      "datasetId": "FRF_ASR001",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "25",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;For the majority of calls, both speakers (in-line/out-line) were collected and transcribed, however, for a smaller number of calls, only one half of the conversation was collected and transcribed",
      "source": "Appen Global",
      "yearOfCollection": [
        "2008"
      ]
    },
    {
      "id": "6a99871d040b22801499b194",
      "collection": "audio-catalogue",
      "title": "French (France) In-Car",
      "slug": "french-speechdat-car",
      "url": "/data-catalog/audio-catalogue/french-speechdat-car",
      "featured": false,
      "datasetId": "French SpeechDat-Car",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "113.7",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8",
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone and mobile phone",
      "recordingCondition": "Mixed (in-car)",
      "datasetDescription": "Dataset is fully transcribed and is accompanied by a pronunciation lexicon and validation report;Approximately 125 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names (some spontaneous), generic command and control items, phonetically rich words and sentences and prompts for spontaneous speech ; 113.7 hours",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99871c31d6f8d8f3d07e88",
      "collection": "audio-catalogue",
      "title": "French (France) scripted telephony",
      "slug": "french-speechdat-ii-fdb-5000",
      "url": "/data-catalog/audio-catalogue/french-speechdat-ii-fdb-5000",
      "featured": false,
      "datasetId": "French SpeechDat(II) FDB-5000",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "305",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;47 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": [
        "1999"
      ]
    },
    {
      "id": "6a99871b811b8e5d73618ebe",
      "collection": "audio-catalogue",
      "title": "French (France) scripted telephony",
      "slug": "french-speechdat-ii-fdb-1000",
      "url": "/data-catalog/audio-catalogue/french-speechdat-ii-fdb-1000",
      "featured": false,
      "datasetId": "French SpeechDat(II) FDB-1000",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "41.67",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;48 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items and phonetically rich sentences and words",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99871beeecffe161181cad",
      "collection": "audio-catalogue",
      "title": "French (Canada) conversational telephony",
      "slug": "frc-asr003",
      "url": "/data-catalog/audio-catalogue/frc-asr003",
      "featured": false,
      "datasetId": "FRC_ASR003",
      "locale": [
        "fr-CA"
      ],
      "country": "Canada",
      "languageGroup": "French",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "9",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;Average length of calls: 10-15 mins; For the majority of calls, only one half of the conversation was collected and transcribed, however, for a smaller number of calls, both speakers (in-line/out-line) were collected and transcribed",
      "source": "Appen Global",
      "yearOfCollection": [
        "2015"
      ]
    },
    {
      "id": "6a99871ae924c86953f8f8be",
      "collection": "audio-catalogue",
      "title": "French (Canada) scripted microphone",
      "slug": "frc-asr002",
      "url": "/data-catalog/audio-catalogue/frc-asr002",
      "featured": false,
      "datasetId": "FRC_ASR002",
      "locale": [
        "fr-CA"
      ],
      "country": "Canada",
      "languageGroup": "French",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "46",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;150 prompts per speaker including digits, digit strings (randomly generated), addresses and phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2011"
      ]
    },
    {
      "id": "6a99871917854c543f93b1af",
      "collection": "audio-catalogue",
      "title": "French (Canada) scripted telephony",
      "slug": "frc-asr001",
      "url": "/data-catalog/audio-catalogue/frc-asr001",
      "featured": false,
      "datasetId": "FRC_ASR001",
      "locale": [
        "fr-CA"
      ],
      "country": "Canada",
      "languageGroup": "French",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "131",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "mulaw",
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon [SAMPA] containing all transcribed words;100 prompts per speaker including digits, natural numbers, letter strings, personal, place, and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2005"
      ]
    },
    {
      "id": "6a99871857206d63ef25fe15",
      "collection": "audio-catalogue",
      "title": "Dutch (Belgium) scripted telephony",
      "slug": "flemish-speechdat-ii-fdb-1000-fixed1fl",
      "url": "/data-catalog/audio-catalogue/flemish-speechdat-ii-fdb-1000-fixed1fl",
      "featured": false,
      "datasetId": "Flemish SpeechDat(II) FDB-1000 (FIXED1FL)",
      "locale": [
        "nl-BE"
      ],
      "country": "Belgium",
      "languageGroup": "Dutch",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "80",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;52 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words and spontaneous items for control",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99871710482f3af40029d6",
      "collection": "audio-catalogue",
      "title": "Iranian Persian (Farsi) (Iran) conversational telephony",
      "slug": "far-asr002",
      "url": "/data-catalog/audio-catalogue/far-asr002",
      "featured": false,
      "datasetId": "FAR_ASR002",
      "locale": [
        "fa-IR"
      ],
      "country": "Iran",
      "languageGroup": "Iranian Persian (Farsi)",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "30.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a998716d3a0ae3d2978ded2",
      "collection": "audio-catalogue",
      "title": "Iranian Persian (Farsi) (Iran) scripted telephony",
      "slug": "far-asr001",
      "url": "/data-catalog/audio-catalogue/far-asr001",
      "featured": false,
      "datasetId": "FAR_ASR001",
      "locale": [
        "fa-IR"
      ],
      "country": "Iran",
      "languageGroup": "Iranian Persian (Farsi)",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "85",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Fully transcribed to OrienTel type conventions;Dataset is accompanied by a pronunciation lexicon [SAMPA] containing all transcribed words;48 prompts per speaker including digits, natural numbers, letter strings, personal, place, and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2008"
      ]
    },
    {
      "id": "6a99871573f796e25926757b",
      "collection": "audio-catalogue",
      "title": "Spanish (Spain) TTS male scripted microphone",
      "slug": "esp-tts001",
      "url": "/data-catalog/audio-catalogue/esp-tts001",
      "featured": false,
      "datasetId": "ESP_TTS001",
      "locale": [
        "es-ES"
      ],
      "country": "Spain",
      "languageGroup": "Spanish",
      "audioType": "TTS Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "1.45",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "22"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Dataset is accompanied by a pronunciation lexicon containing all words spoken in the Dataset;1,787 prompts per speaker including phonetically rich sentences",
      "source": "Appen Global",
      "yearOfCollection": [
        "2002"
      ]
    },
    {
      "id": "6a99871413e9a932dc46fbc2",
      "collection": "audio-catalogue",
      "title": "Spanish (Spain) scripted microphone",
      "slug": "esp-asr001",
      "url": "/data-catalog/audio-catalogue/esp-asr001",
      "featured": false,
      "datasetId": "ESP_ASR001",
      "locale": [
        "es-ES"
      ],
      "country": "Spain",
      "languageGroup": "Spanish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "39.75",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "22"
      ],
      "dataFormat": "raw PCM",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 prompts per speaker including 100 command and control type items and 100 phonetically rich sentences",
      "source": "Appen Global",
      "yearOfCollection": [
        "2014"
      ]
    },
    {
      "id": "6a998713eaf7c7f9ff516525",
      "collection": "audio-catalogue",
      "title": "Spanish (Latin America - Chile and Colombia) conversational telephony",
      "slug": "esl-asr002",
      "url": "/data-catalog/audio-catalogue/esl-asr002",
      "featured": false,
      "datasetId": "ESL_ASR002",
      "locale": [
        "es-CL",
        "es-CO"
      ],
      "country": "Chile-Columbia",
      "languageGroup": "Spanish",
      "audioType": "Conversational Speech",
      "domainContent": [
        "Call Centre (Banking & Telco)"
      ],
      "volume": "22",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Dataset is fully transcribed and time-stamped;Pronunciation lexicon not currently available but can be developed upon request;Call Center;Call Centre style conversations (by 64 customers, 14 agents) in banking and telco domains, primarily using mobile phone",
      "source": "Appen Global",
      "yearOfCollection": [
        "2018"
      ]
    },
    {
      "id": "6a998712eaf7c7f9ff516497",
      "collection": "audio-catalogue",
      "title": "Spanish (Latin America) scripted microphone",
      "slug": "esl-asr001",
      "url": "/data-catalog/audio-catalogue/esl-asr001",
      "featured": false,
      "datasetId": "ESL_ASR001",
      "locale": [
        "es-CR"
      ],
      "country": "Costa Rica",
      "languageGroup": "Spanish",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "17",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996",
        "1997"
      ]
    },
    {
      "id": "6a9987114005faf541bb36c2",
      "collection": "audio-catalogue",
      "title": "English (India) conversational telephony",
      "slug": "eni-asr002",
      "url": "/data-catalog/audio-catalogue/eni-asr002",
      "featured": false,
      "datasetId": "ENI_ASR002",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "67.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;271 telephony conversations are recorded for this project",
      "source": "Appen Global",
      "yearOfCollection": [
        "2013"
      ]
    },
    {
      "id": "6a9987106ab94adf346e7569",
      "collection": "audio-catalogue",
      "title": "English (India) scripted telephony",
      "slug": "eni-asr001",
      "url": "/data-catalog/audio-catalogue/eni-asr001",
      "featured": false,
      "datasetId": "ENI_ASR001",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "217",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions.;Dataset is accompanied by a pronunciation lexicon [SAMPA] containing all transcribed words;49 prompts per speaker including digits, natural numbers, letter strings, personal, place, and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a99870f73f796e259267183",
      "collection": "audio-catalogue",
      "title": "English (Philippines) conversational telephony",
      "slug": "enf-asr001",
      "url": "/data-catalog/audio-catalogue/enf-asr001",
      "featured": false,
      "datasetId": "ENF_ASR001",
      "locale": [
        "en-PH"
      ],
      "country": "Philippines",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "53.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and time stamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;Average length of calls: 10-15 mins",
      "source": "Appen Global",
      "yearOfCollection": [
        "2013"
      ]
    },
    {
      "id": "6a99870d10482f3af400251b",
      "collection": "audio-catalogue",
      "title": "English (Canada) scripted telephony",
      "slug": "enc-asr001",
      "url": "/data-catalog/audio-catalogue/enc-asr001",
      "featured": false,
      "datasetId": "ENC_ASR001",
      "locale": [
        "en-CA"
      ],
      "country": "Canada",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "144",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Fully transcribed to SALA II/SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;99 prompts per speaker including digits, natural numbers, letter strings, personal, place, and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2005"
      ]
    },
    {
      "id": "6a99870c31d6f8d8f3d0768c",
      "collection": "audio-catalogue",
      "title": "English (Arabic - Levant/Egypt) conversational telephony",
      "slug": "ena-asr001",
      "url": "/data-catalog/audio-catalogue/ena-asr001",
      "featured": false,
      "datasetId": "ENA_ASR001",
      "locale": [
        "en-EG"
      ],
      "country": "Egypt",
      "languageGroup": "English",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "28.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;Average length of calls: 10-15 mins",
      "source": "Appen Global",
      "yearOfCollection": [
        "2014"
      ]
    },
    {
      "id": "6a99870bbc894a1ebfd40a6b",
      "collection": "audio-catalogue",
      "title": "Arabic (Eastern Algeria) conversational telephony",
      "slug": "ear-asr001",
      "url": "/data-catalog/audio-catalogue/ear-asr001",
      "featured": false,
      "datasetId": "EAR_ASR001",
      "locale": [
        "ar-DZ"
      ],
      "country": "Algeria",
      "languageGroup": "Arabic",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "29",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;For the majority of calls, both speakers (in-line/out-line) were collected and transcribed however, for a smaller number of calls, only one half of the conversation was collected and transcribed;8% landline, 92% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2007"
      ]
    },
    {
      "id": "6a99870bf4c0365c95ae5a1b",
      "collection": "audio-catalogue",
      "title": "Dutch (Netherlands & Belgium) scripted in-car",
      "slug": "dutch-and-flemish-speechdat-car",
      "url": "/data-catalog/audio-catalogue/dutch-and-flemish-speechdat-car",
      "featured": false,
      "datasetId": "Dutch and Flemish SpeechDat-Car",
      "locale": [
        "nl-NL",
        "nl-BE"
      ],
      "country": "Netherland - Belgium",
      "languageGroup": "Dutch",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "27",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8",
        "16"
      ],
      "dataFormat": "Available on request",
      "recordingDevice": "Microphone and mobile phone",
      "recordingCondition": "Mixed (in-car)",
      "datasetDescription": "Dataset is fully transcribed and is accompanied by a pronunciation lexicon and validation report;125 prompts per adult speaker including digits, natural numbers, letter strings, personal, place and business names (some spontaneous), generic command and control items, phonetically rich words and sentences and prompts for spontaneous speech",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a99870a811b8e5d736187b3",
      "collection": "audio-catalogue",
      "title": "German (Germany) scripted microphone",
      "slug": "deu-asr003",
      "url": "/data-catalog/audio-catalogue/deu-asr003",
      "featured": false,
      "datasetId": "DEU_ASR003",
      "locale": [
        "de-DE"
      ],
      "country": "Germany",
      "languageGroup": "German",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "25",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "2011"
      ]
    },
    {
      "id": "6a998709991d16e5e66e1a86",
      "collection": "audio-catalogue",
      "title": "German (Germany) scripted microphone",
      "slug": "deu-asr001",
      "url": "/data-catalog/audio-catalogue/deu-asr001",
      "featured": false,
      "datasetId": "DEU_ASR001",
      "locale": [
        "de-DE"
      ],
      "country": "Germany",
      "languageGroup": "German",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "16.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "48"
      ],
      "dataFormat": "raw PCM",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;Each speaker read 100 prompts including digits, natural numbers, personal and city names, telephone numbers, generic command and control items, phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a998708e924c86953f8ede3",
      "collection": "audio-catalogue",
      "title": "Dari (Afghanistan) broadcast",
      "slug": "dar-brc001",
      "url": "/data-catalog/audio-catalogue/dar-brc001",
      "featured": false,
      "datasetId": "DAR_BRC001",
      "locale": [
        "fa-AF"
      ],
      "country": "Afghanistan",
      "languageGroup": "Dari",
      "audioType": "Broadcast Speech",
      "domainContent": [
        "Broadcast Media (talk shows, interviews, news)"
      ],
      "volume": "49",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16",
        "22",
        "32",
        "44",
        "48"
      ],
      "dataFormat": "wav",
      "recordingDevice": "",
      "recordingCondition": "Low background noise (studio)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Pronunciation lexicon not currently available but can be developed upon request;Dataset is largely speech only and does not include music or advertisements;Data types include: talk shows, interviews, news broadcasts (excluding news reading by anchors);13% landline, 87% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2017"
      ]
    },
    {
      "id": "6a9987076d858e464b6629cb",
      "collection": "audio-catalogue",
      "title": "Dari (Afghanistan) conversational telephony",
      "slug": "dar-asr001",
      "url": "/data-catalog/audio-catalogue/dar-asr001",
      "featured": false,
      "datasetId": "DAR_ASR001",
      "locale": [
        "fa-AF"
      ],
      "country": "Afghanistan",
      "languageGroup": "Dari",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "40",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;Dataset is largely speech only and does not include music or advertisements;13% landline, 87% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2010"
      ]
    },
    {
      "id": "6a998706e924c86953f8ec68",
      "collection": "audio-catalogue",
      "title": "Czech (Czech Republic) scripted telephony",
      "slug": "czech-speechdat-e-dataset",
      "url": "/data-catalog/audio-catalogue/czech-speechdat-e-dataset",
      "featured": false,
      "datasetId": "Czech SpeechDat(E) Dataset",
      "locale": [
        "cs-CZ"
      ],
      "country": "Czech Republic",
      "languageGroup": "Czech",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "93.33",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;52 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items, and phonetically rich words and sentences",
      "source": "Nuance",
      "yearOfCollection": []
    },
    {
      "id": "6a9987056d858e464b662934",
      "collection": "audio-catalogue",
      "title": "Czech (Czech Republic) scripted microphone",
      "slug": "cze-asr001",
      "url": "/data-catalog/audio-catalogue/cze-asr001",
      "featured": false,
      "datasetId": "CZE_ASR001",
      "locale": [
        "cs-CZ"
      ],
      "country": "Czech Republic",
      "languageGroup": "Czech",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "31",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1998"
      ]
    },
    {
      "id": "6a99870417854c543f93a8df",
      "collection": "audio-catalogue",
      "title": "Croatian (Croatia) scripted microphone",
      "slug": "cro-asr002",
      "url": "/data-catalog/audio-catalogue/cro-asr002",
      "featured": false,
      "datasetId": "CRO_ASR002",
      "locale": [
        "hr-HR"
      ],
      "country": "Croatia",
      "languageGroup": "Croatian",
      "audioType": "Scripted Speech",
      "domainContent": [
        "News (read speech)"
      ],
      "volume": "11",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Microphone",
      "recordingCondition": "Mixed (quiet home/office, public, outdoor)",
      "datasetDescription": "Part of a multilingual corpus; tiered package prices available with purchase of multiple Global Phone languages or the full corpus ; Dataset is fully transcribed and the transcription is available both in original script and in Romanized form;Each speaker reads a number of phonetically rich sentences selected from national newspaper articles available from the web to cover a wide domain with large vocabulary;Developed in collaboration with the Karlsruhe Institute of Technology (KIT)",
      "source": "GlobalPhone",
      "yearOfCollection": [
        "1996",
        "1997"
      ]
    },
    {
      "id": "6a9987036ab94adf346e6d7b",
      "collection": "audio-catalogue",
      "title": "Croatian (Croatia) conversational telephony",
      "slug": "cro-asr001",
      "url": "/data-catalog/audio-catalogue/cro-asr001",
      "featured": false,
      "datasetId": "CRO_ASR001",
      "locale": [
        "hr-HR"
      ],
      "country": "Croatia",
      "languageGroup": "Croatian",
      "audioType": "Conversational Speech",
      "domainContent": [
        "News & Current Affairs",
        "Health and Sport"
      ],
      "volume": "39.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers;53% landline, 47% mobile;Conversations cover a range of topics including: News & Current Affairs, Health and Sport.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a9987026ab94adf346e6c8c",
      "collection": "audio-catalogue",
      "title": "Arabic (United Arab Emirates (UAE)/ Saudi Arabia) scripted microphone",
      "slug": "cga-asr001",
      "url": "/data-catalog/audio-catalogue/cga-asr001",
      "featured": false,
      "datasetId": "CGA_ASR001",
      "locale": [
        "ar-AE"
      ],
      "country": "United Arab Emirates (UAE) - Saudi Arabia",
      "languageGroup": "Arabic",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "86",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "16"
      ],
      "dataFormat": "raw PCM",
      "recordingDevice": "Microphone",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Fully transcribed with acoustic event tagging derived from the SpeechDAT conventions ; Dataset is accompanied by a pronunciation lexicon containing all transcribed words;All transcriptions fully vowelized;280 prompts per speaker including 30 Person names (first name and family name) from a set of 15, 10 single isolated digits 0-10, 8-digit sequences (randomly generated), 200 phonetically balanced sentences, 30 x 10-word phonetically balanced word strings",
      "source": "Appen Global",
      "yearOfCollection": [
        "2003"
      ]
    },
    {
      "id": "6a99870129d74d9309f35b4c",
      "collection": "audio-catalogue",
      "title": "Bulgarian (Bulgaria) conversational telephony",
      "slug": "bul-asr001",
      "url": "/data-catalog/audio-catalogue/bul-asr001",
      "featured": false,
      "datasetId": "BUL_ASR001",
      "locale": [
        "bg-BG"
      ],
      "country": "Bulgaria",
      "languageGroup": "Bulgarian",
      "audioType": "Conversational Speech",
      "domainContent": [
        "Holiday/Leisure",
        "Movies/TV Shows and Work"
      ],
      "volume": "38.5",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;200 telephony conversations are recorded for this project - 100 speakers make 2 calls each (1 from landline, 1 from mobile) to a pool of 100 call receivers;49% landline, 51% mobile;Conversations cover a range of topics including: Holiday/Leisure, Movies/TV Shows and Work.",
      "source": "Appen Global",
      "yearOfCollection": [
        "2009"
      ]
    },
    {
      "id": "6a998700d3a0ae3d2978d48b",
      "collection": "audio-catalogue",
      "title": "Bengali (Bangladesh) conversational telephony",
      "slug": "ben-asr001",
      "url": "/data-catalog/audio-catalogue/ben-asr001",
      "featured": false,
      "datasetId": "BEN_ASR001",
      "locale": [
        "bn-BD"
      ],
      "country": "Bangladesh",
      "languageGroup": "Bengali",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "47",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed (in-car, roadside, home/office)",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2008",
        "2009"
      ]
    },
    {
      "id": "6a9986ff6ab94adf346e69a7",
      "collection": "audio-catalogue",
      "title": "French (Belgium) scripted telephony",
      "slug": "belgian-french-speechdat-ii-fdb-1000-fixed1bf",
      "url": "/data-catalog/audio-catalogue/belgian-french-speechdat-ii-fdb-1000-fixed1bf",
      "featured": false,
      "datasetId": "Belgian French SpeechDat(II) FDB-1000 (FIXED1BF)",
      "locale": [
        "id-ID"
      ],
      "country": "Belgium",
      "languageGroup": "French",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "76.67",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw",
      "recordingDevice": "Landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed to SpeechDAT type conventions and is accompanied by a pronunciation lexicon and validation report;53 prompts per speaker including digits, natural numbers, letter strings, personal, place and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words and spontaneous items for control",
      "source": "Nuance",
      "yearOfCollection": [
        "1998"
      ]
    },
    {
      "id": "6a9986fe040b228014999b69",
      "collection": "audio-catalogue",
      "title": "Bahasa Indonesia conversational telephony",
      "slug": "bah-asr001",
      "url": "/data-catalog/audio-catalogue/bah-asr001",
      "featured": false,
      "datasetId": "BAH_ASR001",
      "locale": [
        "id-ID"
      ],
      "country": "Indonesia",
      "languageGroup": "Indonesian",
      "audioType": "Conversational Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "31",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise",
      "datasetDescription": "Dataset is fully transcribed and timestamped;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;For a large proportion of calls, only one half of the conversation was collected and transcribed;28% landline, 72% mobile",
      "source": "Appen Global",
      "yearOfCollection": [
        "2013"
      ]
    },
    {
      "id": "6a9986fd89ead58b4c205f7b",
      "collection": "audio-catalogue",
      "title": "English (Australia) scripted telephony",
      "slug": "aus-asr002",
      "url": "/data-catalog/audio-catalogue/aus-asr002",
      "featured": false,
      "datasetId": "AUS_ASR002",
      "locale": [
        "en-AU"
      ],
      "country": "Australia",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "118",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Mixed",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;75 prompts per speaker including digits, natural numbers, letter strings, personal, place, and business names, confirmation items (yes, no + fuzzy), generic command and control items, phonetically rich sentences and words;The prompts are a mixture of 'read' and 'elicited' items where 5 prompts per script are 'spontaneous free speech'",
      "source": "Appen Global",
      "yearOfCollection": [
        "2005"
      ]
    },
    {
      "id": "6a9986fc38e229b39cdd1c41",
      "collection": "audio-catalogue",
      "title": "English (Australia) scripted telephony",
      "slug": "aus-asr001",
      "url": "/data-catalog/audio-catalogue/aus-asr001",
      "featured": false,
      "datasetId": "AUS_ASR001",
      "locale": [
        "en-AU"
      ],
      "country": "Australia",
      "languageGroup": "English",
      "audioType": "Scripted Speech",
      "domainContent": [
        "General / not domain-specific (read speech, digits, names, command & control)"
      ],
      "volume": "92",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [
        "8"
      ],
      "dataFormat": "alaw or wav",
      "recordingDevice": "Mobile phone and landline",
      "recordingCondition": "Low background noise (home/office)",
      "datasetDescription": "Fully transcribed to SpeechDAT type conventions;Dataset is accompanied by a pronunciation lexicon containing all transcribed words;162 prompts (read speech) per speaker including digits, natural numbers, letter strings, personal, place, and business names, confirmation items (yes, no + fuzzy), generic command and control items (from a set of 215), phonetically rich sentences and words",
      "source": "Appen Global",
      "yearOfCollection": [
        "2004"
      ]
    },
    {
      "id": "6a9986fb84235eb50a0e84b9",
      "collection": "audio-catalogue",
      "title": "Dutch (The Netherlands) call centre audio",
      "slug": "nld-cc001",
      "url": "/data-catalog/audio-catalogue/nld-cc001",
      "featured": false,
      "datasetId": "NLD_CC001",
      "locale": [
        "nl-NL"
      ],
      "country": "The Netherlands",
      "languageGroup": "Dutch",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ecommerce",
        "retail"
      ],
      "volume": "500",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986faf4ac0d8edcf39a19",
      "collection": "audio-catalogue",
      "title": "Dutch (Belgium) call centre audio",
      "slug": "nlb-cc001",
      "url": "/data-catalog/audio-catalogue/nlb-cc001",
      "featured": false,
      "datasetId": "NLB_CC001",
      "locale": [
        "nl-BE"
      ],
      "country": "Belgium",
      "languageGroup": "Dutch",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ecommerce",
        "retail"
      ],
      "volume": "600",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f99ec510f7c328cf7e",
      "collection": "audio-catalogue",
      "title": "French (France) call centre audio",
      "slug": "frf-cc001",
      "url": "/data-catalog/audio-catalogue/frf-cc001",
      "featured": false,
      "datasetId": "FRF_CC001",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Mix"
      ],
      "volume": "300",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f8e6ee6e81af9ade6a",
      "collection": "audio-catalogue",
      "title": "French (Belgium) call centre audio",
      "slug": "frb-cc001",
      "url": "/data-catalog/audio-catalogue/frb-cc001",
      "featured": false,
      "datasetId": "FRB_CC001",
      "locale": [
        "fr-BE"
      ],
      "country": "Belgium",
      "languageGroup": "French",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Mix utility",
        "telecom",
        "energy",
        "retail"
      ],
      "volume": "914",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f7811b8e5d73618028",
      "collection": "audio-catalogue",
      "title": "Arabic (Egypt) call centre audio - Telecom",
      "slug": "are-cc002",
      "url": "/data-catalog/audio-catalogue/are-cc002",
      "featured": false,
      "datasetId": "ARE_CC002",
      "locale": [
        "ar-EG"
      ],
      "country": "Egypt",
      "languageGroup": "Arabic",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Telecom"
      ],
      "volume": "300",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f738e229b39cdd1a1d",
      "collection": "audio-catalogue",
      "title": "Arabic (Egypt) call centre audio - Finance",
      "slug": "are-cc001",
      "url": "/data-catalog/audio-catalogue/are-cc001",
      "featured": false,
      "datasetId": "ARE_CC001",
      "locale": [
        "ar-EG"
      ],
      "country": "Egypt",
      "languageGroup": "Arabic",
      "audioType": "Real world call center audio",
      "domainContent": [
        "F&B"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f6d80c25273cff2c79",
      "collection": "audio-catalogue",
      "title": "Thai (Thailand) simulated call centre audio 3",
      "slug": "tha-scc003",
      "url": "/data-catalog/audio-catalogue/tha-scc003",
      "featured": false,
      "datasetId": "THA_SCC003",
      "locale": [
        "th-TH"
      ],
      "country": "Thailand",
      "languageGroup": "Thai",
      "audioType": "Simulated Conversations",
      "domainContent": [
        "Government / Telecom"
      ],
      "volume": "9000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f5e924c86953f8e251",
      "collection": "audio-catalogue",
      "title": "Thai (Thailand) simulated call centre audio 2",
      "slug": "tha-scc002",
      "url": "/data-catalog/audio-catalogue/tha-scc002",
      "featured": false,
      "datasetId": "THA_SCC002",
      "locale": [
        "th-TH"
      ],
      "country": "Thailand",
      "languageGroup": "Thai",
      "audioType": "Simulated Conversations",
      "domainContent": [
        "Call center",
        "diverse domains",
        "Human to machine"
      ],
      "volume": "125",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f484235eb50a0e7df0",
      "collection": "audio-catalogue",
      "title": "Thai (Thailand) simulated call centre audio 1",
      "slug": "tha-scc001",
      "url": "/data-catalog/audio-catalogue/tha-scc001",
      "featured": false,
      "datasetId": "THA_SCC001",
      "locale": [
        "th-TH"
      ],
      "country": "Thailand",
      "languageGroup": "Thai",
      "audioType": "Simulated Conversations",
      "domainContent": [
        "Call center",
        "diverse domains",
        "Human to human"
      ],
      "volume": "175",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f3811b8e5d73617d4d",
      "collection": "audio-catalogue",
      "title": "Telugu (India) call centre audio - Ecommerce",
      "slug": "tel-cc002",
      "url": "/data-catalog/audio-catalogue/tel-cc002",
      "featured": false,
      "datasetId": "TEL_CC002",
      "locale": [
        "te-IN"
      ],
      "country": "India",
      "languageGroup": "Telugu",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ecommerce"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f2fa9df117f35885fe",
      "collection": "audio-catalogue",
      "title": "Telugu (India) call centre audio - Finance",
      "slug": "tel-cc001",
      "url": "/data-catalog/audio-catalogue/tel-cc001",
      "featured": false,
      "datasetId": "TEL_CC001",
      "locale": [
        "te-IN"
      ],
      "country": "India",
      "languageGroup": "Telugu",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Loan Recovery"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f16ab94adf346e5c94",
      "collection": "audio-catalogue",
      "title": "Tamil (India) call centre audio - Telecom",
      "slug": "tam-cc008",
      "url": "/data-catalog/audio-catalogue/tam-cc008",
      "featured": false,
      "datasetId": "TAM_CC008",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Telecom"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986f038e229b39cdd1741",
      "collection": "audio-catalogue",
      "title": "Tamil (India) call centre audio - Ed Tech",
      "slug": "tam-cc007",
      "url": "/data-catalog/audio-catalogue/tam-cc007",
      "featured": false,
      "datasetId": "TAM_CC007",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ed Tech"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986ef57206d63ef25e06f",
      "collection": "audio-catalogue",
      "title": "Tamil (India) call centre audio - Logistics",
      "slug": "tam-cc006",
      "url": "/data-catalog/audio-catalogue/tam-cc006",
      "featured": false,
      "datasetId": "TAM_CC006",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Logistics"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986ee84235eb50a0e7759",
      "collection": "audio-catalogue",
      "title": "Tamil (India) call centre audio - Real Estate",
      "slug": "tam-cc005",
      "url": "/data-catalog/audio-catalogue/tam-cc005",
      "featured": false,
      "datasetId": "TAM_CC005",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Real Estate"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986ed17376764883d96c2",
      "collection": "audio-catalogue",
      "title": "Tamil (India) call centre audio - Travel",
      "slug": "tam-cc004",
      "url": "/data-catalog/audio-catalogue/tam-cc004",
      "featured": false,
      "datasetId": "TAM_CC004",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Travel & Hospitality"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986ec811b8e5d736178dc",
      "collection": "audio-catalogue",
      "title": "Tamil (India) call centre audio - Banking",
      "slug": "tam-cc003",
      "url": "/data-catalog/audio-catalogue/tam-cc003",
      "featured": false,
      "datasetId": "TAM_CC003",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Banking"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986ebaa89b6c9886df151",
      "collection": "audio-catalogue",
      "title": "Tamil (India) call centre audio - Ecommerce",
      "slug": "tam-cc002",
      "url": "/data-catalog/audio-catalogue/tam-cc002",
      "featured": false,
      "datasetId": "TAM_CC002",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ecommerce"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986ea811b8e5d736177a4",
      "collection": "audio-catalogue",
      "title": "Tamil (India) call centre audio - Finance",
      "slug": "tam-cc001",
      "url": "/data-catalog/audio-catalogue/tam-cc001",
      "featured": false,
      "datasetId": "TAM_CC001",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Loan Recovery"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986e99ec510f7c328c873",
      "collection": "audio-catalogue",
      "title": "Tagalog (Philippines) simulated call centre audio",
      "slug": "tgl-scc001",
      "url": "/data-catalog/audio-catalogue/tgl-scc001",
      "featured": false,
      "datasetId": "TGL_SCC001",
      "locale": [
        "tl-PH"
      ],
      "country": "Philippines",
      "languageGroup": "Tagalog",
      "audioType": "Simulated Conversations",
      "domainContent": [
        "Diverse"
      ],
      "volume": "450",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986e8d3a0ae3d2978c48b",
      "collection": "audio-catalogue",
      "title": "Spanish (Spain) call centre audio - Various",
      "slug": "esp-cc001",
      "url": "/data-catalog/audio-catalogue/esp-cc001",
      "featured": false,
      "datasetId": "ESP_CC001",
      "locale": [
        "es-ES"
      ],
      "country": "Spain",
      "languageGroup": "Spanish",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Mix Telecom / Energy / Medicare"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986e710482f3af4000ed9",
      "collection": "audio-catalogue",
      "title": "Malayam (India) call centre audio - Ecommerce",
      "slug": "mal-cc002",
      "url": "/data-catalog/audio-catalogue/mal-cc002",
      "featured": false,
      "datasetId": "MAL_CC002",
      "locale": [
        "ml-IN"
      ],
      "country": "India",
      "languageGroup": "Malayalam",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ecommerce"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986e69ec510f7c328c6d7",
      "collection": "audio-catalogue",
      "title": "Malayam (India) call centre audio - Finance",
      "slug": "mal-cc001",
      "url": "/data-catalog/audio-catalogue/mal-cc001",
      "featured": false,
      "datasetId": "MAL_CC001",
      "locale": [
        "ml-IN"
      ],
      "country": "India",
      "languageGroup": "Malayalam",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Loan Recovery"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986e5e57f73b05ad248be",
      "collection": "audio-catalogue",
      "title": "Kannada (India) call centre audio - Ecommerce",
      "slug": "kan-cc002",
      "url": "/data-catalog/audio-catalogue/kan-cc002",
      "featured": false,
      "datasetId": "KAN_CC002",
      "locale": [
        "kn-IN"
      ],
      "country": "India",
      "languageGroup": "Kannada",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ecommerce"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986e1811b8e5d736173eb",
      "collection": "audio-catalogue",
      "title": "Kannada (India) call centre audio - Finance",
      "slug": "kan-cc001",
      "url": "/data-catalog/audio-catalogue/kan-cc001",
      "featured": false,
      "datasetId": "KAN_CC001",
      "locale": [
        "kn-IN"
      ],
      "country": "India",
      "languageGroup": "Kannada",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Loan Recovery"
      ],
      "volume": "500",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986e0fa9df117f3587bbc",
      "collection": "audio-catalogue",
      "title": "Indonesian (Indonesia) call centre audio - Finance",
      "slug": "bah-cc002",
      "url": "/data-catalog/audio-catalogue/bah-cc002",
      "featured": false,
      "datasetId": "BAH_CC002",
      "locale": [
        "id-ID"
      ],
      "country": "Indonesia",
      "languageGroup": "Indonesian",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Finance & Banking"
      ],
      "volume": "400",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986df9ec510f7c328c37e",
      "collection": "audio-catalogue",
      "title": "Indonesian (Indonesia) call centre audio - Fintech/Telecom",
      "slug": "bah-cc001",
      "url": "/data-catalog/audio-catalogue/bah-cc001",
      "featured": false,
      "datasetId": "BAH_CC001",
      "locale": [
        "id-ID"
      ],
      "country": "Indonesia",
      "languageGroup": "Indonesian",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Fintech / Telecom"
      ],
      "volume": "420",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986df6ab94adf346e4e38",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Telecom",
      "slug": "hin-cc010",
      "url": "/data-catalog/audio-catalogue/hin-cc010",
      "featured": false,
      "datasetId": "HIN_CC010",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Telecom"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986de17956efcbddc69e7",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Automotive",
      "slug": "hin-cc009",
      "url": "/data-catalog/audio-catalogue/hin-cc009",
      "featured": false,
      "datasetId": "HIN_CC009",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Automotive"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986dd8afbba395744ebf4",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Healthcare",
      "slug": "hin-cc008",
      "url": "/data-catalog/audio-catalogue/hin-cc008",
      "featured": false,
      "datasetId": "HIN_CC008",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Healthcare"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986dc8afbba395744ebc6",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Finance 4",
      "slug": "hin-cc007",
      "url": "/data-catalog/audio-catalogue/hin-cc007",
      "featured": false,
      "datasetId": "HIN_CC007",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Banking & Finance"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986dbeaf7c7f9ff51423f",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Real Estate",
      "slug": "hin-cc006",
      "url": "/data-catalog/audio-catalogue/hin-cc006",
      "featured": false,
      "datasetId": "HIN_CC006",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Real Estate"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986dab779334273e902eb",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Finance 3",
      "slug": "hin-cc005",
      "url": "/data-catalog/audio-catalogue/hin-cc005",
      "featured": false,
      "datasetId": "HIN_CC005",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Car Sale (Car24)"
      ],
      "volume": "96",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d9eeecffe16117fd7b",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Finance 2",
      "slug": "hin-cc004",
      "url": "/data-catalog/audio-catalogue/hin-cc004",
      "featured": false,
      "datasetId": "HIN_CC004",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Loan Promotion"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d8eeecffe16117fcd6",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio",
      "slug": "hin-cc003",
      "url": "/data-catalog/audio-catalogue/hin-cc003",
      "featured": false,
      "datasetId": "HIN_CC003",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "My Operator"
      ],
      "volume": "105",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d7040b228014998394",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Finance 1",
      "slug": "hin-cc002",
      "url": "/data-catalog/audio-catalogue/hin-cc002",
      "featured": false,
      "datasetId": "HIN_CC002",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Loan Recovery"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d6fa9df117f3587472",
      "collection": "audio-catalogue",
      "title": "Hindi (India) call centre audio - Ecommerce",
      "slug": "hin-cc001",
      "url": "/data-catalog/audio-catalogue/hin-cc001",
      "featured": false,
      "datasetId": "HIN_CC001",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ecommerce"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d5eaf7c7f9ff513c0c",
      "collection": "audio-catalogue",
      "title": "English simulated call centre audio",
      "slug": "eng-scc001",
      "url": "/data-catalog/audio-catalogue/eng-scc001",
      "featured": false,
      "datasetId": "ENG_SCC001",
      "locale": [
        "en-Multi"
      ],
      "country": "Multiple",
      "languageGroup": "English",
      "audioType": "Simulated Conversations",
      "domainContent": [
        "Call center",
        "different moods",
        "diverse domains"
      ],
      "volume": "150",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d46ab94adf346e4993",
      "collection": "audio-catalogue",
      "title": "English (Philippines) simulated call centre audio 2",
      "slug": "enf-scc002",
      "url": "/data-catalog/audio-catalogue/enf-scc002",
      "featured": false,
      "datasetId": "ENF_SCC002",
      "locale": [
        "en-PH"
      ],
      "country": "Philippines",
      "languageGroup": "English",
      "audioType": "Simulated Conversations",
      "domainContent": [
        "Call center",
        "diverse domains (studio environment)"
      ],
      "volume": "130",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d3040b228014997f56",
      "collection": "audio-catalogue",
      "title": "English (Philippines) simulated call centre audio 1",
      "slug": "enf-scc001",
      "url": "/data-catalog/audio-catalogue/enf-scc001",
      "featured": false,
      "datasetId": "ENF_SCC001",
      "locale": [
        "en-PH"
      ],
      "country": "Philippines",
      "languageGroup": "English",
      "audioType": "Simulated Conversations",
      "domainContent": [
        "Call center",
        "diverse domains"
      ],
      "volume": "60",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d129d74d9309f34e7d",
      "collection": "audio-catalogue",
      "title": "English (United States) medical dictation audio",
      "slug": "use-med001",
      "url": "/data-catalog/audio-catalogue/use-med001",
      "featured": false,
      "datasetId": "USE_MED001",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Real world medical dictation audio",
      "domainContent": [
        "Healthcare"
      ],
      "volume": "1300",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986d0f41547c318e6598f",
      "collection": "audio-catalogue",
      "title": "Vietnamese (Vietnam) doctor-patient conversational audio",
      "slug": "vie-doc001",
      "url": "/data-catalog/audio-catalogue/vie-doc001",
      "featured": false,
      "datasetId": "VIE_DOC001",
      "locale": [
        "vi-VN"
      ],
      "country": "Vietnam",
      "languageGroup": "Vietnamese",
      "audioType": "Real world doctor patient conversation",
      "domainContent": [
        "Healthcare"
      ],
      "volume": "2000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986cfd80c25273cff19ba",
      "collection": "audio-catalogue",
      "title": "English Medical Dictation Audio + Doctor SOAP Reports",
      "slug": "eng-med-001",
      "url": "/data-catalog/audio-catalogue/eng-med-001",
      "featured": false,
      "datasetId": "ENG_MED_001",
      "locale": [
        "en"
      ],
      "country": "",
      "languageGroup": "English",
      "audioType": "Real world medical dictation audio",
      "domainContent": [
        "Healthcare / Clinical Documentation"
      ],
      "volume": "1500",
      "unitType": "hours",
      "channel": "",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "Real medical dictation audio recordings paired with original doctor-authored SOAP (Subjective, Objective, Assessment, Plan) reports. Suited for medical ASR, clinical NLP, and documentation-automation model training.",
      "source": "Third Party Vendor",
      "yearOfCollection": [
        "2022 - 2025"
      ]
    },
    {
      "id": "6a9986cee57f73b05ad23c2b",
      "collection": "audio-catalogue",
      "title": "English doctor-patient conversational audio",
      "slug": "eng-doc001",
      "url": "/data-catalog/audio-catalogue/eng-doc001",
      "featured": false,
      "datasetId": "ENG_DOC001",
      "locale": [
        "en"
      ],
      "country": "",
      "languageGroup": "English",
      "audioType": "Real world doctor patient conversation",
      "domainContent": [
        "Healthcare"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986cd040b228014997cde",
      "collection": "audio-catalogue",
      "title": "English (India) call centre audio - Health 2",
      "slug": "eni-cc005",
      "url": "/data-catalog/audio-catalogue/eni-cc005",
      "featured": false,
      "datasetId": "ENI_CC005",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Covid test kit"
      ],
      "volume": "1600",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986ccd3a0ae3d2978aa81",
      "collection": "audio-catalogue",
      "title": "English (India) call centre audio - Telecom",
      "slug": "eni-cc004",
      "url": "/data-catalog/audio-catalogue/eni-cc004",
      "featured": false,
      "datasetId": "ENI_CC004",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Telecom"
      ],
      "volume": "8000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986cbf41547c318e655f7",
      "collection": "audio-catalogue",
      "title": "English (India) call centre audio - Finance",
      "slug": "eni-cc003",
      "url": "/data-catalog/audio-catalogue/eni-cc003",
      "featured": false,
      "datasetId": "ENI_CC003",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Student Loan"
      ],
      "volume": "206",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986ca040b22801499797e",
      "collection": "audio-catalogue",
      "title": "English (United States) call centre audio - Medical",
      "slug": "use-cc007",
      "url": "/data-catalog/audio-catalogue/use-cc007",
      "featured": false,
      "datasetId": "USE_CC007",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Medical / CS Appt"
      ],
      "volume": "15000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c9e924c86953f8c794",
      "collection": "audio-catalogue",
      "title": "English (India) call centre audio - Medical Equipment",
      "slug": "eni-cc002",
      "url": "/data-catalog/audio-catalogue/eni-cc002",
      "featured": false,
      "datasetId": "ENI_CC002",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Medical Equipment"
      ],
      "volume": "2000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c8f41547c318e653b6",
      "collection": "audio-catalogue",
      "title": "English (Philippines) call centre audio - Medicine",
      "slug": "enf-cc002",
      "url": "/data-catalog/audio-catalogue/enf-cc002",
      "featured": false,
      "datasetId": "ENF_CC002",
      "locale": [
        "en-PH"
      ],
      "country": "Philippines",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Masstort / Medicare",
        "Medical Insurance/ Pharmacy"
      ],
      "volume": "10000",
      "unitType": "hours",
      "channel": "Both",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c717956efcbddc5795",
      "collection": "audio-catalogue",
      "title": "English (Philippines) call centre audio - Insurance",
      "slug": "enf-cc001",
      "url": "/data-catalog/audio-catalogue/enf-cc001",
      "featured": false,
      "datasetId": "ENF_CC001",
      "locale": [
        "en-PH"
      ],
      "country": "Philippines",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Insurance"
      ],
      "volume": "148",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c689ead58b4c205714",
      "collection": "audio-catalogue",
      "title": "English (United States) call centre audio - Home",
      "slug": "use-cc006",
      "url": "/data-catalog/audio-catalogue/use-cc006",
      "featured": false,
      "datasetId": "USE_CC006",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Home Service"
      ],
      "volume": "3000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c5040b228014997410",
      "collection": "audio-catalogue",
      "title": "English (United States) call centre audio - Finance",
      "slug": "use-cc005",
      "url": "/data-catalog/audio-catalogue/use-cc005",
      "featured": false,
      "datasetId": "USE_CC005",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Final Expense"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c4f41547c318e65063",
      "collection": "audio-catalogue",
      "title": "English (United States) call centre audio - Transport 4",
      "slug": "use-cc004",
      "url": "/data-catalog/audio-catalogue/use-cc004",
      "featured": false,
      "datasetId": "USE_CC004",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Automotive"
      ],
      "volume": "30000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c3991d16e5e66df899",
      "collection": "audio-catalogue",
      "title": "English (United States) call centre audio - Transport 3",
      "slug": "use-cc003",
      "url": "/data-catalog/audio-catalogue/use-cc003",
      "featured": false,
      "datasetId": "USE_CC003",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Airline"
      ],
      "volume": "2154",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c2afc3cfd64e663dc1",
      "collection": "audio-catalogue",
      "title": "English (United States) call centre audio - Transport 2",
      "slug": "use-cc002",
      "url": "/data-catalog/audio-catalogue/use-cc002",
      "featured": false,
      "datasetId": "USE_CC002",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Taxi"
      ],
      "volume": "5000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c2834e4fbc0a91b5ba",
      "collection": "audio-catalogue",
      "title": "English (India) call centre audio - Health 1",
      "slug": "eni-cc001",
      "url": "/data-catalog/audio-catalogue/eni-cc001",
      "featured": false,
      "datasetId": "ENI_CC001",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Diabetic"
      ],
      "volume": "2000",
      "unitType": "hours",
      "channel": "Mono",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c189ead58b4c2054af",
      "collection": "audio-catalogue",
      "title": "English (United States) call centre audio - Transport 1",
      "slug": "use-cc001",
      "url": "/data-catalog/audio-catalogue/use-cc001",
      "featured": false,
      "datasetId": "USE_CC001",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Transport Services"
      ],
      "volume": "300",
      "unitType": "hours",
      "channel": "Both",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a9986c0f4ac0d8edcf37a9d",
      "collection": "audio-catalogue",
      "title": "Bengali (India) call centre audio - Ecommerce",
      "slug": "ben-cc001",
      "url": "/data-catalog/audio-catalogue/ben-cc001",
      "featured": false,
      "datasetId": "BEN_CC001",
      "locale": [
        "bn-IN"
      ],
      "country": "India",
      "languageGroup": "Bengali",
      "audioType": "Real world call center audio",
      "domainContent": [
        "Ecommerce"
      ],
      "volume": "1000",
      "unitType": "hours",
      "channel": "Stereo",
      "sampleRateKhz": [],
      "dataFormat": "",
      "recordingDevice": "",
      "recordingCondition": "",
      "datasetDescription": "",
      "source": "Third Party Vendor",
      "yearOfCollection": []
    },
    {
      "id": "6a998817afc3cfd64e665233",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Morocco) conversational telephony translation",
      "slug": "ary-mt001",
      "url": "/data-catalog/pronunciation-dictionaries/ary-mt001",
      "featured": false,
      "datasetId": "ARY_MT001",
      "locale": [
        "ar-MA"
      ],
      "country": "Morocco",
      "languageGroup": "Arabic",
      "category": "Conversational Translation",
      "volume": "80,430 utterances",
      "unitType": "utterances",
      "dataFormat": "txt",
      "datasetDescription": "Corresponding audio, transcription, fully reversible romanised transcription and pronunciation lexicon data are available (ARY_ASR001, ARY_ASRMT001)",
      "source": "Appen Global",
      "yearOfCollection": "2019"
    },
    {
      "id": "6a99881689ead58b4c20825b",
      "collection": "pronunciation-dictionaries",
      "title": "Tagalog (Philippines) Offensive Wordlist",
      "slug": "tgl-phl-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/tgl-phl-ner001",
      "featured": false,
      "datasetId": "tgl_PHL_NER001",
      "locale": [
        "tl-PH"
      ],
      "country": "Philippines",
      "languageGroup": "Tagalog",
      "category": "Offensive NER",
      "volume": "4,526 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a998815a24dcd7124d6f982",
      "collection": "pronunciation-dictionaries",
      "title": "Swedish (Sweden) Offensive Wordlist",
      "slug": "swe-swe-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/swe-swe-ner001",
      "featured": false,
      "datasetId": "swe_SWE_NER001",
      "locale": [
        "sv-SE"
      ],
      "country": "Sweden",
      "languageGroup": "Swedish",
      "category": "Offensive NER",
      "volume": "3,480 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a998814afc3cfd64e66512e",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Mexico) Offensive Wordlist",
      "slug": "spa-mex-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/spa-mex-ner001",
      "featured": false,
      "datasetId": "spa_MEX_NER001",
      "locale": [
        "es-MX"
      ],
      "country": "Mexico",
      "languageGroup": "Spanish",
      "category": "Offensive NER",
      "volume": "4,306 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a998813e924c86953f979cb",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Colombia) Offensive Wordlist",
      "slug": "spa-col-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/spa-col-ner001",
      "featured": false,
      "datasetId": "spa_COL_NER001",
      "locale": [
        "es-CO"
      ],
      "country": "Colombia",
      "languageGroup": "Spanish",
      "category": "Offensive NER",
      "volume": "5,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a998812e924c86953f978a4",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Spain) Offensive Wordlist",
      "slug": "spa-esp-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/spa-esp-ner001",
      "featured": false,
      "datasetId": "spa_ESP_NER001",
      "locale": [
        "es-ES"
      ],
      "country": "Spain",
      "languageGroup": "Spanish",
      "category": "Offensive NER",
      "volume": "4,313 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a99881273f796e259270227",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Argentina) Offensive Wordlist",
      "slug": "spa-arg-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/spa-arg-ner001",
      "featured": false,
      "datasetId": "spa_ARG_NER001",
      "locale": [
        "es-AR"
      ],
      "country": "Argentina",
      "languageGroup": "Spanish",
      "category": "Offensive NER",
      "volume": "5,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a998811f4c0365c95aeb22a",
      "collection": "pronunciation-dictionaries",
      "title": "Portuguese (Portugal) Offensive Wordlist",
      "slug": "por-prt-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/por-prt-ner001",
      "featured": false,
      "datasetId": "por_PRT_NER001",
      "locale": [
        "pt-PT"
      ],
      "country": "Portugal",
      "languageGroup": "Portuguese",
      "category": "Offensive NER",
      "volume": "4,628 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a998810bc894a1ebfd44e72",
      "collection": "pronunciation-dictionaries",
      "title": "Portuguese (Brazil) Offensive Wordlist",
      "slug": "por-bra-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/por-bra-ner001",
      "featured": false,
      "datasetId": "por_BRA_NER001",
      "locale": [
        "pt-BR"
      ],
      "country": "Brazil",
      "languageGroup": "Portuguese",
      "category": "Offensive NER",
      "volume": "3,588 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a99880f31d6f8d8f3d0dfe5",
      "collection": "pronunciation-dictionaries",
      "title": "Italian (Italy) Offensive Wordlist",
      "slug": "ita-ita-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/ita-ita-ner001",
      "featured": false,
      "datasetId": "ita_ITA_NER001",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "category": "Offensive NER",
      "volume": "2,443 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a99880e17376764883ddd35",
      "collection": "pronunciation-dictionaries",
      "title": "German (Germany) Offensive Wordlist",
      "slug": "deu-deu-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/deu-deu-ner001",
      "featured": false,
      "datasetId": "deu_DEU_NER001",
      "locale": [
        "de-DE"
      ],
      "country": "Germany",
      "languageGroup": "German",
      "category": "Offensive NER",
      "volume": "4,965 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a99880df3c00f7b2dc20c05",
      "collection": "pronunciation-dictionaries",
      "title": "French (France) Offensive Wordlist",
      "slug": "fra-fra-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/fra-fra-ner001",
      "featured": false,
      "datasetId": "fra_FRA_NER001",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "category": "Offensive NER",
      "volume": "4,986 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a99880c31d6f8d8f3d0df89",
      "collection": "pronunciation-dictionaries",
      "title": "Dutch (Netherlands) Offensive Wordlist",
      "slug": "nld-nld-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/nld-nld-ner001",
      "featured": false,
      "datasetId": "nld_NLD_NER001",
      "locale": [
        "nl-NL"
      ],
      "country": "Netherlands",
      "languageGroup": "Dutch",
      "category": "Offensive NER",
      "volume": "4,997 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a99880b834e4fbc0a91ff19",
      "collection": "pronunciation-dictionaries",
      "title": "Indonesian (Indonesia) Offensive Wordlist",
      "slug": "ind-ind-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/ind-ind-ner001",
      "featured": false,
      "datasetId": "ind_IND_NER001",
      "locale": [
        "id-ID"
      ],
      "country": "Indonesia",
      "languageGroup": "Indonesian",
      "category": "Offensive NER",
      "volume": "3,179 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a99880a57206d63ef265868",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Gulf/Levantine) Offensive Wordlist",
      "slug": "arb-ner002",
      "url": "/data-catalog/pronunciation-dictionaries/arb-ner002",
      "featured": false,
      "datasetId": "ARB_NER002",
      "locale": [
        "ar-AE"
      ],
      "country": "United Arab Emirates",
      "languageGroup": "Arabic",
      "category": "Offensive NER",
      "volume": "5,138 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "List of offensive words labelled with Category, Slang/Standard rating, Offensiveness rating, Inflection, Spelling/Regional variant. ; Offensive categories include: Categories include: Blasphemy, Derogatory, Drugs, Extolling Alcohol Consumption, Gambling, People, Political, Religiously Extremist Nature, Sex, Sexual Impropriety, Undermining The State. ; Includes colloquial words used in Gulf and Levantine countries, and other Arabic-speaking countries.",
      "source": "Appen Global",
      "yearOfCollection": "2016"
    },
    {
      "id": "6a99880957206d63ef26583c",
      "collection": "pronunciation-dictionaries",
      "title": "Latin American Spanish Inverse text normalisation",
      "slug": "spa-itn001",
      "url": "/data-catalog/pronunciation-dictionaries/spa-itn001",
      "featured": false,
      "datasetId": "SPA_ITN001",
      "locale": [
        "es"
      ],
      "country": "N/A",
      "languageGroup": "Spanish",
      "category": "Inverse text normalisation",
      "volume": "3795 test cases",
      "unitType": "test cases",
      "dataFormat": "txt",
      "datasetDescription": "Inverse text normalisation input-output pairs, in 14 semiotic classes: cardinal, ordinal, decimal, fraction, measure, time, date, currency, letter, digit, electronic, address, postal codes, identifiers",
      "source": "Appen Global",
      "yearOfCollection": "2022"
    },
    {
      "id": "6a998808e924c86953f9716a",
      "collection": "pronunciation-dictionaries",
      "title": "Mandarin Chinese Inverse text normalisation",
      "slug": "cmn-itn001",
      "url": "/data-catalog/pronunciation-dictionaries/cmn-itn001",
      "featured": false,
      "datasetId": "CMN_ITN001",
      "locale": [
        "zh"
      ],
      "country": "N/A",
      "languageGroup": "Mandarin Chinese",
      "category": "Inverse text normalisation",
      "volume": "4230 test cases",
      "unitType": "test cases",
      "dataFormat": "txt",
      "datasetDescription": "Inverse text normalisation input-output pairs, in 14 semiotic classes: cardinal, ordinal, decimal, fraction, measure, time, date, currency, letter, digit, electronic, address, postal codes, identifiers",
      "source": "Appen Global",
      "yearOfCollection": "2022"
    },
    {
      "id": "6a99880738e229b39cdd479d",
      "collection": "pronunciation-dictionaries",
      "title": "Japanese Inverse text normalisation",
      "slug": "jpn-itn001",
      "url": "/data-catalog/pronunciation-dictionaries/jpn-itn001",
      "featured": false,
      "datasetId": "JPN_ITN001",
      "locale": [
        "ja"
      ],
      "country": "N/A",
      "languageGroup": "Japanese",
      "category": "Inverse text normalisation",
      "volume": "5363 test cases",
      "unitType": "test cases",
      "dataFormat": "txt",
      "datasetDescription": "Inverse text normalisation input-output pairs, in 14 semiotic classes: cardinal, ordinal, decimal, fraction, measure, time, date, currency, letter, digit, electronic, address, postal codes, identifiers",
      "source": "Appen Global",
      "yearOfCollection": "2022"
    },
    {
      "id": "6a99880617376764883dda02",
      "collection": "pronunciation-dictionaries",
      "title": "French Inverse text normalisation",
      "slug": "fra-itn001",
      "url": "/data-catalog/pronunciation-dictionaries/fra-itn001",
      "featured": false,
      "datasetId": "FRA_ITN001",
      "locale": [
        "fr"
      ],
      "country": "N/A",
      "languageGroup": "French",
      "category": "Inverse text normalisation",
      "volume": "3274 test cases",
      "unitType": "test cases",
      "dataFormat": "txt",
      "datasetDescription": "Inverse text normalisation input-output pairs, in 14 semiotic classes: cardinal, ordinal, decimal, fraction, measure, time, date, currency, letter, digit, electronic, address, postal codes, identifiers",
      "source": "Appen Global",
      "yearOfCollection": "2022"
    },
    {
      "id": "6a998806c8ebe72e2d9ed231",
      "collection": "pronunciation-dictionaries",
      "title": "English Inverse text normalisation",
      "slug": "eng-itn001",
      "url": "/data-catalog/pronunciation-dictionaries/eng-itn001",
      "featured": false,
      "datasetId": "ENG_ITN001",
      "locale": [
        "en"
      ],
      "country": "N/A",
      "languageGroup": "English",
      "category": "Inverse text normalisation",
      "volume": "4454 test cases",
      "unitType": "test cases",
      "dataFormat": "txt",
      "datasetDescription": "Inverse text normalisation input-output pairs, in 14 semiotic classes: cardinal, ordinal, decimal, fraction, measure, time, date, currency, letter, digit, electronic, address, postal codes, identifiers",
      "source": "Appen Global",
      "yearOfCollection": "2022"
    },
    {
      "id": "6a99880529d74d9309f39acc",
      "collection": "pronunciation-dictionaries",
      "title": "German Inverse text normalisation",
      "slug": "deu-itn001",
      "url": "/data-catalog/pronunciation-dictionaries/deu-itn001",
      "featured": false,
      "datasetId": "DEU_ITN001",
      "locale": [
        "de"
      ],
      "country": "N/A",
      "languageGroup": "German",
      "category": "Inverse text normalisation",
      "volume": "8001 test cases",
      "unitType": "test cases",
      "dataFormat": "txt",
      "datasetDescription": "Inverse text normalisation input-output pairs, in 14 semiotic classes: cardinal, ordinal, decimal, fraction, measure, time, date, currency, letter, digit, electronic, address, postal codes, identifiers",
      "source": "Appen Global",
      "yearOfCollection": "2022"
    },
    {
      "id": "6a998804040b2280149a12ba",
      "collection": "pronunciation-dictionaries",
      "title": "Hindi Inverse text normalisation",
      "slug": "hin-itn001",
      "url": "/data-catalog/pronunciation-dictionaries/hin-itn001",
      "featured": false,
      "datasetId": "HIN_ITN001",
      "locale": [
        "hi"
      ],
      "country": "N/A",
      "languageGroup": "Hindi",
      "category": "Inverse text normalisation",
      "volume": "6924 test cases",
      "unitType": "test cases",
      "dataFormat": "txt",
      "datasetDescription": "Inverse text normalisation input-output pairs, in 14 semiotic classes: cardinal, ordinal, decimal, fraction, measure, time, date, currency, letter, digit, electronic, address, postal codes, identifiers",
      "source": "Appen Global",
      "yearOfCollection": "2022"
    },
    {
      "id": "6a998803a24dcd7124d6f3f3",
      "collection": "pronunciation-dictionaries",
      "title": "Icelandic (Iceland) Pronunciation Dictionary",
      "slug": "isl-isl-phon",
      "url": "/data-catalog/pronunciation-dictionaries/isl-isl-phon",
      "featured": false,
      "datasetId": "isl_ISL_PHON",
      "locale": [
        "is-IS"
      ],
      "country": "Iceland",
      "languageGroup": "Icelandic",
      "category": "Pronunciation Dictionary",
      "volume": "3,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99880229d74d9309f39a6e",
      "collection": "pronunciation-dictionaries",
      "title": "Slovenian (Slovenian) Pronunciation Dictionary",
      "slug": "slv-svn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/slv-svn-phon",
      "featured": false,
      "datasetId": "slv_SVN_PHON",
      "locale": [
        "sl-SI"
      ],
      "country": "Slovenia",
      "languageGroup": "Slovenian",
      "category": "Pronunciation Dictionary",
      "volume": "28,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9988014005faf541bb68dd",
      "collection": "pronunciation-dictionaries",
      "title": "Georgian (Georgia) Pronunciation Dictionary",
      "slug": "kat-geo-phon",
      "url": "/data-catalog/pronunciation-dictionaries/kat-geo-phon",
      "featured": false,
      "datasetId": "kat_GEO_PHON",
      "locale": [
        "ka-GE"
      ],
      "country": "Georgia",
      "languageGroup": "Georgian",
      "category": "Pronunciation Dictionary",
      "volume": "67,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a998800f3c00f7b2dc2080f",
      "collection": "pronunciation-dictionaries",
      "title": "English (United States) Medical Terms Pronunciation Dictionary",
      "slug": "eng-usa-med-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-usa-med-phon",
      "featured": false,
      "datasetId": "eng_USA_Med_PHON",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "8,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "Pronunciation dictionary of medical terms with their associated transcriptions and domain tagging. ; Data is comprised of medical words extracted from PubMed abstracts, as well as pharmaceutical drug names collected by Appen through web-spidering. Pronunciations were processed by native speakers of US English and domain tagging done by a team of US English native speakers with medical transcription or other medical qualifications and experience. ; Domains include: Anatomy, Biochem/biological, Condition, General, Organisation, Person, Pharmaceutical, Procedure.",
      "source": "Appen Global",
      "yearOfCollection": "2021"
    },
    {
      "id": "6a9987ffe6ee6e81af9b5ecb",
      "collection": "pronunciation-dictionaries",
      "title": "Zulu (South Africa) Pronunciation Dictionary",
      "slug": "zul-zaf-phon",
      "url": "/data-catalog/pronunciation-dictionaries/zul-zaf-phon",
      "featured": false,
      "datasetId": "zul_ZAF_PHON",
      "locale": [
        "zu-ZA"
      ],
      "country": "South Africa",
      "languageGroup": "Zulu",
      "category": "Pronunciation Dictionary",
      "volume": "77,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987fe73f796e25926f649",
      "collection": "pronunciation-dictionaries",
      "title": "Xiang (China) Pronunciation Dictionary",
      "slug": "hsn-chn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/hsn-chn-phon",
      "featured": false,
      "datasetId": "hsn_CHN_PHON",
      "locale": [
        "hsn-CN"
      ],
      "country": "China",
      "languageGroup": "Xiang",
      "category": "Pronunciation Dictionary",
      "volume": "12,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987fd38e229b39cdd454a",
      "collection": "pronunciation-dictionaries",
      "title": "Wu (China) Pronunciation Dictionary",
      "slug": "wuu-chn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/wuu-chn-phon",
      "featured": false,
      "datasetId": "wuu_CHN_PHON",
      "locale": [
        "wuu-CN"
      ],
      "country": "China",
      "languageGroup": "Wu",
      "category": "Pronunciation Dictionary",
      "volume": "11,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987fc8dcd14d10a92ad7f",
      "collection": "pronunciation-dictionaries",
      "title": "Vietnamese (Vietnam) Pronunciation Dictionary",
      "slug": "vie-vnm-phon",
      "url": "/data-catalog/pronunciation-dictionaries/vie-vnm-phon",
      "featured": false,
      "datasetId": "vie_VNM_PHON",
      "locale": [
        "vi-VN"
      ],
      "country": "Vietnam",
      "languageGroup": "Vietnamese",
      "category": "Pronunciation Dictionary",
      "volume": "8,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987fb8afbba395745441d",
      "collection": "pronunciation-dictionaries",
      "title": "Urdu (Pakistan) Part of Speech Dictionary",
      "slug": "urd-pak-pos",
      "url": "/data-catalog/pronunciation-dictionaries/urd-pak-pos",
      "featured": false,
      "datasetId": "urd_PAK_POS",
      "locale": [
        "ur-PK"
      ],
      "country": "Pakistan",
      "languageGroup": "Urdu",
      "category": "Part of Speech Dictionary",
      "volume": "12,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987fae0fff96563b45555",
      "collection": "pronunciation-dictionaries",
      "title": "Urdu (Pakistan) Pronunciation Dictionary",
      "slug": "urd-pak-phon",
      "url": "/data-catalog/pronunciation-dictionaries/urd-pak-phon",
      "featured": false,
      "datasetId": "urd_PAK_PHON",
      "locale": [
        "ur-PK"
      ],
      "country": "Pakistan",
      "languageGroup": "Urdu",
      "category": "Pronunciation Dictionary",
      "volume": "21,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f9991d16e5e66e52db",
      "collection": "pronunciation-dictionaries",
      "title": "Ukrainian (Ukraine) Pronunciation Dictionary",
      "slug": "ukr-ukr-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ukr-ukr-phon",
      "featured": false,
      "datasetId": "ukr_UKR_PHON",
      "locale": [
        "uk-UA"
      ],
      "country": "Ukraine",
      "languageGroup": "Ukrainian",
      "category": "Pronunciation Dictionary",
      "volume": "6,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f96d858e464b667080",
      "collection": "pronunciation-dictionaries",
      "title": "Turkish (Turkey) Part of Speech Dictionary",
      "slug": "tur-tur-pos",
      "url": "/data-catalog/pronunciation-dictionaries/tur-tur-pos",
      "featured": false,
      "datasetId": "tur_TUR_POS",
      "locale": [
        "tr-TR"
      ],
      "country": "Turkey",
      "languageGroup": "Turkish",
      "category": "Part of Speech Dictionary",
      "volume": "257,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f857206d63ef26505d",
      "collection": "pronunciation-dictionaries",
      "title": "Turkish (Turkey) Pronunciation Dictionary",
      "slug": "tur-tur-phon",
      "url": "/data-catalog/pronunciation-dictionaries/tur-tur-phon",
      "featured": false,
      "datasetId": "tur_TUR_PHON",
      "locale": [
        "tr-TR"
      ],
      "country": "Turkey",
      "languageGroup": "Turkish",
      "category": "Pronunciation Dictionary",
      "volume": "255,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f7b779334273e937f8",
      "collection": "pronunciation-dictionaries",
      "title": "Tok Pisin (Papua New Guinea) Pronunciation Dictionary",
      "slug": "tpi-png-phon",
      "url": "/data-catalog/pronunciation-dictionaries/tpi-png-phon",
      "featured": false,
      "datasetId": "tpi_PNG_PHON",
      "locale": [
        "tpi-PG"
      ],
      "country": "Papua New Guinea",
      "languageGroup": "Tok Pisin",
      "category": "Pronunciation Dictionary",
      "volume": "8,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f638e229b39cdd4013",
      "collection": "pronunciation-dictionaries",
      "title": "Thai (Thailand) Pronunciation Dictionary",
      "slug": "tha-tha-phon",
      "url": "/data-catalog/pronunciation-dictionaries/tha-tha-phon",
      "featured": false,
      "datasetId": "tha_THA_PHON",
      "locale": [
        "th-TH"
      ],
      "country": "Thailand",
      "languageGroup": "Thai",
      "category": "Pronunciation Dictionary",
      "volume": "30,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f5fa9df117f3590c86",
      "collection": "pronunciation-dictionaries",
      "title": "Tamil (India) Pronunciation Dictionary",
      "slug": "tam-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/tam-ind-phon",
      "featured": false,
      "datasetId": "tam_IND_PHON",
      "locale": [
        "ta-IN"
      ],
      "country": "India",
      "languageGroup": "Tamil",
      "category": "Pronunciation Dictionary",
      "volume": "106,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f438e229b39cdd3e9f",
      "collection": "pronunciation-dictionaries",
      "title": "Telugu (India) Pronunciation Dictionary",
      "slug": "tel-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/tel-ind-phon",
      "featured": false,
      "datasetId": "tel_IND_PHON",
      "locale": [
        "te-IN"
      ],
      "country": "India",
      "languageGroup": "Telugu",
      "category": "Pronunciation Dictionary",
      "volume": "51,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f3834e4fbc0a91f4fd",
      "collection": "pronunciation-dictionaries",
      "title": "Tagalog (Philippines) Pronunciation Dictionary",
      "slug": "tgl-phl-phon",
      "url": "/data-catalog/pronunciation-dictionaries/tgl-phl-phon",
      "featured": false,
      "datasetId": "tgl_PHL_PHON",
      "locale": [
        "tl-PH"
      ],
      "country": "Philippines",
      "languageGroup": "Tagalog",
      "category": "Pronunciation Dictionary",
      "volume": "34,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f213e9a932dc473819",
      "collection": "pronunciation-dictionaries",
      "title": "Sylheti (Bangladesh - India) Pronunciation Dictionary",
      "slug": "syl-bgd-phon",
      "url": "/data-catalog/pronunciation-dictionaries/syl-bgd-phon",
      "featured": false,
      "datasetId": "syl_BGD_PHON",
      "locale": [
        "syl-BD",
        "syl-IN"
      ],
      "country": "Bangladesh - India",
      "languageGroup": "Sylheti",
      "category": "Pronunciation Dictionary",
      "volume": "22,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f173f796e25926ed88",
      "collection": "pronunciation-dictionaries",
      "title": "Swedish (Sweden) Part of Speech Dictionary",
      "slug": "swe-swe-pos",
      "url": "/data-catalog/pronunciation-dictionaries/swe-swe-pos",
      "featured": false,
      "datasetId": "swe_SWE_POS",
      "locale": [
        "sv-SE"
      ],
      "country": "Sweden",
      "languageGroup": "Swedish",
      "category": "Part of Speech Dictionary",
      "volume": "105,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987f0040b2280149a016e",
      "collection": "pronunciation-dictionaries",
      "title": "Swedish (Sweden) Pronunciation Dictionary",
      "slug": "swe-swe-phon",
      "url": "/data-catalog/pronunciation-dictionaries/swe-swe-phon",
      "featured": false,
      "datasetId": "swe_SWE_PHON",
      "locale": [
        "sv-SE"
      ],
      "country": "Sweden",
      "languageGroup": "Swedish",
      "category": "Pronunciation Dictionary",
      "volume": "105,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987efd3a0ae3d29794453",
      "collection": "pronunciation-dictionaries",
      "title": "Swahili (Kenya) Pronunciation Dictionary",
      "slug": "swa-ken-phon",
      "url": "/data-catalog/pronunciation-dictionaries/swa-ken-phon",
      "featured": false,
      "datasetId": "swa_KEN_PHON",
      "locale": [
        "sw-KE"
      ],
      "country": "Kenya",
      "languageGroup": "Swahili",
      "category": "Pronunciation Dictionary",
      "volume": "66,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987ee17376764883dcf56",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Venezuela) Pronunciation Dictionary",
      "slug": "spa-ven-phon",
      "url": "/data-catalog/pronunciation-dictionaries/spa-ven-phon",
      "featured": false,
      "datasetId": "spa_VEN_PHON",
      "locale": [
        "es-VE"
      ],
      "country": "Venezuela",
      "languageGroup": "Spanish",
      "category": "Pronunciation Dictionary",
      "volume": "15,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987edf4c0365c95aea1e5",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (United States) Pronunciation Dictionary",
      "slug": "spa-usa-phon",
      "url": "/data-catalog/pronunciation-dictionaries/spa-usa-phon",
      "featured": false,
      "datasetId": "spa_USA_PHON",
      "locale": [
        "es-US"
      ],
      "country": "United States",
      "languageGroup": "Spanish",
      "category": "Pronunciation Dictionary",
      "volume": "90,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987ec73f796e25926e976",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Peru) Pronunciation Dictionary",
      "slug": "spa-per-phon",
      "url": "/data-catalog/pronunciation-dictionaries/spa-per-phon",
      "featured": false,
      "datasetId": "spa_PER_PHON",
      "locale": [
        "es-PE"
      ],
      "country": "Peru",
      "languageGroup": "Spanish",
      "category": "Pronunciation Dictionary",
      "volume": "15,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987ebe57f73b05ad27ef4",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Colombia) Pronunciation Dictionary",
      "slug": "spa-col-phon",
      "url": "/data-catalog/pronunciation-dictionaries/spa-col-phon",
      "featured": false,
      "datasetId": "spa_COL_PHON",
      "locale": [
        "es-CO"
      ],
      "country": "Colombia",
      "languageGroup": "Spanish",
      "category": "Pronunciation Dictionary",
      "volume": "15,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987ea84235eb50a0f373e",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Chile) Pronunciation Dictionary",
      "slug": "spa-chl-phon",
      "url": "/data-catalog/pronunciation-dictionaries/spa-chl-phon",
      "featured": false,
      "datasetId": "spa_CHL_PHON",
      "locale": [
        "es-CL"
      ],
      "country": "Chile",
      "languageGroup": "Spanish",
      "category": "Pronunciation Dictionary",
      "volume": "15,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e9aefba034e0250c73",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Spain) Pronunciation Dictionary",
      "slug": "spa-esp-phon",
      "url": "/data-catalog/pronunciation-dictionaries/spa-esp-phon",
      "featured": false,
      "datasetId": "spa_ESP_PHON",
      "locale": [
        "es-ES"
      ],
      "country": "Spain",
      "languageGroup": "Spanish",
      "category": "Pronunciation Dictionary",
      "volume": "100,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e873f796e25926e668",
      "collection": "pronunciation-dictionaries",
      "title": "Spanish (Argentina) Pronunciation Dictionary",
      "slug": "spa-arg-phon",
      "url": "/data-catalog/pronunciation-dictionaries/spa-arg-phon",
      "featured": false,
      "datasetId": "spa_ARG_PHON",
      "locale": [
        "es-AR"
      ],
      "country": "Argentina",
      "languageGroup": "Spanish",
      "category": "Pronunciation Dictionary",
      "volume": "15,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e710482f3af4007067",
      "collection": "pronunciation-dictionaries",
      "title": "Sorani (Iraq) Pronunciation Dictionary",
      "slug": "kur-irq-phon",
      "url": "/data-catalog/pronunciation-dictionaries/kur-irq-phon",
      "featured": false,
      "datasetId": "kur_IRQ_PHON",
      "locale": [
        "ku-IQ"
      ],
      "country": "Iraq",
      "languageGroup": "Sorani",
      "category": "Pronunciation Dictionary",
      "volume": "26,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e7f4c0365c95ae9efa",
      "collection": "pronunciation-dictionaries",
      "title": "Somali (Somalia) Pronunciation Dictionary",
      "slug": "som-som-phon",
      "url": "/data-catalog/pronunciation-dictionaries/som-som-phon",
      "featured": false,
      "datasetId": "som_SOM_PHON",
      "locale": [
        "so-SO"
      ],
      "country": "Somalia",
      "languageGroup": "Somali",
      "category": "Pronunciation Dictionary",
      "volume": "76,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e66ab94adf346ed75a",
      "collection": "pronunciation-dictionaries",
      "title": "Serbian (Serbia) Pronunciation Dictionary",
      "slug": "srp-srb-phon",
      "url": "/data-catalog/pronunciation-dictionaries/srp-srb-phon",
      "featured": false,
      "datasetId": "srp_SRB_PHON",
      "locale": [
        "sr-RS"
      ],
      "country": "Serbia",
      "languageGroup": "Serbian",
      "category": "Pronunciation Dictionary",
      "volume": "29,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e5eaf7c7f9ff51db2f",
      "collection": "pronunciation-dictionaries",
      "title": "Russian (Russia) Part of Speech Dictionary",
      "slug": "rus-rus-pos",
      "url": "/data-catalog/pronunciation-dictionaries/rus-rus-pos",
      "featured": false,
      "datasetId": "rus_RUS_POS",
      "locale": [
        "ru-RU"
      ],
      "country": "Russia",
      "languageGroup": "Russian",
      "category": "Part of Speech Dictionary",
      "volume": "100,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e46ab94adf346ed5b5",
      "collection": "pronunciation-dictionaries",
      "title": "Russian (Russia) Pronunciation Dictionary",
      "slug": "rus-rus-phon",
      "url": "/data-catalog/pronunciation-dictionaries/rus-rus-phon",
      "featured": false,
      "datasetId": "rus_RUS_PHON",
      "locale": [
        "ru-RU"
      ],
      "country": "Russia",
      "languageGroup": "Russian",
      "category": "Pronunciation Dictionary",
      "volume": "120,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e3eaf7c7f9ff51d8cf",
      "collection": "pronunciation-dictionaries",
      "title": "Romanian (Romania) Pronunciation Dictionary",
      "slug": "ron-rou-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ron-rou-phon",
      "featured": false,
      "datasetId": "ron_ROU_PHON",
      "locale": [
        "ro-RO"
      ],
      "country": "Romania",
      "languageGroup": "Romanian",
      "category": "Pronunciation Dictionary",
      "volume": "16,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e217854c543f93f0fc",
      "collection": "pronunciation-dictionaries",
      "title": "Portuguese (Portugal) Part of Speech Dictionary",
      "slug": "por-prt-pos",
      "url": "/data-catalog/pronunciation-dictionaries/por-prt-pos",
      "featured": false,
      "datasetId": "por_PRT_POS",
      "locale": [
        "pt-PT"
      ],
      "country": "Portugal",
      "languageGroup": "Portuguese",
      "category": "Part of Speech Dictionary",
      "volume": "60,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e157206d63ef2646d8",
      "collection": "pronunciation-dictionaries",
      "title": "Portuguese (Portugal) Pronunciation Dictionary",
      "slug": "por-prt-phon",
      "url": "/data-catalog/pronunciation-dictionaries/por-prt-phon",
      "featured": false,
      "datasetId": "por_PRT_PHON",
      "locale": [
        "pt-PT"
      ],
      "country": "Portugal",
      "languageGroup": "Portuguese",
      "category": "Pronunciation Dictionary",
      "volume": "112,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987e0bc894a1ebfd43ae3",
      "collection": "pronunciation-dictionaries",
      "title": "Portuguese (Brazil) Part of Speech Dictionary",
      "slug": "por-bra-pos",
      "url": "/data-catalog/pronunciation-dictionaries/por-bra-pos",
      "featured": false,
      "datasetId": "por_BRA_POS",
      "locale": [
        "pt-BR"
      ],
      "country": "Brazil",
      "languageGroup": "Portuguese",
      "category": "Part of Speech Dictionary",
      "volume": "98,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987df6d858e464b6664d3",
      "collection": "pronunciation-dictionaries",
      "title": "Portuguese (Brazil) Pronunciation Dictionary",
      "slug": "por-bra-phon",
      "url": "/data-catalog/pronunciation-dictionaries/por-bra-phon",
      "featured": false,
      "datasetId": "por_BRA_PHON",
      "locale": [
        "pt-BR"
      ],
      "country": "Brazil",
      "languageGroup": "Portuguese",
      "category": "Pronunciation Dictionary",
      "volume": "102,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987defa9df117f358fed9",
      "collection": "pronunciation-dictionaries",
      "title": "Polish (Poland) Part of Speech Dictionary",
      "slug": "pol-pol-pos",
      "url": "/data-catalog/pronunciation-dictionaries/pol-pol-pos",
      "featured": false,
      "datasetId": "pol_POL_POS",
      "locale": [
        "pl-PL"
      ],
      "country": "Poland",
      "languageGroup": "Polish",
      "category": "Part of Speech Dictionary",
      "volume": "4,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987de9ec510f7c328f897",
      "collection": "pronunciation-dictionaries",
      "title": "Polish (Poland) Pronunciation Dictionary",
      "slug": "pol-pol-phon",
      "url": "/data-catalog/pronunciation-dictionaries/pol-pol-phon",
      "featured": false,
      "datasetId": "pol_POL_PHON",
      "locale": [
        "pl-PL"
      ],
      "country": "Poland",
      "languageGroup": "Polish",
      "category": "Pronunciation Dictionary",
      "volume": "42,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987dd84235eb50a0f2b9e",
      "collection": "pronunciation-dictionaries",
      "title": "Pashto (Afghanistan) Pronunciation Dictionary",
      "slug": "pus-afg-phon",
      "url": "/data-catalog/pronunciation-dictionaries/pus-afg-phon",
      "featured": false,
      "datasetId": "pus_AFG_PHON",
      "locale": [
        "ps-AF"
      ],
      "country": "Afghanistan",
      "languageGroup": "Pashto",
      "category": "Pronunciation Dictionary",
      "volume": "64,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987dceaf7c7f9ff51d3ba",
      "collection": "pronunciation-dictionaries",
      "title": "Oriya (India) Pronunciation Dictionary",
      "slug": "ori-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ori-ind-phon",
      "featured": false,
      "datasetId": "ori_IND_PHON",
      "locale": [
        "or-IN"
      ],
      "country": "India",
      "languageGroup": "Oriya",
      "category": "Pronunciation Dictionary",
      "volume": "19,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987db811b8e5d7361d54a",
      "collection": "pronunciation-dictionaries",
      "title": "Norwegian (Norway) Part of Speech Dictionary",
      "slug": "nor-nor-pos",
      "url": "/data-catalog/pronunciation-dictionaries/nor-nor-pos",
      "featured": false,
      "datasetId": "nor_NOR_POS",
      "locale": [
        "nb-NO"
      ],
      "country": "Norway",
      "languageGroup": "Norwegian",
      "category": "Part of Speech Dictionary",
      "volume": "3,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987dae57f73b05ad27961",
      "collection": "pronunciation-dictionaries",
      "title": "Norwegian (Norway) Pronunciation Dictionary",
      "slug": "nor-nor-phon",
      "url": "/data-catalog/pronunciation-dictionaries/nor-nor-phon",
      "featured": false,
      "datasetId": "nor_NOR_PHON",
      "locale": [
        "nb-NO"
      ],
      "country": "Norway",
      "languageGroup": "Norwegian",
      "category": "Pronunciation Dictionary",
      "volume": "117,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d917854c543f93edb8",
      "collection": "pronunciation-dictionaries",
      "title": "Mongolian (Mongolia) Pronunciation Dictionary",
      "slug": "mon-mng-phon",
      "url": "/data-catalog/pronunciation-dictionaries/mon-mng-phon",
      "featured": false,
      "datasetId": "mon_MNG_PHON",
      "locale": [
        "mn-MN"
      ],
      "country": "Mongolia",
      "languageGroup": "Mongolian",
      "category": "Pronunciation Dictionary",
      "volume": "32,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d817854c543f93ed4f",
      "collection": "pronunciation-dictionaries",
      "title": "Marathi (India) Pronunciation Dictionary",
      "slug": "mar-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/mar-ind-phon",
      "featured": false,
      "datasetId": "mar_IND_PHON",
      "locale": [
        "mr-IN"
      ],
      "country": "India",
      "languageGroup": "Marathi",
      "category": "Pronunciation Dictionary",
      "volume": "30,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d8991d16e5e66e47fd",
      "collection": "pronunciation-dictionaries",
      "title": "Mandarin (Traditional) (Taiwan) Pronunciation Dictionary",
      "slug": "zho-twn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/zho-twn-phon",
      "featured": false,
      "datasetId": "zho_TWN_PHON",
      "locale": [
        "zh-TW"
      ],
      "country": "Taiwan",
      "languageGroup": "Mandarin (Traditional)",
      "category": "Pronunciation Dictionary",
      "volume": "50,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d7991d16e5e66e47ca",
      "collection": "pronunciation-dictionaries",
      "title": "Mandarin (Simplified) (China) Pronunciation Dictionary",
      "slug": "zho-chn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/zho-chn-phon",
      "featured": false,
      "datasetId": "zho_CHN_PHON",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Mandarin (Simplified)",
      "category": "Pronunciation Dictionary",
      "volume": "35,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d617956efcbddcca79",
      "collection": "pronunciation-dictionaries",
      "title": "Malaysian (Malaysia) Pronunciation Dictionary",
      "slug": "msa-mys-phon",
      "url": "/data-catalog/pronunciation-dictionaries/msa-mys-phon",
      "featured": false,
      "datasetId": "msa_MYS_PHON",
      "locale": [
        "ms-MY"
      ],
      "country": "Malaysia",
      "languageGroup": "Malaysian",
      "category": "Pronunciation Dictionary",
      "volume": "26,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d584235eb50a0f2573",
      "collection": "pronunciation-dictionaries",
      "title": "Malayalam (India) Pronunciation Dictionary",
      "slug": "mal-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/mal-ind-phon",
      "featured": false,
      "datasetId": "mal_IND_PHON",
      "locale": [
        "ml-IN"
      ],
      "country": "India",
      "languageGroup": "Malayalam",
      "category": "Pronunciation Dictionary",
      "volume": "19,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d49ec510f7c328f242",
      "collection": "pronunciation-dictionaries",
      "title": "Lithuanian (Lithuania) Pronunciation Dictionary",
      "slug": "lit-ltu-phon",
      "url": "/data-catalog/pronunciation-dictionaries/lit-ltu-phon",
      "featured": false,
      "datasetId": "lit_LTU_PHON",
      "locale": [
        "lt-LT"
      ],
      "country": "Lithuania",
      "languageGroup": "Lithuanian",
      "category": "Pronunciation Dictionary",
      "volume": "71,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d3c8ebe72e2d9ebd97",
      "collection": "pronunciation-dictionaries",
      "title": "Lao (Laos) Pronunciation Dictionary",
      "slug": "lao-lao-phon",
      "url": "/data-catalog/pronunciation-dictionaries/lao-lao-phon",
      "featured": false,
      "datasetId": "lao_LAO_PHON",
      "locale": [
        "lo-LA"
      ],
      "country": "Laos",
      "languageGroup": "Lao",
      "category": "Pronunciation Dictionary",
      "volume": "9,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d2991d16e5e66e469c",
      "collection": "pronunciation-dictionaries",
      "title": "Kurmanji (Turkey) Pronunciation Dictionary",
      "slug": "kur-tur-phon",
      "url": "/data-catalog/pronunciation-dictionaries/kur-tur-phon",
      "featured": false,
      "datasetId": "kur_TUR_PHON",
      "locale": [
        "ku-TR"
      ],
      "country": "Turkey",
      "languageGroup": "Kurmanji",
      "category": "Pronunciation Dictionary",
      "volume": "60,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d284235eb50a0f2201",
      "collection": "pronunciation-dictionaries",
      "title": "Korean (South Korea) Part of Speech Dictionary",
      "slug": "kor-kor-pos",
      "url": "/data-catalog/pronunciation-dictionaries/kor-kor-pos",
      "featured": false,
      "datasetId": "kor_KOR_POS",
      "locale": [
        "ko-KR"
      ],
      "country": "South Korea",
      "languageGroup": "Korean",
      "category": "Part of Speech Dictionary",
      "volume": "100,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987d084235eb50a0f214c",
      "collection": "pronunciation-dictionaries",
      "title": "Korean (South Korea) Pronunciation Dictionary",
      "slug": "kor-kor-phon",
      "url": "/data-catalog/pronunciation-dictionaries/kor-kor-phon",
      "featured": false,
      "datasetId": "kor_KOR_PHON",
      "locale": [
        "ko-KR"
      ],
      "country": "South Korea",
      "languageGroup": "Korean",
      "category": "Pronunciation Dictionary",
      "volume": "105,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987cf13e9a932dc472acd",
      "collection": "pronunciation-dictionaries",
      "title": "Kazakh (Kazakhstan) Pronunciation Dictionary",
      "slug": "kaz-kaz-phon",
      "url": "/data-catalog/pronunciation-dictionaries/kaz-kaz-phon",
      "featured": false,
      "datasetId": "kaz_KAZ_PHON",
      "locale": [
        "kk-KZ"
      ],
      "country": "Kazakhstan",
      "languageGroup": "Kazakh",
      "category": "Pronunciation Dictionary",
      "volume": "31,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987ce31b4728186af2bc1",
      "collection": "pronunciation-dictionaries",
      "title": "Kannada (India) Pronunciation Dictionary",
      "slug": "kan-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/kan-ind-phon",
      "featured": false,
      "datasetId": "kan_IND_PHON",
      "locale": [
        "kn-IN"
      ],
      "country": "India",
      "languageGroup": "Kannada",
      "category": "Pronunciation Dictionary",
      "volume": "49,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987cd17956efcbddcc7eb",
      "collection": "pronunciation-dictionaries",
      "title": "Javanese (Indonesia) Pronunciation Dictionary",
      "slug": "jav-idn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/jav-idn-phon",
      "featured": false,
      "datasetId": "jav_IDN_PHON",
      "locale": [
        "jv-ID"
      ],
      "country": "Indonesia",
      "languageGroup": "Javanese",
      "category": "Pronunciation Dictionary",
      "volume": "22,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987ccbc894a1ebfd43357",
      "collection": "pronunciation-dictionaries",
      "title": "Japanese (Japan) Part of Speech Dictionary",
      "slug": "jpn-jpn-pos",
      "url": "/data-catalog/pronunciation-dictionaries/jpn-jpn-pos",
      "featured": false,
      "datasetId": "jpn_JPN_POS",
      "locale": [
        "ja-JP"
      ],
      "country": "Japan",
      "languageGroup": "Japanese",
      "category": "Part of Speech Dictionary",
      "volume": "269,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987cbd3a0ae3d29793a7b",
      "collection": "pronunciation-dictionaries",
      "title": "Japanese (Japan) Pronunciation Dictionary",
      "slug": "jpn-jpn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/jpn-jpn-phon",
      "featured": false,
      "datasetId": "jpn_JPN_PHON",
      "locale": [
        "ja-JP"
      ],
      "country": "Japan",
      "languageGroup": "Japanese",
      "category": "Pronunciation Dictionary",
      "volume": "262,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987cac8ebe72e2d9eb6da",
      "collection": "pronunciation-dictionaries",
      "title": "Italian (Italy) Part of Speech Dictionary",
      "slug": "ita-ita-pos",
      "url": "/data-catalog/pronunciation-dictionaries/ita-ita-pos",
      "featured": false,
      "datasetId": "ita_ITA_POS",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "category": "Part of Speech Dictionary",
      "volume": "171,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c929d74d9309f389b0",
      "collection": "pronunciation-dictionaries",
      "title": "Italian (Italy) Pronunciation Dictionary",
      "slug": "ita-ita-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ita-ita-phon",
      "featured": false,
      "datasetId": "ita_ITA_PHON",
      "locale": [
        "it-IT"
      ],
      "country": "Italy",
      "languageGroup": "Italian",
      "category": "Pronunciation Dictionary",
      "volume": "197,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c96d858e464b665ea3",
      "collection": "pronunciation-dictionaries",
      "title": "Igbo (Nigeria) Pronunciation Dictionary",
      "slug": "ibo-nga-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ibo-nga-phon",
      "featured": false,
      "datasetId": "ibo_NGA_PHON",
      "locale": [
        "ig-NG"
      ],
      "country": "Nigeria",
      "languageGroup": "Igbo",
      "category": "Pronunciation Dictionary",
      "volume": "32,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c8991d16e5e66e43c9",
      "collection": "pronunciation-dictionaries",
      "title": "Hungarian (Hungary) Pronunciation Dictionary",
      "slug": "hun-hun-phon",
      "url": "/data-catalog/pronunciation-dictionaries/hun-hun-phon",
      "featured": false,
      "datasetId": "hun_HUN_PHON",
      "locale": [
        "hu-HU"
      ],
      "country": "Hungary",
      "languageGroup": "Hungarian",
      "category": "Pronunciation Dictionary",
      "volume": "500 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c7eaf7c7f9ff51c9f3",
      "collection": "pronunciation-dictionaries",
      "title": "Hindi (India) Pronunciation Dictionary",
      "slug": "hin-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/hin-ind-phon",
      "featured": false,
      "datasetId": "hin_IND_PHON",
      "locale": [
        "hi-IN"
      ],
      "country": "India",
      "languageGroup": "Hindi",
      "category": "Pronunciation Dictionary",
      "volume": "35,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c68dcd14d10a92a2a8",
      "collection": "pronunciation-dictionaries",
      "title": "Hebrew (Israel) Pronunciation Dictionary",
      "slug": "heb-isr-phon",
      "url": "/data-catalog/pronunciation-dictionaries/heb-isr-phon",
      "featured": false,
      "datasetId": "heb_ISR_PHON",
      "locale": [
        "he-IL"
      ],
      "country": "Israel",
      "languageGroup": "Hebrew",
      "category": "Pronunciation Dictionary",
      "volume": "31,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c5d3a0ae3d297937d0",
      "collection": "pronunciation-dictionaries",
      "title": "Hausa (Nigeria) Pronunciation Dictionary",
      "slug": "hau-nga-phon",
      "url": "/data-catalog/pronunciation-dictionaries/hau-nga-phon",
      "featured": false,
      "datasetId": "hau_NGA_PHON",
      "locale": [
        "ha-NG"
      ],
      "country": "Nigeria",
      "languageGroup": "Hausa",
      "category": "Pronunciation Dictionary",
      "volume": "11,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c4fa9df117f358f9a0",
      "collection": "pronunciation-dictionaries",
      "title": "Haitian Creole (Haiti) Pronunciation Dictionary",
      "slug": "hat-hti-phon",
      "url": "/data-catalog/pronunciation-dictionaries/hat-hti-phon",
      "featured": false,
      "datasetId": "hat_HTI_PHON",
      "locale": [
        "ht-HT"
      ],
      "country": "Haiti",
      "languageGroup": "Haitian Creole",
      "category": "Pronunciation Dictionary",
      "volume": "18,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c3991d16e5e66e41e0",
      "collection": "pronunciation-dictionaries",
      "title": "Guarani (Paraguay) Pronunciation Dictionary",
      "slug": "grn-pry-phon",
      "url": "/data-catalog/pronunciation-dictionaries/grn-pry-phon",
      "featured": false,
      "datasetId": "grn_PRY_PHON",
      "locale": [
        "gn-PY"
      ],
      "country": "Paraguay",
      "languageGroup": "Guarani",
      "category": "Pronunciation Dictionary",
      "volume": "36,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c26ab94adf346eca64",
      "collection": "pronunciation-dictionaries",
      "title": "Greek (Greece) Pronunciation Dictionary",
      "slug": "ell-grc-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ell-grc-phon",
      "featured": false,
      "datasetId": "ell_GRC_PHON",
      "locale": [
        "el-GR"
      ],
      "country": "Greece",
      "languageGroup": "Greek",
      "category": "Pronunciation Dictionary",
      "volume": "5,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c131b4728186af28ba",
      "collection": "pronunciation-dictionaries",
      "title": "German (Switzerland) Pronunciation Dictionary",
      "slug": "deu-che-phon",
      "url": "/data-catalog/pronunciation-dictionaries/deu-che-phon",
      "featured": false,
      "datasetId": "deu_CHE_PHON",
      "locale": [
        "de-CH"
      ],
      "country": "Switzerland",
      "languageGroup": "German",
      "category": "Pronunciation Dictionary",
      "volume": "27,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987c0d3a0ae3d297934f1",
      "collection": "pronunciation-dictionaries",
      "title": "German (Germany) Pronunciation Dictionary",
      "slug": "deu-deu-phon",
      "url": "/data-catalog/pronunciation-dictionaries/deu-deu-phon",
      "featured": false,
      "datasetId": "deu_DEU_PHON",
      "locale": [
        "de-DE"
      ],
      "country": "Germany",
      "languageGroup": "German",
      "category": "Pronunciation Dictionary",
      "volume": "146,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987bfbc894a1ebfd42d7a",
      "collection": "pronunciation-dictionaries",
      "title": "French (France) Part of Speech Dictionary",
      "slug": "fra-fra-pos",
      "url": "/data-catalog/pronunciation-dictionaries/fra-fra-pos",
      "featured": false,
      "datasetId": "fra_FRA_POS",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "category": "Part of Speech Dictionary",
      "volume": "95,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987bf17376764883db4a4",
      "collection": "pronunciation-dictionaries",
      "title": "French (France) Pronunciation Dictionary",
      "slug": "fra-fra-phon",
      "url": "/data-catalog/pronunciation-dictionaries/fra-fra-phon",
      "featured": false,
      "datasetId": "fra_FRA_PHON",
      "locale": [
        "fr-FR"
      ],
      "country": "France",
      "languageGroup": "French",
      "category": "Pronunciation Dictionary",
      "volume": "112,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987beaa89b6c9886e13f1",
      "collection": "pronunciation-dictionaries",
      "title": "French (Canada) Pronunciation Dictionary",
      "slug": "fra-can-phon",
      "url": "/data-catalog/pronunciation-dictionaries/fra-can-phon",
      "featured": false,
      "datasetId": "fra_CAN_PHON",
      "locale": [
        "fr-CA"
      ],
      "country": "Canada",
      "languageGroup": "French",
      "category": "Pronunciation Dictionary",
      "volume": "67,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987bdaa89b6c9886e1376",
      "collection": "pronunciation-dictionaries",
      "title": "Finnish (Finland) Part of Speech Dictionary",
      "slug": "fin-fin-pos",
      "url": "/data-catalog/pronunciation-dictionaries/fin-fin-pos",
      "featured": false,
      "datasetId": "fin_FIN_POS",
      "locale": [
        "fi-FI"
      ],
      "country": "Finland",
      "languageGroup": "Finnish",
      "category": "Part of Speech Dictionary",
      "volume": "10,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987bceaf7c7f9ff51c3c5",
      "collection": "pronunciation-dictionaries",
      "title": "Finnish (Finland) Pronunciation Dictionary",
      "slug": "fin-fin-phon",
      "url": "/data-catalog/pronunciation-dictionaries/fin-fin-phon",
      "featured": false,
      "datasetId": "fin_FIN_PHON",
      "locale": [
        "fi-FI"
      ],
      "country": "Finland",
      "languageGroup": "Finnish",
      "category": "Pronunciation Dictionary",
      "volume": "86,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987bb991d16e5e66e3fcd",
      "collection": "pronunciation-dictionaries",
      "title": "Iranian Persian (Iran) Part of Speech Dictionary",
      "slug": "pes-irn-pos",
      "url": "/data-catalog/pronunciation-dictionaries/pes-irn-pos",
      "featured": false,
      "datasetId": "pes_IRN_POS",
      "locale": [
        "fa-IR"
      ],
      "country": "Iran",
      "languageGroup": "Iranian Persian",
      "category": "Part of Speech Dictionary",
      "volume": "1,400,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987baeaf7c7f9ff51c2a5",
      "collection": "pronunciation-dictionaries",
      "title": "Iranian Persian (Iran) Pronunciation Dictionary",
      "slug": "pes-irn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/pes-irn-phon",
      "featured": false,
      "datasetId": "pes_IRN_PHON",
      "locale": [
        "fa-IR"
      ],
      "country": "Iran",
      "languageGroup": "Iranian Persian",
      "category": "Pronunciation Dictionary",
      "volume": "85,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b9811b8e5d7361cb4e",
      "collection": "pronunciation-dictionaries",
      "title": "English (United States) Part of Speech Dictionary",
      "slug": "eng-usa-pos",
      "url": "/data-catalog/pronunciation-dictionaries/eng-usa-pos",
      "featured": false,
      "datasetId": "eng_USA_POS",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "category": "Part of Speech Dictionary",
      "volume": "263,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b8e6ee6e81af9b4341",
      "collection": "pronunciation-dictionaries",
      "title": "English (United States) Pronunciation Dictionary",
      "slug": "eng-usa-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-usa-phon",
      "featured": false,
      "datasetId": "eng_USA_PHON",
      "locale": [
        "en-US"
      ],
      "country": "United States",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "358,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b717854c543f93de29",
      "collection": "pronunciation-dictionaries",
      "title": "English (United Kingdom) Part of Speech Dictionary",
      "slug": "eng-gbr-pos",
      "url": "/data-catalog/pronunciation-dictionaries/eng-gbr-pos",
      "featured": false,
      "datasetId": "eng_GBR_POS",
      "locale": [
        "en-GB"
      ],
      "country": "United Kingdom",
      "languageGroup": "English",
      "category": "Part of Speech Dictionary",
      "volume": "155,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b6eaf7c7f9ff51c04e",
      "collection": "pronunciation-dictionaries",
      "title": "English (United Kingdom) Pronunciation Dictionary",
      "slug": "eng-gbr-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-gbr-phon",
      "featured": false,
      "datasetId": "eng_GBR_PHON",
      "locale": [
        "en-GB"
      ],
      "country": "United Kingdom",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "195,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b5f41547c318e68923",
      "collection": "pronunciation-dictionaries",
      "title": "English (NZ) Pronunciation Dictionary",
      "slug": "eng-nzl-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-nzl-phon",
      "featured": false,
      "datasetId": "eng_NZL_PHON",
      "locale": [
        "en-NZ"
      ],
      "country": "NZ",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "28,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b4f4ac0d8edcf3e6bb",
      "collection": "pronunciation-dictionaries",
      "title": "English (Ireland) Pronunciation Dictionary",
      "slug": "eng-irl-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-irl-phon",
      "featured": false,
      "datasetId": "eng_IRL_PHON",
      "locale": [
        "en-IE"
      ],
      "country": "Ireland",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "12,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b3eaf7c7f9ff51bd99",
      "collection": "pronunciation-dictionaries",
      "title": "English (India) Part of Speech Dictionary",
      "slug": "eng-ind-pos",
      "url": "/data-catalog/pronunciation-dictionaries/eng-ind-pos",
      "featured": false,
      "datasetId": "eng_IND_POS",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "category": "Part of Speech Dictionary",
      "volume": "13,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b2834e4fbc0a91e2ba",
      "collection": "pronunciation-dictionaries",
      "title": "English (India) Pronunciation Dictionary",
      "slug": "eng-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-ind-phon",
      "featured": false,
      "datasetId": "eng_IND_PHON",
      "locale": [
        "en-IN"
      ],
      "country": "India",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "60,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b217956efcbddcc2c0",
      "collection": "pronunciation-dictionaries",
      "title": "English (Hong Kong) Pronunciation Dictionary",
      "slug": "eng-hkg-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-hkg-phon",
      "featured": false,
      "datasetId": "eng_HKG_PHON",
      "locale": [
        "en-HK"
      ],
      "country": "Hong Kong",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "18,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b16ab94adf346ec467",
      "collection": "pronunciation-dictionaries",
      "title": "English (Philippines) Pronunciation Dictionary",
      "slug": "eng-phl-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-phl-phon",
      "featured": false,
      "datasetId": "eng_PHL_PHON",
      "locale": [
        "en-PH"
      ],
      "country": "Philippines",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "7,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987b073f796e25926ccb5",
      "collection": "pronunciation-dictionaries",
      "title": "English (Canada) Part of Speech Dictionary",
      "slug": "eng-can-pos",
      "url": "/data-catalog/pronunciation-dictionaries/eng-can-pos",
      "featured": false,
      "datasetId": "eng_CAN_POS",
      "locale": [
        "en-CA"
      ],
      "country": "Canada",
      "languageGroup": "English",
      "category": "Part of Speech Dictionary",
      "volume": "3,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987af946e817c7d639ebe",
      "collection": "pronunciation-dictionaries",
      "title": "English (Canada) Pronunciation Dictionary",
      "slug": "eng-can-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-can-phon",
      "featured": false,
      "datasetId": "eng_CAN_PHON",
      "locale": [
        "en-CA"
      ],
      "country": "Canada",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "50,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987adeaf7c7f9ff51baff",
      "collection": "pronunciation-dictionaries",
      "title": "English (Australia) Pronunciation Dictionary",
      "slug": "eng-aus-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-aus-phon",
      "featured": false,
      "datasetId": "eng_AUS_PHON",
      "locale": [
        "en-AU"
      ],
      "country": "Australia",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "157,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987acf4ac0d8edcf3ddd1",
      "collection": "pronunciation-dictionaries",
      "title": "English (United Arab Emirates (UAE)) Pronunciation Dictionary",
      "slug": "eng-are-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eng-are-phon",
      "featured": false,
      "datasetId": "eng_ARE_PHON",
      "locale": [
        "en-AE"
      ],
      "country": "United Arab Emirates (UAE)",
      "languageGroup": "English",
      "category": "Pronunciation Dictionary",
      "volume": "5,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987ab10482f3af4005d65",
      "collection": "pronunciation-dictionaries",
      "title": "Dutch (Netherlands) Pronunciation Dictionary",
      "slug": "nld-nld-phon",
      "url": "/data-catalog/pronunciation-dictionaries/nld-nld-phon",
      "featured": false,
      "datasetId": "nld_NLD_PHON",
      "locale": [
        "nl-NL"
      ],
      "country": "Netherlands",
      "languageGroup": "Dutch",
      "category": "Pronunciation Dictionary",
      "volume": "45,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987aa84235eb50a0f09c7",
      "collection": "pronunciation-dictionaries",
      "title": "Dholuo (Kenya) Pronunciation Dictionary",
      "slug": "luo-ken-phon",
      "url": "/data-catalog/pronunciation-dictionaries/luo-ken-phon",
      "featured": false,
      "datasetId": "luo_KEN_PHON",
      "locale": [
        "luo-KE"
      ],
      "country": "Kenya",
      "languageGroup": "Dholuo",
      "category": "Pronunciation Dictionary",
      "volume": "23,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a94005faf541bb525a",
      "collection": "pronunciation-dictionaries",
      "title": "Dari (Afghanistan) Pronunciation Dictionary",
      "slug": "prs-afg-phon",
      "url": "/data-catalog/pronunciation-dictionaries/prs-afg-phon",
      "featured": false,
      "datasetId": "prs_AFG_PHON",
      "locale": [
        "fa-AF"
      ],
      "country": "Afghanistan",
      "languageGroup": "Dari",
      "category": "Pronunciation Dictionary",
      "volume": "31,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a8e6ee6e81af9b3c75",
      "collection": "pronunciation-dictionaries",
      "title": "Danish (Denmark) Part of Speech Dictionary",
      "slug": "dan-dnk-pos",
      "url": "/data-catalog/pronunciation-dictionaries/dan-dnk-pos",
      "featured": false,
      "datasetId": "dan_DNK_POS",
      "locale": [
        "da-DK"
      ],
      "country": "Denmark",
      "languageGroup": "Danish",
      "category": "Part of Speech Dictionary",
      "volume": "100,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a7aefba034e025012c",
      "collection": "pronunciation-dictionaries",
      "title": "Danish (Denmark) Pronunciation Dictionary",
      "slug": "dan-dnk-phon",
      "url": "/data-catalog/pronunciation-dictionaries/dan-dnk-phon",
      "featured": false,
      "datasetId": "dan_DNK_PHON",
      "locale": [
        "da-DK"
      ],
      "country": "Denmark",
      "languageGroup": "Danish",
      "category": "Pronunciation Dictionary",
      "volume": "107,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a610482f3af4005ad0",
      "collection": "pronunciation-dictionaries",
      "title": "Czech (Czech Republic) Pronunciation Dictionary",
      "slug": "ces-cze-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ces-cze-phon",
      "featured": false,
      "datasetId": "ces_CZE_PHON",
      "locale": [
        "cs-CZ"
      ],
      "country": "Czech Republic",
      "languageGroup": "Czech",
      "category": "Pronunciation Dictionary",
      "volume": "50,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a5e6ee6e81af9b3a6f",
      "collection": "pronunciation-dictionaries",
      "title": "Croatian (Croatia) Pronunciation Dictionary",
      "slug": "hrv-hrv-phon",
      "url": "/data-catalog/pronunciation-dictionaries/hrv-hrv-phon",
      "featured": false,
      "datasetId": "hrv_HRV_PHON",
      "locale": [
        "hr-HR"
      ],
      "country": "Croatia",
      "languageGroup": "Croatian",
      "category": "Pronunciation Dictionary",
      "volume": "19,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a5946e817c7d6399a1",
      "collection": "pronunciation-dictionaries",
      "title": "Cebuano (Philippines) Pronunciation Dictionary",
      "slug": "ceb-phl-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ceb-phl-phon",
      "featured": false,
      "datasetId": "ceb_PHL_PHON",
      "locale": [
        "ceb-PH"
      ],
      "country": "Philippines",
      "languageGroup": "Cebuano",
      "category": "Pronunciation Dictionary",
      "volume": "21,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a417854c543f93d91f",
      "collection": "pronunciation-dictionaries",
      "title": "Catalan (Spain) Pronunciation Dictionary",
      "slug": "cat-esp-phon",
      "url": "/data-catalog/pronunciation-dictionaries/cat-esp-phon",
      "featured": false,
      "datasetId": "cat_ESP_PHON",
      "locale": [
        "ca-ES"
      ],
      "country": "Spain",
      "languageGroup": "Catalan",
      "category": "Pronunciation Dictionary",
      "volume": "10,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a3fa9df117f358e59d",
      "collection": "pronunciation-dictionaries",
      "title": "Cantonese (Hong Kong) Traditional Part of Speech Dictionary",
      "slug": "yue-hkg-pos",
      "url": "/data-catalog/pronunciation-dictionaries/yue-hkg-pos",
      "featured": false,
      "datasetId": "yue_HKG_POS",
      "locale": [
        "yue-HK"
      ],
      "country": "Hong Kong",
      "languageGroup": "Cantonese",
      "category": "Part of Speech Dictionary",
      "volume": "10,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "Traditional",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a231b4728186af20a6",
      "collection": "pronunciation-dictionaries",
      "title": "Cantonese (Hong Kong) Traditional Pronunciation Dictionary",
      "slug": "yue-hkg-phon",
      "url": "/data-catalog/pronunciation-dictionaries/yue-hkg-phon",
      "featured": false,
      "datasetId": "yue_HKG_PHON",
      "locale": [
        "yue-HK"
      ],
      "country": "Hong Kong",
      "languageGroup": "Cantonese",
      "category": "Pronunciation Dictionary",
      "volume": "40,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "Traditional",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987a184235eb50a0f0197",
      "collection": "pronunciation-dictionaries",
      "title": "Cantonese (China) Simplified Pronunciation Dictionary",
      "slug": "yue-chn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/yue-chn-phon",
      "featured": false,
      "datasetId": "yue_CHN_PHON",
      "locale": [
        "yue-CN"
      ],
      "country": "China",
      "languageGroup": "Cantonese",
      "category": "Pronunciation Dictionary",
      "volume": "37,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "Simplified",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99879f946e817c7d639744",
      "collection": "pronunciation-dictionaries",
      "title": "Bulgarian (Bulgaria) Pronunciation Dictionary",
      "slug": "bul-bgr-phon",
      "url": "/data-catalog/pronunciation-dictionaries/bul-bgr-phon",
      "featured": false,
      "datasetId": "bul_BGR_PHON",
      "locale": [
        "bg-BG"
      ],
      "country": "Bulgaria",
      "languageGroup": "Bulgarian",
      "category": "Pronunciation Dictionary",
      "volume": "55,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99879f040b22801499ebb1",
      "collection": "pronunciation-dictionaries",
      "title": "Bengali (India) Pronunciation Dictionary",
      "slug": "ben-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ben-ind-phon",
      "featured": false,
      "datasetId": "ben_IND_PHON",
      "locale": [
        "bn-IN"
      ],
      "country": "India",
      "languageGroup": "Bengali",
      "category": "Pronunciation Dictionary",
      "volume": "29,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99879e17854c543f93d6cb",
      "collection": "pronunciation-dictionaries",
      "title": "Basque (Spain) Pronunciation Dictionary",
      "slug": "eus-esp-phon",
      "url": "/data-catalog/pronunciation-dictionaries/eus-esp-phon",
      "featured": false,
      "datasetId": "eus_ESP_PHON",
      "locale": [
        "eu-ES"
      ],
      "country": "Spain",
      "languageGroup": "Basque",
      "category": "Pronunciation Dictionary",
      "volume": "10,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99879deaf7c7f9ff51afda",
      "collection": "pronunciation-dictionaries",
      "title": "Indonesian (Indonesia) Part of Speech Dictionary",
      "slug": "ind-idn-pos",
      "url": "/data-catalog/pronunciation-dictionaries/ind-idn-pos",
      "featured": false,
      "datasetId": "ind_IDN_POS",
      "locale": [
        "id-ID"
      ],
      "country": "Indonesia",
      "languageGroup": "Indonesian",
      "category": "Part of Speech Dictionary",
      "volume": "10,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99879bf4c0365c95ae8ca1",
      "collection": "pronunciation-dictionaries",
      "title": "Indonesian (Indonesia) Pronunciation Dictionary",
      "slug": "ind-idn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ind-idn-phon",
      "featured": false,
      "datasetId": "ind_IDN_PHON",
      "locale": [
        "id-ID"
      ],
      "country": "Indonesia",
      "languageGroup": "Indonesian",
      "category": "Pronunciation Dictionary",
      "volume": "95,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987996ab94adf346ebde2",
      "collection": "pronunciation-dictionaries",
      "title": "Assamese (India) Pronunciation Dictionary",
      "slug": "asm-ind-phon",
      "url": "/data-catalog/pronunciation-dictionaries/asm-ind-phon",
      "featured": false,
      "datasetId": "asm_IND_PHON",
      "locale": [
        "as-IN"
      ],
      "country": "India",
      "languageGroup": "Assamese",
      "category": "Pronunciation Dictionary",
      "volume": "40,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a998798f4c0365c95ae8c34",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Sudan) Pronunciation Dictionary",
      "slug": "ara-sdn-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ara-sdn-phon",
      "featured": false,
      "datasetId": "ara_SDN_PHON",
      "locale": [
        "ar-SD"
      ],
      "country": "Sudan",
      "languageGroup": "Arabic",
      "category": "Pronunciation Dictionary",
      "volume": "17,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987976ab94adf346ebc84",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (United Arab Emirates (UAE)) Pronunciation Dictionary",
      "slug": "ara-are-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ara-are-phon",
      "featured": false,
      "datasetId": "ara_ARE_PHON",
      "locale": [
        "ar-AE"
      ],
      "country": "United Arab Emirates (UAE)",
      "languageGroup": "Arabic",
      "category": "Pronunciation Dictionary",
      "volume": "75,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "Gulf pronunciation lexicon",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a998797040b22801499e780",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (MSA) Pronunciation Dictionary",
      "slug": "arb-msa-phon",
      "url": "/data-catalog/pronunciation-dictionaries/arb-msa-phon",
      "featured": false,
      "datasetId": "arb_MSA_PHON",
      "locale": [
        "ar"
      ],
      "country": "N/A",
      "languageGroup": "Arabic (Standard)",
      "category": "Pronunciation Dictionary",
      "volume": "40,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987968dcd14d10a929677",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Morocco) Pronunciation Dictionary",
      "slug": "ara-mar-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ara-mar-phon",
      "featured": false,
      "datasetId": "ara_MAR_PHON",
      "locale": [
        "ar-MA"
      ],
      "country": "Morocco",
      "languageGroup": "Arabic",
      "category": "Pronunciation Dictionary",
      "volume": "60,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a9987958dcd14d10a929618",
      "collection": "pronunciation-dictionaries",
      "title": "French (Algeria) Pronunciation Dictionary",
      "slug": "fra-dza-phon",
      "url": "/data-catalog/pronunciation-dictionaries/fra-dza-phon",
      "featured": false,
      "datasetId": "fra_DZA_PHON",
      "locale": [
        "fr-DZ"
      ],
      "country": "Algeria",
      "languageGroup": "French",
      "category": "Pronunciation Dictionary",
      "volume": "4,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "Arabic script",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a998794946e817c7d639222",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Algeria) Pronunciation Dictionary",
      "slug": "ara-dza-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ara-dza-phon",
      "featured": false,
      "datasetId": "ara_DZA_PHON",
      "locale": [
        "ar-DZ"
      ],
      "country": "Algeria",
      "languageGroup": "Arabic",
      "category": "Pronunciation Dictionary",
      "volume": "11,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a998793040b22801499e681",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Libya) Pronunciation Dictionary",
      "slug": "ara-lby-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ara-lby-phon",
      "featured": false,
      "datasetId": "ara_LBY_PHON",
      "locale": [
        "ar-LY"
      ],
      "country": "Libya",
      "languageGroup": "Arabic",
      "category": "Pronunciation Dictionary",
      "volume": "48,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a998792e924c86953f9436f",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Iraq) Part of Speech Dictionary",
      "slug": "ara-irq-pos",
      "url": "/data-catalog/pronunciation-dictionaries/ara-irq-pos",
      "featured": false,
      "datasetId": "ara_IRQ_POS",
      "locale": [
        "ar-IQ"
      ],
      "country": "Iraq",
      "languageGroup": "Arabic",
      "category": "Part of Speech Dictionary",
      "volume": "13,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99879184235eb50a0ef295",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Iraq) Pronunciation Dictionary",
      "slug": "ara-irq-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ara-irq-phon",
      "featured": false,
      "datasetId": "ara_IRQ_PHON",
      "locale": [
        "ar-IQ"
      ],
      "country": "Iraq",
      "languageGroup": "Arabic",
      "category": "Pronunciation Dictionary",
      "volume": "19,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "Person names",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99878f84235eb50a0ef0d4",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic (Egypt) Pronunciation Dictionary",
      "slug": "ara-egy-phon",
      "url": "/data-catalog/pronunciation-dictionaries/ara-egy-phon",
      "featured": false,
      "datasetId": "ara_EGY_PHON",
      "locale": [
        "ar-EG"
      ],
      "country": "Egypt",
      "languageGroup": "Arabic",
      "category": "Pronunciation Dictionary",
      "volume": "40,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99878e6ab94adf346eb8d8",
      "collection": "pronunciation-dictionaries",
      "title": "Amharic (Ethiopia) Pronunciation Dictionary",
      "slug": "amh-eth-phon",
      "url": "/data-catalog/pronunciation-dictionaries/amh-eth-phon",
      "featured": false,
      "datasetId": "amh_ETH_PHON",
      "locale": [
        "am-ET"
      ],
      "country": "Ethiopia",
      "languageGroup": "Amharic",
      "category": "Pronunciation Dictionary",
      "volume": "49,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99878d8afbba3957452208",
      "collection": "pronunciation-dictionaries",
      "title": "Albanian (Albania) Pronunciation Dictionary",
      "slug": "sqi-alb-phon",
      "url": "/data-catalog/pronunciation-dictionaries/sqi-alb-phon",
      "featured": false,
      "datasetId": "sqi_ALB_PHON",
      "locale": [
        "sq-AL"
      ],
      "country": "Albania",
      "languageGroup": "Albanian",
      "category": "Pronunciation Dictionary",
      "volume": "12,000 words",
      "unitType": "words",
      "dataFormat": "txt",
      "datasetDescription": "",
      "source": "Appen Global",
      "yearOfCollection": ""
    },
    {
      "id": "6a99878c811b8e5d7361beaf",
      "collection": "pronunciation-dictionaries",
      "title": "Urdu NER news text",
      "slug": "urd-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/urd-ner001",
      "featured": false,
      "datasetId": "URD_NER001",
      "locale": [
        "ur-PK"
      ],
      "country": "Pakistan",
      "languageGroup": "Urdu",
      "category": "News NER",
      "volume": "20,634 sentences",
      "unitType": "sentences",
      "dataFormat": "txt",
      "datasetDescription": "News text corpora with entities tagged in XML format: Person, Title, Organization, Location, Geo-political entity, Facility, Religion, Nationality, Quantity",
      "source": "Appen Global",
      "yearOfCollection": "2009"
    },
    {
      "id": "6a99878cc8ebe72e2d9e9f09",
      "collection": "pronunciation-dictionaries",
      "title": "Japanese NER news text",
      "slug": "jpy-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/jpy-ner001",
      "featured": false,
      "datasetId": "JPY_NER001",
      "locale": [
        "ja-JP"
      ],
      "country": "Japan",
      "languageGroup": "Japanese",
      "category": "News NER",
      "volume": "20,629 sentences",
      "unitType": "sentences",
      "dataFormat": "txt",
      "datasetDescription": "News text corpora with entities tagged in XML format: Person, Title, Organization, Location, Geo-political entity, Facility, Religion, Nationality, Quantity",
      "source": "Appen Global",
      "yearOfCollection": "2009"
    },
    {
      "id": "6a99878bf4ac0d8edcf3cecc",
      "collection": "pronunciation-dictionaries",
      "title": "Farsi/Persian NER news text",
      "slug": "far-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/far-ner001",
      "featured": false,
      "datasetId": "FAR_NER001",
      "locale": [
        "fa-IR"
      ],
      "country": "Iran",
      "languageGroup": "Iranian Persian",
      "category": "News NER",
      "volume": "19,584 sentences",
      "unitType": "sentences",
      "dataFormat": "txt",
      "datasetDescription": "News text corpora with entities tagged in XML format: Person, Title, Organization, Location, Geo-political entity, Facility, Religion, Nationality, Quantity",
      "source": "Appen Global",
      "yearOfCollection": "2009"
    },
    {
      "id": "6a99878a57206d63ef261d93",
      "collection": "pronunciation-dictionaries",
      "title": "Mandarin NER news text",
      "slug": "mac-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/mac-ner001",
      "featured": false,
      "datasetId": "MAC_NER001",
      "locale": [
        "zh-CN"
      ],
      "country": "China",
      "languageGroup": "Mandarin Chinese",
      "category": "News NER",
      "volume": "17,313 sentences",
      "unitType": "sentences",
      "dataFormat": "txt",
      "datasetDescription": "News text corpora with entities tagged in XML format: Person, Title, Organization, Location, Geo-political entity, Facility, Religion, Nationality, Quantity",
      "source": "Appen Global",
      "yearOfCollection": "2009"
    },
    {
      "id": "6a998789bc894a1ebfd42401",
      "collection": "pronunciation-dictionaries",
      "title": "Russian NER news text",
      "slug": "rus-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/rus-ner001",
      "featured": false,
      "datasetId": "RUS_NER001",
      "locale": [
        "ru-RU"
      ],
      "country": "Russia",
      "languageGroup": "Russian",
      "category": "News NER",
      "volume": "29,888 sentences",
      "unitType": "sentences",
      "dataFormat": "txt",
      "datasetDescription": "News text corpora with entities tagged in XML format: Person, Title, Organization, Location, Geo-political entity, Facility, Religion, Nationality, Quantity",
      "source": "Appen Global",
      "yearOfCollection": "2009"
    },
    {
      "id": "6a9987886ab94adf346eb59e",
      "collection": "pronunciation-dictionaries",
      "title": "Korean NER news text",
      "slug": "kor-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/kor-ner001",
      "featured": false,
      "datasetId": "KOR_NER001",
      "locale": [
        "ko-KR"
      ],
      "country": "South Korea",
      "languageGroup": "Korean",
      "category": "News NER",
      "volume": "25,830 sentences",
      "unitType": "sentences",
      "dataFormat": "txt",
      "datasetDescription": "News text corpora with entities tagged in XML format: Person, Title, Organization, Location, Geo-political entity, Facility, Religion, Nationality, Quantity",
      "source": "Appen Global",
      "yearOfCollection": "2009"
    },
    {
      "id": "6a99878784235eb50a0ee723",
      "collection": "pronunciation-dictionaries",
      "title": "English NER news text",
      "slug": "eng-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/eng-ner001",
      "featured": false,
      "datasetId": "ENG_NER001",
      "locale": [
        "en"
      ],
      "country": "N/A",
      "languageGroup": "English",
      "category": "News NER",
      "volume": "22,768 sentences",
      "unitType": "sentences",
      "dataFormat": "txt",
      "datasetDescription": "News text corpora with entities tagged in XML format: Person, Title, Organization, Location, Geo-political entity, Facility, Religion, Nationality, Quantity",
      "source": "Appen Global",
      "yearOfCollection": "2009"
    },
    {
      "id": "6a99878610482f3af40051e6",
      "collection": "pronunciation-dictionaries",
      "title": "Arabic NER news text",
      "slug": "arb-ner001",
      "url": "/data-catalog/pronunciation-dictionaries/arb-ner001",
      "featured": false,
      "datasetId": "ARB_NER001",
      "locale": [
        "ar"
      ],
      "country": "N/A",
      "languageGroup": "Arabic (Standard)",
      "category": "News NER",
      "volume": "20,774 sentences",
      "unitType": "sentences",
      "dataFormat": "txt",
      "datasetDescription": "News text corpora with entities tagged in XML format: Person, Title, Organization, Location, Geo-political entity, Facility, Religion, Nationality, Quantity",
      "source": "Appen Global",
      "yearOfCollection": "2009"
    },
    {
      "id": "6a99883017376764883decc1",
      "collection": "enterprise-company-data",
      "title": "FinTech/Doorstep Gold Loan Services — FinTech-60",
      "slug": "fintech-60",
      "url": "/data-catalog/enterprise-company-data/fintech-60",
      "featured": false,
      "datasetId": "FinTech-60",
      "industry": "FinTech/Doorstep Gold Loan Services",
      "codeBaseAvailable": "Yes",
      "businessDescription": "A doorstep gold loan platform offering fast, low-interest lending against gold with high per-gram valuation. Customers request a loan, get gold valued at home, and receive money instantly, combining technology and logistics to make gold-backed lending simple, affordable and relationship-driven.",
      "operatingPeriod": "2021–2024",
      "peakHeadcount": "100",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Application servers & databases",
        "enterprise Gmail",
        "Google Drive",
        "Git repositories"
      ],
      "dataVolumeDetails": "~1,100+ GB. Codebase details: 29 repositories; 3,601,659 LOC across 26,459 files (18,434 source / 238 test); C++, PHP, JavaScript, Java, Python; 2,533 commits, 298 PRs, 12 contributors; commit spread 170 days; product period 2021–2024 Reference: Company_Ops_FinTech-60."
    },
    {
      "id": "6a99882f84235eb50a0f709f",
      "collection": "enterprise-company-data",
      "title": "Manufacturing / Supply Chain ERP (SaaS) — ManufERP-20",
      "slug": "manuferp-20",
      "url": "/data-catalog/enterprise-company-data/manuferp-20",
      "featured": false,
      "datasetId": "ManufERP-20",
      "industry": "Manufacturing / Supply Chain ERP (SaaS)",
      "codeBaseAvailable": "Yes",
      "businessDescription": "A cloud-based B2B SaaS manufacturing ERP platform for inventory control, procurement, production planning, and operational efficiency, helping businesses manage their supply chain from sourcing to fulfillment. Offers real-time stock tracking, barcode scanning, low-stock alerts, and analytics/reporting. ~$2Mn raised",
      "operatingPeriod": "2022-2026",
      "peakHeadcount": "~40",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Mail",
        "Google Drive",
        "Git repositories",
        "DevRev",
        "Fathom"
      ],
      "dataVolumeDetails": "~300GB. Codebase details: 36 repositories, primarily Java, JavaScript, TypeScript, Python, Ruby. 18554 files total (7330 test files), 16690 commits, 472 PRs. Reference: Company Ops Manuf-ERP-20."
    },
    {
      "id": "6a99882f4005faf541bb753d",
      "collection": "enterprise-company-data",
      "title": "B2B Commerce Marketplace/Jewellery Retail — FinTech-49",
      "slug": "fintech-49",
      "url": "/data-catalog/enterprise-company-data/fintech-49",
      "featured": false,
      "datasetId": "FinTech-49",
      "industry": "B2B Commerce Marketplace/Jewellery Retail",
      "codeBaseAvailable": "Yes",
      "businessDescription": "A SaaS-led B2B commerce marketplace for small and medium jewellery retailers, enabling procurement, inventory organization, marketing, and sales through a single platform. Also offers digital enablement tools and working capital access which scaled to 5,000+ retailers - raised multiple $Mn rounds from Tier-1 VCs",
      "operatingPeriod": "2021–2023",
      "peakHeadcount": "50",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Mail",
        "Google Drive",
        "Git repositories"
      ],
      "dataVolumeDetails": "~550+ GB. Codebase details: 29 repositories; 608,761 LOC across 7,883 files (2,402 source / 127 test); TypeScript, Python, JavaScript, C++, Swift, Kotlin; 11,023 commits, 3,602 PRs, 112 contributors; commit spread 459 days; product period 2021–2023 Reference: Company_Ops_FinTech-49."
    },
    {
      "id": "6a99882e89ead58b4c209120",
      "collection": "enterprise-company-data",
      "title": "Logistics — Logistics-63",
      "slug": "logistics-63",
      "url": "/data-catalog/enterprise-company-data/logistics-63",
      "featured": false,
      "datasetId": "Logistics-63",
      "industry": "Logistics",
      "codeBaseAvailable": "Yes",
      "businessDescription": "Logistics-63 was an India-founded, GCC-expanded freight and logistics technology platform that operated for seven years, from launch through international expansion into the Gulf and eventual wind-down.",
      "operatingPeriod": "2018-2022",
      "peakHeadcount": "60",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Mail",
        "Documents",
        "Codebase"
      ],
      "dataVolumeDetails": "~88 GB. Codebase details: 2 repos: Java/Spring Maven project; primary language Java, with JavaScript for front-end resources. Real production logic for truck dispatch, live tracking, invoicing, and user management, captured across two sequential codebase snapshots for before/after evolution analysis. Reference: Company_Ops_Logistics-63.xlsx."
    },
    {
      "id": "6a99882c811b8e5d736215f8",
      "collection": "enterprise-company-data",
      "title": "Education + Immigration — Immigration_Tech_07",
      "slug": "immigration-tech-07",
      "url": "/data-catalog/enterprise-company-data/immigration-tech-07",
      "featured": false,
      "datasetId": "Immigration_Tech_07",
      "industry": "Education + Immigration",
      "codeBaseAvailable": "Yes",
      "businessDescription": "An AI-powered global mobility and immigration platform based in Bangalore, helping Indian professionals navigate visa, work permit, and immigration pathways to countries including Germany, Canada, and Australia. Active business.",
      "operatingPeriod": "2.0 years (Active )",
      "peakHeadcount": "100+",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Slack",
        "Hangouts",
        "WhatsApp",
        "Zoom",
        "Jira",
        "Chetto",
        "Internal CRM",
        "Notion",
        "Pyjama HR",
        "GreytHR",
        "My Operator",
        "Flexmoney",
        "Smallest AI",
        "Zoop",
        "Deepgram",
        "Fireflies",
        "Firebase"
      ],
      "dataVolumeDetails": "~1,600 GB. Funding: Angel Funding. Email suite available: Yes. Google Workspace/Documentation available: Yes. Sample: Exclusively Sold, not available."
    },
    {
      "id": "6a99882bf4c0365c95aebc39",
      "collection": "enterprise-company-data",
      "title": "Media Holding Company — Media_Holding_06",
      "slug": "media-holding-06",
      "url": "/data-catalog/enterprise-company-data/media-holding-06",
      "featured": false,
      "datasetId": "Media_Holding_06",
      "industry": "Media Holding Company",
      "codeBaseAvailable": "Yes",
      "businessDescription": "A US-based digital media holding company operating 20+ web properties across consumer verticals, with a centralized AI-powered editorial and monetization platform. Active business.",
      "operatingPeriod": "2.0 years (Active )",
      "peakHeadcount": "100+",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Slack",
        "Hangouts",
        "WhatsApp",
        "Jira",
        "GreyT HR",
        "Woodpecker",
        "Fathom",
        "BoldSign"
      ],
      "dataVolumeDetails": "~598 GB. Funding: Angel Funding. Email suite available: Yes. Google Workspace/Documentation available: Yes. Sample: Exclusively Sold, not available."
    },
    {
      "id": "6a99882b13e9a932dc4755f6",
      "collection": "enterprise-company-data",
      "title": "Transportation and Logistics — Transport_Tech_01",
      "slug": "transport-tech-01",
      "url": "/data-catalog/enterprise-company-data/transport-tech-01",
      "featured": false,
      "datasetId": "Transport_Tech_01",
      "industry": "Transportation and Logistics",
      "codeBaseAvailable": "Yes",
      "businessDescription": "A Bangalore-based B2B tech-logistics platform for intra-city and last-mile freight, serving enterprise clients across FMCG, retail, and e-commerce. Raised around $100M across several rounds. Acquired in 2026. Annual revenue crossed  $55M in FY25.",
      "operatingPeriod": "10+ years (Active)",
      "peakHeadcount": "700+",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Google Chat",
        "Jira",
        "Confluence",
        "Darwinbox",
        "JIRA Service Desk",
        "Inhouse CRM",
        "Inhouse ERP",
        "Zoho Books"
      ],
      "dataVolumeDetails": "~10,000 GB. Funding: ~ USD 100M. Email suite available: Yes. Google Workspace/Documentation available: Yes. Sample: Exclusively Sold, not available."
    },
    {
      "id": "6a99882a73f796e259270f73",
      "collection": "enterprise-company-data",
      "title": "Education — Education_B",
      "slug": "education-b",
      "url": "/data-catalog/enterprise-company-data/education-b",
      "featured": false,
      "datasetId": "Education_B",
      "industry": "Education",
      "codeBaseAvailable": "Yes",
      "businessDescription": "Online competitive and government exam preparation platform serving the Indian market. Reaches ~40M annual users with content covering banking; civil services; SSC; railways; and other major government recruitment exams. Operates with a team of ~112 employees.",
      "operatingPeriod": "7+ years (Active)",
      "peakHeadcount": "100+",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Slack",
        "Hangouts",
        "Zoho (ITSM + support)",
        "Greythr",
        "Inhouse HRIS",
        "Inhouse CRM"
      ],
      "dataVolumeDetails": "~1,000 GB. Funding: Angel Funding. Email suite available: Yes. Google Workspace/Documentation available: Yes."
    },
    {
      "id": "6a998829f3c00f7b2dc2185d",
      "collection": "enterprise-company-data",
      "title": "Adtech — A_CD",
      "slug": "a-cd",
      "url": "/data-catalog/enterprise-company-data/a-cd",
      "featured": false,
      "datasetId": "A_CD",
      "industry": "Adtech",
      "codeBaseAvailable": "Yes",
      "businessDescription": "A performance-driven ad-tech and digital marketing company focused on user acquisition, affiliate marketing, and programmatic media buying across mobile and desktop platforms. The business leverages AI, audience segmentation, and data-driven targeting to help brands improve ROI and scale customer acquisition globally.",
      "operatingPeriod": "6+ years (Active)",
      "peakHeadcount": "200+",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Slack",
        "Hangouts",
        "Zoho (ITSM + support)",
        "Greythr",
        "Inhouse HRIS",
        "Inhouse CRM"
      ],
      "dataVolumeDetails": "~4,000 GB. Funding: Angel Funding. Email suite available: Yes. Google Workspace/Documentation available: Yes."
    },
    {
      "id": "6a998828834e4fbc0a921492",
      "collection": "enterprise-company-data",
      "title": "Education — Education_A",
      "slug": "education-a",
      "url": "/data-catalog/enterprise-company-data/education-a",
      "featured": false,
      "datasetId": "Education_A",
      "industry": "Education",
      "codeBaseAvailable": "Yes",
      "businessDescription": "India's largest higher education discovery platform and college review portal. ~100M annual visitors, USD 25M+ revenue.",
      "operatingPeriod": "10+ years (Active)",
      "peakHeadcount": "800+",
      "headquarters": "",
      "employeeLocations": "",
      "operatingModel": "",
      "platformsTools": [
        "Slack",
        "Hangouts",
        "Zoho (ITSM + support)",
        "Greythr",
        "Inhouse HRIS",
        "Inhouse CRM"
      ],
      "dataVolumeDetails": "~30,000 GB. Funding: Angel Funding. Email suite available: Yes. Google Workspace/Documentation available: Yes. Sample: CD.zip."
    },
    {
      "id": "6a998827991d16e5e66e5db5",
      "collection": "enterprise-company-data",
      "title": "Fintech — OP17",
      "slug": "op17",
      "url": "/data-catalog/enterprise-company-data/op17",
      "featured": false,
      "datasetId": "OP17",
      "industry": "Fintech",
      "codeBaseAvailable": "No",
      "businessDescription": "Fintech solution serving low and moderate income consumers in auto. Developed a connected car digital wallet",
      "operatingPeriod": "6 years, launched May 2020",
      "peakHeadcount": "10",
      "headquarters": "US",
      "employeeLocations": "US only",
      "operatingModel": "Hybrid",
      "platformsTools": [
        "Google Drive",
        "Slack",
        "Linear",
        "Figma",
        "GitHub",
        "Airtable",
        "Retool",
        "telematics data",
        "Stripe",
        "Power Bi"
      ],
      "dataVolumeDetails": "Summary: ~589 GB across 10 tools\nGoogle Drive: 543 GB\nAirtable: 45 GB\nSlack: 444 MB\nRetool: 4.7 MB\nFigma: 37 files\nGitHub: pending analysis\nLinear, Stripe, Power BI, telematics data: not sized"
    },
    {
      "id": "6a99882613e9a932dc475346",
      "collection": "enterprise-company-data",
      "title": "Interior Design - Technology — OP16",
      "slug": "op16",
      "url": "/data-catalog/enterprise-company-data/op16",
      "featured": false,
      "datasetId": "OP16",
      "industry": "Interior Design - Technology",
      "codeBaseAvailable": "Yes",
      "businessDescription": "Interior Design for Short Term Rentals",
      "operatingPeriod": "6 Years",
      "peakHeadcount": "20",
      "headquarters": "US",
      "employeeLocations": "US, Philippines (8 contractors)",
      "operatingModel": "Remote",
      "platformsTools": [
        "Google Drive",
        "Slack",
        "Jira",
        "HubSpot",
        "GitHub",
        "ZenDesk",
        "Brex",
        "PostgreSQL"
      ],
      "dataVolumeDetails": "Summary: 1,000+ Loom videos and 3 years of Google Ads data, remaining 8 tools not sized\nLoom: 1,000+ videos\nGoogle Ads: 3 years of account data\nGoogle Drive, Slack, Jira, HubSpot, GitHub, ZenDesk, Brex, PostgreSQL: not sized"
    },
    {
      "id": "6a998823040b2280149a271a",
      "collection": "enterprise-company-data",
      "title": "AI / Financial Services Technology — OP13",
      "slug": "op13",
      "url": "/data-catalog/enterprise-company-data/op13",
      "featured": false,
      "datasetId": "OP13",
      "industry": "AI / Financial Services Technology",
      "codeBaseAvailable": "No",
      "businessDescription": "AI-powered enterprise intelligence platform with a decade of proprietary data spanning financial transactions, CRM, engineering, communications, and operational systems across 30 integrated enterprise platforms. Production-ready data estate for advanced analytics, sentiment analysis, IP valuation, and strategic intelligence extraction.",
      "operatingPeriod": "10 years",
      "peakHeadcount": "40",
      "headquarters": "US",
      "employeeLocations": "US only",
      "operatingModel": "Hybrid",
      "platformsTools": [
        "Confluence",
        "Google Drive",
        "Slack",
        "Teams",
        "Dropbox",
        "Asana",
        "Jira",
        "Trello",
        "Figma",
        "HubSpot",
        "Salesforce",
        "GitHub",
        "Brex"
      ],
      "dataVolumeDetails": "Summary: 10 years of data across ~30 enterprise platforms, no size figures given\nSlack, Teams, Gmail: 10 years of communications and correspondence\nGitHub, Bitbucket: complete engineering commit history across all repos\nHubSpot, Salesforce: full CRM deal pipeline and customer interaction records\nConfluence, SharePoint, Google Drive, Dropbox: knowledge base and documentation\nJira, Asana, Motion, Trello: complete sprint and project management history\nFigma, Canva, Miro: full design evolution and workshop sessions\nZoom, Google Meet: video recordings and transcripts\nQuickBooks, Chase, Amex, Brex, Bill.com: full transaction and accounting history\nEnterprise data lake: structured warehouse, custom control layer with 300 prebuilt connectors"
    },
    {
      "id": "6a99882117376764883de4e3",
      "collection": "enterprise-company-data",
      "title": "Biotech — OP12",
      "slug": "op12",
      "url": "/data-catalog/enterprise-company-data/op12",
      "featured": false,
      "datasetId": "OP12",
      "industry": "Biotech",
      "codeBaseAvailable": "No",
      "businessDescription": "Cancer therapy based on T cells sourced from peripheral blood and novel isolation device",
      "operatingPeriod": "3.5 years",
      "peakHeadcount": "20",
      "headquarters": "US",
      "employeeLocations": "US only",
      "operatingModel": "Hybrid",
      "platformsTools": [
        "Slack",
        "Gusto",
        "Ramp",
        "Rippling",
        "Box"
      ],
      "dataVolumeDetails": "Summary: 1.3M Box files plus 126 GB of Google Workspace data across 5 tools\nBox: 1.3M collaboration files and documents\nGoogle Workspace: 126 GB, 3,800 files shared\nSlack: 11,500 messages\nGusto, Ramp, Rippling: not sized"
    },
    {
      "id": "6a998821040b2280149a256d",
      "collection": "enterprise-company-data",
      "title": "EdTech / Language Learning — OP11",
      "slug": "op11",
      "url": "/data-catalog/enterprise-company-data/op11",
      "featured": false,
      "datasetId": "OP11",
      "industry": "EdTech / Language Learning",
      "codeBaseAvailable": "No",
      "businessDescription": "Three shipped products.1: voice-first personalized language learning (~20k users, 7 languages). 2: multimodal search for enterprise. 3: composable multimodal workflows",
      "operatingPeriod": "3 years",
      "peakHeadcount": "12",
      "headquarters": "US",
      "employeeLocations": "US, UK",
      "operatingModel": "Remote",
      "platformsTools": [
        "Notion",
        "Google Drive",
        "Slack",
        "Linear",
        "Figma",
        "GitHub"
      ],
      "dataVolumeDetails": "Summary: ~4 TiB in total, dominated by cloud storage, plus 316k lines of code and ~600k text pairs\nGoogle Cloud Storage: ~4 TiB total, sellable subset is images plus ~600k text pairs, audio excluded\nGitHub: 316k lines of code, 26 repos\nNotion: ~3,450 pages, ~2 GB\nSlack: ~31k messages per year, 3,140 files\nLinear: ~1,600 issues\nGoogle Drive: minimal, records retained for dissolution"
    },
    {
      "id": "6a99882031b4728186af39a8",
      "collection": "enterprise-company-data",
      "title": "Technology / Artificial Intelligence — OP10",
      "slug": "op10",
      "url": "/data-catalog/enterprise-company-data/op10",
      "featured": false,
      "datasetId": "OP10",
      "industry": "Technology / Artificial Intelligence",
      "codeBaseAvailable": "No",
      "businessDescription": "Enterprise-scale RLHF and benchmarking platform for large language models (LLMs) and applied AI teams.",
      "operatingPeriod": "4 years",
      "peakHeadcount": "7",
      "headquarters": "US",
      "employeeLocations": "US only",
      "operatingModel": "Hybrid",
      "platformsTools": [
        "Notion",
        "Google Drive",
        "Slack",
        "Linear",
        "Figma",
        "GitHub",
        "Ramp",
        "Brex",
        "Attio",
        "Clickhouse",
        "etc"
      ],
      "dataVolumeDetails": "Summary: hundreds of thousands of items across 11 tools, no per-tool breakdown given\nNotion, Google Drive, Slack, Linear, Figma, GitHub, Ramp, Brex, Attio, Clickhouse: seller reports hundreds of thousands of items in total"
    },
    {
      "id": "6a99881f17854c543f94127c",
      "collection": "enterprise-company-data",
      "title": "Fintech — OP9",
      "slug": "op9",
      "url": "/data-catalog/enterprise-company-data/op9",
      "featured": false,
      "datasetId": "OP9",
      "industry": "Fintech",
      "codeBaseAvailable": "No",
      "businessDescription": "Core product was a digital banking platform with additional features including financial literacy programming and content, P2P payments, round-up savings, and collaborative savings tools.",
      "operatingPeriod": "2018 - 2023",
      "peakHeadcount": "10",
      "headquarters": "US",
      "employeeLocations": "US only",
      "operatingModel": "Pre-covid: in-person",
      "platformsTools": [
        "Google Drive",
        "Slack",
        "Dropbox",
        "Asana",
        "Figma",
        "GitHub",
        "ZenDesk",
        "Brex",
        "Rippling",
        "SendGrid",
        "Mailchimp"
      ],
      "dataVolumeDetails": "Summary: ~251 GB across 11 tools\nGoogle Drive: ~230 GB\nGmail: ~20 GB\nFigma: ~703 MB\nSlack, Dropbox, Asana, GitHub, ZenDesk, Brex, Rippling, SendGrid, Mailchimp: not sized"
    },
    {
      "id": "6a99881e17376764883de220",
      "collection": "enterprise-company-data",
      "title": "Healthcare — OP8",
      "slug": "op8",
      "url": "/data-catalog/enterprise-company-data/op8",
      "featured": false,
      "datasetId": "OP8",
      "industry": "Healthcare",
      "codeBaseAvailable": "No",
      "businessDescription": "Platform that allows healthcare personnel to conduct diabetic rentiopathy screenings anywhere",
      "operatingPeriod": "8 years",
      "peakHeadcount": "10",
      "headquarters": "US",
      "employeeLocations": "US only",
      "operatingModel": "Remote",
      "platformsTools": [
        "Notion",
        "Google Drive",
        "Jira",
        "Slack",
        "HubSpot",
        "Ramp"
      ],
      "dataVolumeDetails": "Summary: ~124 GB across 7 tools\nGoogle Drive: 80.5 GB\nNotion: 37 GB\nJira: 6.4 GB\nSlack: 37 MB\nGoogle Workspace, HubSpot, Ramp: not sized"
    },
    {
      "id": "6a99881d31d6f8d8f3d0e928",
      "collection": "enterprise-company-data",
      "title": "Finance — OP7",
      "slug": "op7",
      "url": "/data-catalog/enterprise-company-data/op7",
      "featured": false,
      "datasetId": "OP7",
      "industry": "Finance",
      "codeBaseAvailable": "No",
      "businessDescription": "Agentic workflow for deal sourcing and screening (M&A)",
      "operatingPeriod": "3 years",
      "peakHeadcount": "5",
      "headquarters": "US",
      "employeeLocations": "US, Canada (1 in Toronto)",
      "operatingModel": "Remote",
      "platformsTools": [
        "Google Drive",
        "Slack",
        "Trello",
        "Figma",
        "GitHub",
        "Gusto",
        "Brex"
      ],
      "dataVolumeDetails": "Summary: no size figures given, core value is proprietary M&A financial datasets\nFinancial / M&A datasets: large volume, multiple proprietary sets, some previously sold at $10k+ each\nGoogle Drive, Slack, Trello, Figma, GitHub, Gusto, Brex: not sized"
    },
    {
      "id": "6a99881c811b8e5d736206b7",
      "collection": "enterprise-company-data",
      "title": "SaaS — OP6",
      "slug": "op6",
      "url": "/data-catalog/enterprise-company-data/op6",
      "featured": false,
      "datasetId": "OP6",
      "industry": "SaaS",
      "codeBaseAvailable": "Yes",
      "businessDescription": "Change management and initiative collaboration platform that helps organizations turn ideas into approved, actionable plans. It guides teams through building business cases, engaging stakeholders, identifying risks, and aligning decision-makers so complex initiatives can move from concept to execution with greater visibility, accountability, and buy-in.",
      "operatingPeriod": "7 years",
      "peakHeadcount": "45",
      "headquarters": "US",
      "employeeLocations": "US, Albania (full-time contractors)",
      "operatingModel": "Hybrid",
      "platformsTools": [
        "Slack",
        "Teams",
        "Figma",
        "GitHub",
        "Gusto",
        "Divvy (Acquired by Bill.com)"
      ],
      "dataVolumeDetails": "Summary: 157k Slack messages, 502k lines of code and 200k+ Figma layers across 7 tools\nGitHub: 502k lines of code\nFigma: 200k+ layers\nSlack: 157k messages\nClickUp: 3,000 tasks\nTeams, Gusto, Divvy: not sized"
    },
    {
      "id": "6a99881b84235eb50a0f5be1",
      "collection": "enterprise-company-data",
      "title": "FinTech + Legal Tech — OP5",
      "slug": "op5",
      "url": "/data-catalog/enterprise-company-data/op5",
      "featured": false,
      "datasetId": "OP5",
      "industry": "FinTech + Legal Tech",
      "codeBaseAvailable": "Yes",
      "businessDescription": "Built fintech + legal tech products",
      "operatingPeriod": "5 years",
      "peakHeadcount": "8",
      "headquarters": "US",
      "employeeLocations": "US, Malta (1 employee)",
      "operatingModel": "Remote",
      "platformsTools": [
        "Notion",
        "Slack",
        "Dropbox",
        "Linear",
        "Figma",
        "GitHub"
      ],
      "dataVolumeDetails": "Summary: tens of thousands of documents across 6 tools, no per-tool breakdown given\nNotion, Slack, Dropbox, Linear, Figma, GitHub: seller estimates tens of thousands of documents, chats and in-depth Figma files"
    },
    {
      "id": "6a99881a13e9a932dc474cdc",
      "collection": "enterprise-company-data",
      "title": "Fintech AI — OP4",
      "slug": "op4",
      "url": "/data-catalog/enterprise-company-data/op4",
      "featured": false,
      "datasetId": "OP4",
      "industry": "Fintech AI",
      "codeBaseAvailable": "Yes",
      "businessDescription": "Pivoted from a neobanking product to an AI services company",
      "operatingPeriod": "8 years",
      "peakHeadcount": "30",
      "headquarters": "US",
      "employeeLocations": "US, India, Europe",
      "operatingModel": "Remote",
      "platformsTools": [
        "Notion",
        "Google Drive",
        "Slack",
        "Jira",
        "Linear",
        "Figma",
        "HubSpot",
        "GitHub"
      ],
      "dataVolumeDetails": "Summary: ~100 GB plus ~1M lines of code and 8 years of Slack history across 8 tools\nGoogle Drive: ~100 GB\nGitHub: ~1M lines of code\nSlack: ~8 years of conversations\nHubSpot: 2,000+ contacts\nJira: 500+ tickets\nNotion, Linear, Figma: not sized"
    },
    {
      "id": "6a998819d3a0ae3d2979555e",
      "collection": "enterprise-company-data",
      "title": "Consumer Productivity / Mental Health — OP2",
      "slug": "op2",
      "url": "/data-catalog/enterprise-company-data/op2",
      "featured": false,
      "datasetId": "OP2",
      "industry": "Consumer Productivity / Mental Health",
      "codeBaseAvailable": "No",
      "businessDescription": "Tech-enabled personal assistant and designed specifically for busy families to manage their mental load and household to-dos.",
      "operatingPeriod": "7 years; 2018 - 2025",
      "peakHeadcount": "20",
      "headquarters": "US",
      "employeeLocations": "US only",
      "operatingModel": "Remote",
      "platformsTools": [
        "Notion",
        "Google Drive",
        "Slack",
        "Trello",
        "Figma",
        "HubSpot",
        "GitLab",
        "Gusto"
      ],
      "dataVolumeDetails": "Summary: ~54 GB across 7 tools, plus ~7 years of unsized Slack and Gusto history (seller estimates)\nGoogle Drive: ~50 GB\nNotion: ~4 GB, exported as CSV\nTrello: ~3,000 cards\nFigma: ~33 MB\nHubSpot: ~5 MB\nSlack: not sized, ~7 years of a fully remote team\nGusto: not sized, ~7 years of records"
    },
    {
      "id": "6a998818811b8e5d736200b7",
      "collection": "enterprise-company-data",
      "title": "B2B SaaS — OP1",
      "slug": "op1",
      "url": "/data-catalog/enterprise-company-data/op1",
      "featured": false,
      "datasetId": "OP1",
      "industry": "B2B SaaS",
      "codeBaseAvailable": "Yes",
      "businessDescription": "Generative Video AI for sales and marketing professionals",
      "operatingPeriod": "5 years",
      "peakHeadcount": "14",
      "headquarters": "US",
      "employeeLocations": "US only",
      "operatingModel": "Remote",
      "platformsTools": [
        "Notion",
        "Google Drive",
        "Wikis",
        "Slack",
        "Asana",
        "Jira",
        "Figma",
        "GitHub",
        "Gusto"
      ],
      "dataVolumeDetails": "Summary: ~181 GB across 7 tools, 658k+ messages and emails, 12.7k commits\nGmail: 536,540 emails\nGoogle Drive: 4,448 files, 163.88 GB\nGoogle Workspace: 548 Docs, 324 Sheets, 54 Slides\nSlack: 110,421 messages, 122 channels, 9,027 files, 14.26 GB\nGitHub: 65 repos, 12,717 commits, 29 contributors, 3.2 GB\nAsana: 1,023 tasks, 51 projects, 55 attachments\nIntercom: 844 conversations, 11,303 messages, 11,854 contacts"
    },
    {
      "id": "6a998846fa9df117f3592aea",
      "collection": "image-video-sets",
      "title": "Roomba view images",
      "slug": "img-sdj-cn",
      "url": "/data-catalog/image-video-sets/img-sdj-cn",
      "featured": false,
      "datasetId": "IMG_SDJ_CN",
      "category": "Image recognition",
      "domain": [
        "Home / Pet Care"
      ],
      "recordingDevice": "Roomba camera",
      "recordingCondition": "",
      "resolutionPixelDimensions": [],
      "volume": "82000 images",
      "unitType": "Image",
      "generationSource": "Captured from robotic vacuum cleaner camera perspective",
      "annotation": [
        "Not specified"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen China",
      "datasetDescription": "Particles, seasoning sauce, pet food, and pet feces from the perspective of a robotic vacuum cleaner. Clarity 2K+",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99884513e9a932dc4766d5",
      "collection": "image-video-sets",
      "title": "Garments image and video collection **in development**",
      "slug": "img-vid-garments-us",
      "url": "/data-catalog/image-video-sets/img-vid-garments-us",
      "featured": false,
      "datasetId": "IMG_VID_GARMENTS_US",
      "category": "Image recognition",
      "domain": [
        "Fashion / Garments"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [],
      "volume": "300 sessions",
      "unitType": "Video",
      "generationSource": "Participant self-recorded photos/videos following a prompt",
      "annotation": [
        "Bounding box + category labels",
        "Demographic + body measurement metadata, garment category/description labels"
      ],
      "dataFormat": [
        "jpg",
        "mp4",
        "mov"
      ],
      "source": "Appen Global",
      "datasetDescription": "Participants took 2 pictures (front and back) of an item of clothing, and a 60-second video of themselves wearing the garment and moving to various angles. Metadata includes demographics, body measurements, labels for garment category (e.g. t-shirt, trousers) and description. | Data collected, QA is underway, expected to be ready Q3 2025. Can be prioritized upon request.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a998844946e817c7d63eca9",
      "collection": "image-video-sets",
      "title": "English (United States) Receipts **in development**",
      "slug": "img-ocr-use-receipts",
      "url": "/data-catalog/image-video-sets/img-ocr-use-receipts",
      "featured": false,
      "datasetId": "IMG_OCR_USE_RECEIPTS",
      "category": "OCR",
      "domain": [
        "Retail Documents / OCR"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [],
      "volume": "4500 images",
      "unitType": "Image",
      "generationSource": "Photographs taken by contributors/field collectors",
      "annotation": [
        "Bounding box annotation",
        "PII redacted"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen Global",
      "datasetDescription": "Photos of receipts, bills or invoices, annotated with bounding boxes and transcribed text. PII redacted. | Data collected, QA and annotation to be done, expected to be ready in H2 2025. Can be prioritized upon request.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a998843afc3cfd64e666066",
      "collection": "image-video-sets",
      "title": "Object videos **in development**",
      "slug": "vid-object-us",
      "url": "/data-catalog/image-video-sets/vid-object-us",
      "featured": false,
      "datasetId": "VID_OBJECT_US",
      "category": "Movement recognition",
      "domain": [
        "Everyday Objects"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [],
      "volume": "5500 videos",
      "unitType": "Video",
      "generationSource": "Participant self-recorded videos of selected everyday objects",
      "annotation": [
        "Annotation pending (in progress)"
      ],
      "dataFormat": [
        "mp4",
        "mov"
      ],
      "source": "Appen Global",
      "datasetDescription": "Approximately 6 hours of videos of various objects under different angles, distances and lighting conditions. Contributors selected from a list of ~150 everyday objects (e.g. dog, kettle, desk). | Data collected, QA is underway, expected to be ready Q3 2025. Can be prioritized upon request.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a998842d3a0ae3d29796ef1",
      "collection": "image-video-sets",
      "title": "Hand gesture videos",
      "slug": "human-body-vid003",
      "url": "/data-catalog/image-video-sets/human-body-vid003",
      "featured": true,
      "datasetId": "HUMAN_BODY_VID003",
      "category": "Human Body Movement",
      "domain": [
        "Human Gestures"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [],
      "volume": "3099 videos",
      "unitType": "Video",
      "generationSource": "Participant self-recorded videos following a prompt",
      "annotation": [
        "Gesture-type metadata"
      ],
      "dataFormat": [
        "mp4",
        "mov"
      ],
      "source": "Appen Global",
      "datasetDescription": "Approximately 11 hours of video of participants making hand gestures e.g. thumbs up, wave. Videos may include the participants face or only their hand. Metadata included describing the type of hand gesture in the video.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a998840811b8e5d73621f48",
      "collection": "image-video-sets",
      "title": "English (United States) Street signs **in development**",
      "slug": "img-ocr-use-street002",
      "url": "/data-catalog/image-video-sets/img-ocr-use-street002",
      "featured": false,
      "datasetId": "IMG_OCR_USE_STREET002",
      "category": "OCR",
      "domain": [
        "Signage / OCR"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [],
      "volume": "3500 images",
      "unitType": "Image",
      "generationSource": "Photographs taken by contributors/field collectors",
      "annotation": [
        "Bounding box annotation",
        "Text description labelling"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen Global",
      "datasetDescription": "Photos of US street signs, annotated with bounding boxes, transcribed text, and text description of the sign |Data collected, QA is underway, expected to be ready Q3 2025. Can be prioritized upon request.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99883f13e9a932dc476284",
      "collection": "image-video-sets",
      "title": "English (United States) Symbols",
      "slug": "img-symbols-us",
      "url": "/data-catalog/image-video-sets/img-symbols-us",
      "featured": false,
      "datasetId": "IMG_SYMBOLS_US",
      "category": "OCR",
      "domain": [
        "Signage / Symbols"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [],
      "volume": "500 images",
      "unitType": "Image",
      "generationSource": "Photographs taken by contributors/field collectors",
      "annotation": [
        "Text description labelling"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen Global",
      "datasetDescription": "Photos of symbols - small pictures that communicate an action or warning (e.g. recycling or laundering instructions) encountered in everyday life, with text descriptions.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99883e946e817c7d63e9a2",
      "collection": "image-video-sets",
      "title": "English (United States) Product labels",
      "slug": "img-ocr-use-productlabels",
      "url": "/data-catalog/image-video-sets/img-ocr-use-productlabels",
      "featured": true,
      "datasetId": "IMG_OCR_USE_PRODUCTLABELS",
      "category": "Image recognition",
      "domain": [
        "Product Packaging / Retail"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [
        "Resolution: Phone-native corpus, no document scans. ~63% vertical 1080px-wide phone video/photo frames (variable height, mostly 1440px)",
        "~25% phone camera photos (native 4:3 sensor, e.g. 3024×4032, 4000×3000)",
        "~4% 16:9 photo/video frames",
        "~3% panoramic/extreme-aspect shots",
        "~5% other/odd aspect ratios (including some square 3120×3120 crops) and oversized outliers"
      ],
      "volume": "54350 images",
      "unitType": "Image",
      "generationSource": "Photographs taken by contributors/field collectors",
      "annotation": [
        "Bounding box annotation",
        "Annotated for category e"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen Global",
      "datasetDescription": "Photos of various products including the label |Annotated for category e.g. Food, health & beauty, pet supplies; brand name, packaging type, product description, angle and image quality. | Bounding box and text transcription annotation can be developed upon request.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99883df3c00f7b2dc21d4e",
      "collection": "image-video-sets",
      "title": "Action videos",
      "slug": "vid-action-us",
      "url": "/data-catalog/image-video-sets/vid-action-us",
      "featured": true,
      "datasetId": "VID_ACTION_US",
      "category": "Human Body Movement",
      "domain": [
        "Human & Animal Actions/Activities"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [
        "Various: 1280x720",
        "1920x1080",
        "3840x2160"
      ],
      "volume": "281 videos",
      "unitType": "Video",
      "generationSource": "Participant self-recorded photos/videos following a prompt",
      "annotation": [
        "Not specified"
      ],
      "dataFormat": [
        "mp4"
      ],
      "source": "Appen Global",
      "datasetDescription": "Participants videoed themselves or an animal completing an action from a given prompt, e.g. “zip up a jacket”, “drink a beverage”, \"an animal running\"",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99883cbc894a1ebfd46032",
      "collection": "image-video-sets",
      "title": "Selfie image and video collection",
      "slug": "img-vid-selfie-us",
      "url": "/data-catalog/image-video-sets/img-vid-selfie-us",
      "featured": true,
      "datasetId": "IMG_VID_SELFIE_US",
      "category": "Human Face",
      "domain": [
        "Facial Expressions / Selfies"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [
        "Various: 1280x720",
        "1280x960",
        "1920x1080",
        "3840x2160"
      ],
      "volume": "2938 files (1403 images, 1535 videos)",
      "unitType": "Image; Video",
      "generationSource": "Participant self-recorded photos/videos following a prompt",
      "annotation": [
        "Not specified"
      ],
      "dataFormat": [
        "jpg",
        "mp4",
        "mov"
      ],
      "source": "Appen Global",
      "datasetDescription": "Participants took a short video and picture of themselves following a prompt making various facial expressions under different conditions, e.g. “while blinking”, “while wearing a scarf”. There are 1403 images and 1535 videos across 1566 recording sessions, by 70 unique participants.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99883b811b8e5d73621daa",
      "collection": "image-video-sets",
      "title": "Baking Pictures",
      "slug": "img-bake-cn",
      "url": "/data-catalog/image-video-sets/img-bake-cn",
      "featured": false,
      "datasetId": "IMG_BAKE_CN",
      "category": "Image recognition",
      "domain": [
        "Food / Baked Goods"
      ],
      "recordingDevice": "",
      "recordingCondition": "",
      "resolutionPixelDimensions": [
        "640 x 640 px"
      ],
      "volume": "6000 images",
      "unitType": "Image",
      "generationSource": "Sourced from public websites",
      "annotation": [
        "Not specified"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen China",
      "datasetDescription": "(Data source: website) This dataset includes pictures of baked goods: 2000 images of bread, 2000 images of cakes, and 2000 images of cookies. Image resolution: 640px * 640px. Shooting angle: either vertically downward or slightly offset.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99883ae924c86953f994e8",
      "collection": "image-video-sets",
      "title": "Electric vehicles in elevators",
      "slug": "img-ddc-cn",
      "url": "/data-catalog/image-video-sets/img-ddc-cn",
      "featured": false,
      "datasetId": "IMG_DDC_CN",
      "category": "Image recognition",
      "domain": [
        "Automotive (electric vehicles, elevator scenes)"
      ],
      "recordingDevice": "Surveillance camera",
      "recordingCondition": "",
      "resolutionPixelDimensions": [
        "1080x1920"
      ],
      "volume": "17132 images",
      "unitType": "Image",
      "generationSource": "Collected photographs/CCTV-style images",
      "annotation": [
        "Bounding box annotation",
        "Bounding box + category labels"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen China",
      "datasetDescription": "The electric vehicle image in elevator scene, with no more than 5 images of the same electric vehicle appearing. All images have annotation (monitoring perspective) with bounding boxes and labels (person, vehicle)",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99883917854c543f941961",
      "collection": "image-video-sets",
      "title": "Home environment pictures",
      "slug": "img-home-cn",
      "url": "/data-catalog/image-video-sets/img-home-cn",
      "featured": false,
      "datasetId": "IMG_HOME_CN",
      "category": "Image recognition",
      "domain": [
        "Home Interiors"
      ],
      "recordingDevice": "",
      "recordingCondition": "",
      "resolutionPixelDimensions": [
        "640 x 480"
      ],
      "volume": "10000 images",
      "unitType": "Image",
      "generationSource": "Sourced from public websites",
      "annotation": [
        "No annotation"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen China",
      "datasetDescription": "(Data source: website) 4000 images in the study room; 6000 images in the living room. No annotation.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a9988388dcd14d10a92bfd6",
      "collection": "image-video-sets",
      "title": "Vehicle tail light images",
      "slug": "img-wd-cn",
      "url": "/data-catalog/image-video-sets/img-wd-cn",
      "featured": false,
      "datasetId": "IMG_WD_CN",
      "category": "Image recognition",
      "domain": [
        "Automotive / License Plates"
      ],
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [
        "Resolution: Highly variable",
        "no fixed capture resolution — individually cropped/exported stills rather than raw camera output. Resolutions range roughly from 900×600 to 2400×2800px",
        "with most clustering near native 4:3 phone-camera ratio (~1.33) alongside some near-square 1:1 crops and a few wider or portrait outliers."
      ],
      "volume": "30793 images",
      "unitType": "Image",
      "generationSource": "Collected photographs/CCTV-style images",
      "annotation": [
        "License plates redacted"
      ],
      "dataFormat": [
        "jpg"
      ],
      "source": "Appen China",
      "datasetDescription": "Images of vehicle tail lights, with right turn signal on (55%), left turn signal on (22%), both lights on (23%). |License plates have been redacted.",
      "yearOfCollection": "2024"
    },
    {
      "id": "6a99883717956efcbddcffaa",
      "collection": "image-video-sets",
      "title": "Arabic (UAE) printed text annotated OCR",
      "slug": "img-ocr-aru002-cn",
      "url": "/data-catalog/image-video-sets/img-ocr-aru002-cn",
      "featured": false,
      "datasetId": "IMG_OCR_ARU002_CN",
      "category": "Document OCR",
      "domain": [
        "Signage / OCR (slogans, advertisements, maps, store names, menus, packaging)"
      ],
      "recordingDevice": "Mobile phone",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [],
      "volume": "20000 images",
      "unitType": "Image",
      "generationSource": "Photographs/images collected containing text",
      "annotation": [
        "Bounding box annotation"
      ],
      "dataFormat": [
        "jpg",
        "json"
      ],
      "source": "Appen China",
      "datasetDescription": "Images containing text, such as slogans, advertisements, maps, store names, menus, product outer packaging, indication board. Includes bounding box annotations, 50 boxes per image, with all text annotated (Arabic, non-Arabic characters, special characters, numbers)",
      "yearOfCollection": "2023"
    },
    {
      "id": "6a99883613e9a932dc475e0f",
      "collection": "image-video-sets",
      "title": "Location entrance human body movement videos",
      "slug": "human-body-vid002",
      "url": "/data-catalog/image-video-sets/human-body-vid002",
      "featured": false,
      "datasetId": "HUMAN_BODY_VID002",
      "category": "Human Body Movement",
      "domain": [
        "Human Movement / Crowd Behaviour"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed background and lighting conditions",
      "resolutionPixelDimensions": [
        "2048p resolution"
      ],
      "volume": "130 videos",
      "unitType": "Video",
      "generationSource": "Participant video recordings (multi-camera capture)",
      "annotation": [
        "No annotation"
      ],
      "dataFormat": [
        "mp4"
      ],
      "source": "Appen Global",
      "datasetDescription": "This dataset contains 130 sessions of approximately 1-minute videos of groups of 3-10 people (52% 3-5 people, 41% 6-8 people, 37% 9-10 people) walking towards and through entrances in one location in Exeter, UK (2 camera views: front, top - 20 sessions) and 2 locations in Cavite, Philippines (3 camera views: front, top, side for location 1 - 85 sessions - and front, top, top2 for location 2 - 25 sessions). | 2.85 hours of video footage. | Varying scenes (e.g. weather conditions, time of day) and participants' appearance (e.g. wearing masks, hat, glasses, clothes) and actions (e.g. looking at phone, talking, bowing head). | No annotation. | 2048p resolution, 30 fps, synchronized camera streams.",
      "yearOfCollection": "2023|2024"
    },
    {
      "id": "6a998836e6ee6e81af9b631f",
      "collection": "image-video-sets",
      "title": "English (United States) street signs",
      "slug": "img-ocr-use-street001",
      "url": "/data-catalog/image-video-sets/img-ocr-use-street001",
      "featured": false,
      "datasetId": "IMG_OCR_USE_STREET001",
      "category": "OCR",
      "domain": [
        "Signage / OCR"
      ],
      "recordingDevice": "Camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [
        "Resolution: Fixed width of 1,080px",
        "height varies across 12 distinct values from 556 to 2,211px (556, 558, 650, 651, 810, 1440, 1794, 2084, 2085, 2088, 2094, 2211). Most cluster in the 1440–2211px range (standard portrait video/photo frames)",
        "the shorter heights (556–810px) likely reflect partial-frame crops or letterboxed clips rather than full portrait frames."
      ],
      "volume": "669 images",
      "unitType": "Image",
      "generationSource": "Photographs taken by contributors/field collectors",
      "annotation": [
        "Not specified"
      ],
      "dataFormat": [
        "png"
      ],
      "source": "Appen Global",
      "datasetDescription": "Photographs of street signs, 51% traffic signs and 49% other. English from 18 locales.",
      "yearOfCollection": "2021"
    },
    {
      "id": "6a9988356d858e464b668de7",
      "collection": "image-video-sets",
      "title": "European License Plate Detection Annotations",
      "slug": "license-anno",
      "url": "/data-catalog/image-video-sets/license-anno",
      "featured": false,
      "datasetId": "LICENSE_ANNO",
      "category": "Image and Video Bounding Box Annotations",
      "domain": [
        "Automotive / License Plates"
      ],
      "recordingDevice": "",
      "recordingCondition": "",
      "resolutionPixelDimensions": [],
      "volume": "100,000 bounding boxes",
      "unitType": "Image",
      "generationSource": "Derived from existing public autonomous-driving datasets (KITTI, Cityscapes)",
      "annotation": [
        "Bounding box annotation (100,000 license plate boxes across 38,000 images/video frames), incl. box size/position metadata",
        "annotated by Appen's in-house workforce"
      ],
      "dataFormat": [
        "json"
      ],
      "source": "Appen Global",
      "datasetDescription": "This dataset contains 100,000 license plate bounding box annotations of 38,000 images and video frames from the KITTI and Cityscapes datasets, from Germany, France and Switzerland. Metadata associated with the bounding boxes, of the box size and position distributions, is included. | The source images and video frames cover real world complex scenes in good/median weather conditions, captured over several months (spring, summer, fall), varying scene layouts, backgrounds, and occlusion. |The annotations were carried out by Appen's in-house workforce.",
      "yearOfCollection": "2022"
    },
    {
      "id": "6a998834e924c86953f98de8",
      "collection": "image-video-sets",
      "title": "Handwritten text document OCR",
      "slug": "img-ocr-handwritten",
      "url": "/data-catalog/image-video-sets/img-ocr-handwritten",
      "featured": false,
      "datasetId": "IMG_OCR_Handwritten",
      "category": "Document OCR",
      "domain": [
        "Handwriting / OCR"
      ],
      "recordingDevice": "Camera, scan",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [
        "Resolution: ~90% are 1080px-wide vertical phone video/photo frames (height varies — mostly 1440px, 54.6% of the whole set",
        "also 1794, 2088, 2094, 2211, 2085, 1796, 1792, 810, 1920, 1344). The remaining ~10% is non-video: 2550×3507 document scans (Letter-width/A4-height ratio, ~5.8%), 3456×4608 phone camera photos (4:3 sensor, ~3.0%), and a handful of odd one-off resolutions (~1%)."
      ],
      "volume": "663 images",
      "unitType": "Image",
      "generationSource": "Scanned/photographed real documents",
      "annotation": [
        "Not specified"
      ],
      "dataFormat": [
        "png"
      ],
      "source": "Appen Global",
      "datasetDescription": "Scans and photographs of handwritten forms and handwritten documents. 3 Languages: 11% Arabic, 60% English, 29% Russian",
      "yearOfCollection": "2021"
    },
    {
      "id": "6a99883384235eb50a0f7357",
      "collection": "image-video-sets",
      "title": "Business-to-business printed text document OCR",
      "slug": "img-ocr-b2b",
      "url": "/data-catalog/image-video-sets/img-ocr-b2b",
      "featured": false,
      "datasetId": "IMG_OCR_B2B",
      "category": "Document OCR",
      "domain": [
        "Business Documents / OCR"
      ],
      "recordingDevice": "Camera, scan",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [
        "Resolution: Mixed corpus — no single dominant resolution. ~52% document/page scans (A4, Letter/Legal, and mixed-crop ratios, ~150–300dpi)",
        "~19% phone camera photos (native 4:3 sensor, e.g. 4032×3024)",
        "~17% vertical 1080px-wide phone video/photo frames (variable height)",
        "~12% other (odd aspect ratios, panoramas, oversized scans up to 10,300×14,040, and small thumbnails)."
      ],
      "volume": "5,838 documents",
      "unitType": "Image",
      "generationSource": "Scanned/photographed real documents",
      "annotation": [
        "Not specified"
      ],
      "dataFormat": [
        "png"
      ],
      "source": "Appen Global",
      "datasetDescription": "Scans and photographs of business-to-business documents containing printed text. 38% Premium Quality images in 10 languages, 25 countries, including Purchase Order, Payment Advice or Remittance Advice, Order Confirmation and Delivery note. 64% Standard Quality images in various challenging conditions in 11 languages, 34 countries, in a wider range of categories including Complaints or Return, Delivery advice, Delivery note, Dunning, Goods receipt, Invoice, Offer, Order confirmation, Pay slip, Payment Advice or Remittance Advice, Purchase Order, Receipt, and Supplier load",
      "yearOfCollection": "2021"
    },
    {
      "id": "6a99883289ead58b4c209300",
      "collection": "image-video-sets",
      "title": "Object Image Collection",
      "slug": "img-tag-cn",
      "url": "/data-catalog/image-video-sets/img-tag-cn",
      "featured": false,
      "datasetId": "IMG_TAG_CN",
      "category": "Image recognition",
      "domain": [
        "Airport",
        "Beach",
        "Car",
        "Clothing store",
        "Crowd",
        "Department store",
        "Desert",
        "Electrical equipment",
        "Gym",
        "Handbag",
        "KTV",
        "Market",
        "Mountain area",
        "Museum",
        "Night view",
        "Office",
        "Pet",
        "Playground",
        "Restaurant",
        "Sandbeach",
        "Scenic spot",
        "Sea",
        "Ship",
        "Sky",
        "Snow Mountain",
        "Snow scene",
        "Sports equipment",
        "Store",
        "Tree",
        "Window scenery",
        "Zoo"
      ],
      "recordingDevice": "Mobile phone and camera",
      "recordingCondition": "Mixed lighting conditions",
      "resolutionPixelDimensions": [
        "Resolution: Phone-native corpus. ~53% 1080-edge video/photo frames (mostly landscape 1440×1080)",
        "~31% phone camera photos (native 4:3 sensor, e.g. 4032×3024, 3264×2448)",
        "remaining ~16% is a long tail — small thumbnails (~5%), 16:9 frames (~2%), square 1:1 crops (~2%), oversized images up to 8000×6000 (~1%), panoramas (~1%), and miscellaneous odd-aspect crops (~4%)."
      ],
      "volume": "1832 images",
      "unitType": "Image",
      "generationSource": "Collected/curated photographs across multiple scene categories",
      "annotation": [
        "Text description labelling"
      ],
      "dataFormat": [
        "jpg",
        "json"
      ],
      "source": "Appen China; Appen Global",
      "datasetDescription": "Multi-scene picture sample library of 1832 images with English text descriptions. Categories: Airport, Beach, Car, Clothing store, Crowd, Department store, Desert, Electrical equipment, Gym, Handbag, KTV, Market, Mountain area, Museum, Night view, Office, Pet, Playground, Restaurant, Sandbeach, Scenic spot, Sea, Ship, Sky, Snow Mountain, Snow scene, Sports equipment, Store, Tree, Window scenery, Zoo",
      "yearOfCollection": "2020|2024"
    },
    {
      "id": "6a998855a24dcd7124d705a2",
      "collection": "other-sets",
      "title": "English (United States) Text message conversations",
      "slug": "use-sms003",
      "url": "/data-catalog/other-sets/use-sms003",
      "featured": false,
      "datasetId": "USE_SMS003",
      "languages": [
        "English"
      ],
      "category": "Text messages",
      "domainSubjectArea": "Past Events, Hobbies, World Affairs, Climate Change, Politics, Travel, Finance/Economics, Sports, Arts and Entertainment, Work Life, Music (plus naturally occurring topics: Conspiracy Theories, Finance, Food & Drink, Health & Fitness, Household/Logistics, Pets, Relationships, Shopping, Weather)",
      "dataCoveragePeriod": [
        "2024"
      ],
      "qtyAvailable": "101 conversations",
      "generationSource": "Real SMS/WhatsApp text conversations between participants",
      "annotation": "Topic labelling",
      "licenseType": "",
      "dataFormat": [
        "tsv"
      ],
      "refreshCadence": "Static",
      "source": "Appen Global",
      "datasetDescription": "Short WhatsApp and SMS text message conversations (20-400 words), labelled for topic",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a99885417854c543f941fc4",
      "collection": "other-sets",
      "title": "English (United States) Chatbot conversations",
      "slug": "use-llm003",
      "url": "/data-catalog/other-sets/use-llm003",
      "featured": false,
      "datasetId": "USE_LLM003",
      "languages": [
        "English"
      ],
      "category": "LLM training",
      "domainSubjectArea": "financial, retail, entertainment, IT",
      "dataCoveragePeriod": [
        "2024"
      ],
      "qtyAvailable": "1800 prompts",
      "generationSource": "Collected by querying live customer service chatbots on company websites",
      "annotation": "Not specified",
      "licenseType": "",
      "dataFormat": [
        "csv"
      ],
      "refreshCadence": "Static",
      "source": "Appen Global",
      "datasetDescription": "Real-world conversations between a user and a chatbot. Conversations were collected by asking questions of customer service chatbots on websites from a variety of industries to trigger 3 different conversation formats: chatbot input, chatbot solutions and follow up, solution instructions. Domains include: financial, retail, entertainment, IT",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a998853e924c86953f9a26f",
      "collection": "other-sets",
      "title": "English (United States) Adversarial prompts for LLM red teaming",
      "slug": "use-llm002",
      "url": "/data-catalog/other-sets/use-llm002",
      "featured": false,
      "datasetId": "USE_LLM002",
      "languages": [
        "English"
      ],
      "category": "LLM training",
      "domainSubjectArea": "LLM Safety / Red-teaming",
      "dataCoveragePeriod": [
        "2024",
        "2025"
      ],
      "qtyAvailable": "1000 prompts",
      "generationSource": "Adversarial prompts authored/tested against LLMs (red-teaming)",
      "annotation": "Harm category and prompt-target labelling; harmful/harmless response labelling",
      "licenseType": "",
      "dataFormat": [
        "csv"
      ],
      "refreshCadence": "Static",
      "source": "Appen Global",
      "datasetDescription": "Prompts employing a variety of red-teaming attack techniques tested against 4 leading LLMs (Deepseek, Claude 3.7, LLAMA and GPT 4o) and labelled according to whether they received a harmful or harmless response. Prompts are annotated for harm category, and prompt target where applicable. This dataset corresponds to the research paper Adversarial Prompting: Benchmarking Safety in Large Language Models (https://www.appen.com/ebooks/adversarial-prompting).",
      "yearOfCollection": [
        "2024",
        "2025"
      ]
    },
    {
      "id": "6a99885231b4728186af3d67",
      "collection": "other-sets",
      "title": "Chinese and English related texts",
      "slug": "glwb-cn",
      "url": "/data-catalog/other-sets/glwb-cn",
      "featured": false,
      "datasetId": "GLWB_CN",
      "languages": [
        "English",
        "Chinese"
      ],
      "category": "LLM training",
      "domainSubjectArea": "Long-form Books / Literature",
      "dataCoveragePeriod": [],
      "qtyAvailable": "400000 texts",
      "generationSource": "Sourced from publicly available books",
      "annotation": "Not specified",
      "licenseType": "",
      "dataFormat": [
        "json"
      ],
      "refreshCadence": "Static",
      "source": "Appen China",
      "datasetDescription": "This data set contains long article content in English and Chinese, sourced from publicly available books including title, author and language metadata.",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a998851bc894a1ebfd46c11",
      "collection": "other-sets",
      "title": "Code Q&A Dataset",
      "slug": "dm-cnrd",
      "url": "/data-catalog/other-sets/dm-cnrd",
      "featured": false,
      "datasetId": "DM_CNRD",
      "languages": [
        "English"
      ],
      "category": "LLM training",
      "domainSubjectArea": "computer, scientific research technology, wholesale and retail, finance, entertainment and other industries",
      "dataCoveragePeriod": [],
      "qtyAvailable": "6 million pairs",
      "generationSource": "Sourced via web-spidering",
      "annotation": "Not specified",
      "licenseType": "",
      "dataFormat": [
        "json"
      ],
      "refreshCadence": "Static",
      "source": "Appen China",
      "datasetDescription": "This is a text dataset of coding questions and answers in English, sourced through web-spidering with subsequent clean up and filtering. Programming languages include: JavaScript, Python, Java, C#, PHP, C++, SQL, R, C, Swift. Topics include: computer, scientific research technology, wholesale and retail, finance, entertainment and other industries",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a99885113e9a932dc476d12",
      "collection": "other-sets",
      "title": "Chinese multidisciplinary test questions corpus",
      "slug": "mtq-cn",
      "url": "/data-catalog/other-sets/mtq-cn",
      "featured": false,
      "datasetId": "MTQ_CN",
      "languages": [
        "Chinese"
      ],
      "category": "LLM training",
      "domainSubjectArea": "Geography, Chemistry, History, Biology, Math, Physics, Chinese language, Political science (school exam questions)",
      "dataCoveragePeriod": [
        "2024"
      ],
      "qtyAvailable": "319970 sentences",
      "generationSource": "Compiled exam-style question/answer sets",
      "annotation": "Not specified",
      "licenseType": "",
      "dataFormat": [
        "json"
      ],
      "refreshCadence": "Static",
      "source": "Appen China",
      "datasetDescription": "Corpus containing 8 sections of middle-high school prompt response pairs with metadata Subject, Grade, Knowledge Area, Question Type, Question, Answer, Difficulty. Question categories included are:|Geography - 30k sentences (DLT001_CN);|Chemistry - 40k sentences (HXT001_CN);|History - 40k sentences (LST001_CN:);|Biology - 40k sentences (SWT001_CN);|Math - 30k sentences (SXT001_CN);|Physics - 40k sentences (WLT001_CN);|Chinese language - 10k sentences (YWT001_CN);|Political - 40k sentences (ZZT001_CN)",
      "yearOfCollection": [
        "2024"
      ]
    },
    {
      "id": "6a99885013e9a932dc476be1",
      "collection": "other-sets",
      "title": "Chinese instruction set sentence corpus",
      "slug": "zlj-corpus-cn",
      "url": "/data-catalog/other-sets/zlj-corpus-cn",
      "featured": false,
      "datasetId": "ZLJ_corpus_CN",
      "languages": [
        "Chinese"
      ],
      "category": "LLM training",
      "domainSubjectArea": "LLM Instruction Tuning (Q&A, dialogue, reasoning, code, brainstorming, rewriting, safety, roleplay, long-form generation)",
      "dataCoveragePeriod": [
        "2023"
      ],
      "qtyAvailable": "200000 sentences",
      "generationSource": "Compiled/authored LLM instruction-tuning prompt-response pairs",
      "annotation": "Section/task-type tagging across 10 instruction categories",
      "licenseType": "",
      "dataFormat": [
        "txt"
      ],
      "refreshCadence": "Static",
      "source": "Appen China",
      "datasetDescription": "Sentence corpus containing 10 sections:|Question and answer class instruction set ( ZLCWD_corpus_CN);|Multi-turn dialogue instruction set prompt-response pairs (ZLCDH_corpus_CN);|Logical reasoning instruction set prompt (Topic) - response (Reasoning) pairs (ZLCLJ_corpus_CN);|Programming code language instruction set prompt-response pairs, e.g. python (ZLCDM_corpus_CN);|Brainstorming instruction set question-answer pairs (ZLCTN_corpus_CN);|Text rewriting-instruction set original-rewritten pairs (ZLCGX_corpus_CN);|Text to reply to security - command set (ZLCAQ_corpus_CN);|Roleplay instruction set prompt-response pairs (ZLCJS_corpus_CN);|Long text-instruction set prompt-response pairs (ZLCCWB_corpus_CN);|Text generation instruction set prompt-response pairs (ZLCWB_corpus_CN)",
      "yearOfCollection": [
        "2023"
      ]
    },
    {
      "id": "6a99884f834e4fbc0a9226f0",
      "collection": "other-sets",
      "title": "Chinese command and control prompt response corpus",
      "slug": "dsdh-corpus-cn",
      "url": "/data-catalog/other-sets/dsdh-corpus-cn",
      "featured": false,
      "datasetId": "DSDH_corpus_CN",
      "languages": [
        "Chinese"
      ],
      "category": "LLM training",
      "domainSubjectArea": "Virtual Assistant / Device Control",
      "dataCoveragePeriod": [
        "2023"
      ],
      "qtyAvailable": "20000 sentences",
      "generationSource": "Compiled app command and Q&A prompt-response pairs",
      "annotation": "Category and intent tagging",
      "licenseType": "",
      "dataFormat": [
        "txt"
      ],
      "refreshCadence": "Static",
      "source": "Appen China",
      "datasetDescription": "App Commands, Question & response pairs, tagged with categories and intents, for use with TV player controls, lifestyle services, and device control.",
      "yearOfCollection": [
        "2023"
      ]
    },
    {
      "id": "6a99884e946e817c7d63f3e8",
      "collection": "other-sets",
      "title": "Chinese news text summaries corpus",
      "slug": "dmxwb-corpus-cn",
      "url": "/data-catalog/other-sets/dmxwb-corpus-cn",
      "featured": false,
      "datasetId": "DMXWB_corpus_CN",
      "languages": [
        "Chinese"
      ],
      "category": "LLM training",
      "domainSubjectArea": "Finance and economics, Lottery ticket, House property, Share certificate, Home furnishings, Education, Science & Technology, Society & people's livelihood, Fashion, Politics, Sports activities, Constellation, Game, Entertainment",
      "dataCoveragePeriod": [],
      "qtyAvailable": "20000 summaries",
      "generationSource": "Summarised/curated from published news articles",
      "annotation": "Domain tagging (15 news domains)",
      "licenseType": "",
      "dataFormat": [
        "xls"
      ],
      "refreshCadence": "Static",
      "source": "Appen China",
      "datasetDescription": "Summaries of main events and themes from news data in 15 domains (Finance and economics, Lottery ticket, House property, Share certificate, Home furnishings, Education, Science & Technology, Society & people's livelihood, Fashion, Politics, Sports activities, Constellation, Game, Entertainment)",
      "yearOfCollection": [
        "2023"
      ]
    },
    {
      "id": "6a99884b31d6f8d8f3d0f4c0",
      "collection": "other-sets",
      "title": "CAD Files",
      "slug": "cad-001",
      "url": "/data-catalog/other-sets/cad-001",
      "featured": false,
      "datasetId": "CAD_001",
      "languages": [],
      "category": "2D/3D CAD",
      "domainSubjectArea": "Robotics, Electrical, Mechanical, Architectural, 3D Printing, Aerospace, Automotive",
      "dataCoveragePeriod": [
        "2018 - 2026"
      ],
      "qtyAvailable": "1200000",
      "generationSource": "Human-Generated (Real Enterprise Usage)",
      "annotation": "Real-World Capture / Expert Review",
      "licenseType": "Perpetual — Non-Exclusive",
      "dataFormat": [],
      "refreshCadence": "Monthly",
      "source": "Third Party Vendor",
      "datasetDescription": "CAD files from a variety of fields - Robotics, Engineering, Electrical, Architecture and more - including multi-part projects",
      "yearOfCollection": [
        "2018 - 2026"
      ]
    },
    {
      "id": "6a99884a13e9a932dc47688e",
      "collection": "other-sets",
      "title": "PCB Schematics",
      "slug": "schem-001",
      "url": "/data-catalog/other-sets/schem-001",
      "featured": false,
      "datasetId": "SCHEM_001",
      "languages": [],
      "category": "2D/3D CAD + Schematics and Project Files + SVG Renders",
      "domainSubjectArea": "Electronics",
      "dataCoveragePeriod": [],
      "qtyAvailable": "25000",
      "generationSource": "Human-Generated (Real Enterprise Usage)",
      "annotation": "Real-World Capture / Expert Review",
      "licenseType": "Perpetual — Non-Exclusive",
      "dataFormat": [],
      "refreshCadence": "Monthly",
      "source": "Third Party Vendor",
      "datasetDescription": "real‑world hardware designs—schematics,\nlayouts, BoMs (Bills of Materials), and matching firmware—to empower multimodal models that\ngenerate, debug, and optimize electronic products.",
      "yearOfCollection": []
    },
    {
      "id": "6a9988498dcd14d10a92cafe",
      "collection": "other-sets",
      "title": "Enterprise Agentic Trajectories",
      "slug": "traject-agentic-001",
      "url": "/data-catalog/other-sets/traject-agentic-001",
      "featured": false,
      "datasetId": "TRAJECT_AGENTIC_001",
      "languages": [
        "English"
      ],
      "category": "Agentic / Multi-Turn Trajectories",
      "domainSubjectArea": "Legal, Finance, HR (multi-role enterprise personas)",
      "dataCoveragePeriod": [
        "July 2026"
      ],
      "qtyAvailable": "3000",
      "generationSource": "Human-Generated (Real Enterprise Usage)",
      "annotation": "Real-World Capture / Expert Review",
      "licenseType": "Perpetual — Non-Exclusive",
      "dataFormat": [],
      "refreshCadence": "Monthly",
      "source": "Third Party Vendor",
      "datasetDescription": "Trajectories sourced from real enterprises leveraging ChatGPT Work or Claude Cowork. Real prompts and real trajectories/tasks from real personas across different roles in organizations — Legal, Finance, HR. Entire working folders available for a portion of the dataset.",
      "yearOfCollection": [
        "2026"
      ]
    },
    {
      "id": "6a99884889ead58b4c209c0b",
      "collection": "other-sets",
      "title": "MRI / CTI / X-Ray Scans with Doctor Notes",
      "slug": "med-scans-001",
      "url": "/data-catalog/other-sets/med-scans-001",
      "featured": false,
      "datasetId": "MED_SCANS_001",
      "languages": [
        "English"
      ],
      "category": "Image + Clinical Text",
      "domainSubjectArea": "Healthcare / Clinical Documentation",
      "dataCoveragePeriod": [
        "2018 - 2025"
      ],
      "qtyAvailable": "",
      "generationSource": "Human-Generated",
      "annotation": "Expert Authoring & Verification (Visual + Text)",
      "licenseType": "Perpetual — Non-Exclusive",
      "dataFormat": [],
      "refreshCadence": "Quaterly",
      "source": "Third Party Vendor",
      "datasetDescription": "Original scans in DICOM format with doctor notes and annotations",
      "yearOfCollection": [
        "2018 - 2025"
      ]
    },
    {
      "id": "6a9988478dcd14d10a92c992",
      "collection": "other-sets",
      "title": "Human-Created Infographics (Multi-Category)",
      "slug": "infograph-001",
      "url": "/data-catalog/other-sets/infograph-001",
      "featured": false,
      "datasetId": "INFOGRAPH_001",
      "languages": [
        "English"
      ],
      "category": "Image / Visual Design",
      "domainSubjectArea": "Multi-Category (Business, Health, Education, Finance, etc.)",
      "dataCoveragePeriod": [
        "2018 - 2025"
      ],
      "qtyAvailable": "1,200,000 images",
      "generationSource": "Human-Generated (Original Designer-Created Infographics)",
      "annotation": "",
      "licenseType": "Perpetual — Non-Exclusive",
      "dataFormat": [],
      "refreshCadence": "Quaterly",
      "source": "Third Party Vendor",
      "datasetDescription": "Original, human-designed infographics spanning multiple categories — business, health, education, finance, lifestyle, and more. Suited for visual reasoning, layout understanding, and multimodal document AI training.",
      "yearOfCollection": [
        "2018 - 2025"
      ]
    },
    {
      "id": "6ac65f6ca67a8c94ffe701b2",
      "collection": "location-data",
      "title": "Points of Interest (POI) Data",
      "slug": "location-poi-global",
      "url": "/data-catalog/location-data/location-poi-global",
      "featured": false,
      "datasetId": "LOCATION_POI_GLOBAL",
      "category": "Points of Interest (POI) Data",
      "qtyAvailable": "300 million+ places",
      "geographicCoverage": "200+ countries and territories",
      "coverageLevel": "Global",
      "numberOfAttributes": "50+",
      "attributes": [
        "Location ID",
        "Name",
        "Website",
        "Brand ID",
        "Phone",
        "Street Address",
        "City",
        "State",
        "Country Code",
        "ZIP",
        "Geohash",
        "Specialty",
        "Category"
      ],
      "dataFormat": [
        "CSV",
        "XLS",
        "JSON",
        "Parquet"
      ],
      "licenseType": [
        "One-off",
        "On-demand",
        "Annual subscription",
        "Data enrichment"
      ],
      "refreshCadence": [
        "Yearly",
        "On-demand"
      ],
      "yearOfCollection": [],
      "dataCoveragePeriod": [],
      "languages": [],
      "generationSource": "Quadrant",
      "annotation": "",
      "source": "Quadrant",
      "privacyPolicyUrl": "https://www.quadrant.io/privacy-policy",
      "datasetDescription": "Quadrant (an Appen Company) provides validated, structured Points of Interest (POI) data covering more than 300 million places across 200+ countries and territories. Our global POI database helps organizations understand the places, businesses, and locations that make up markets around the world, providing a reliable foundation for location intelligence, analytics, AI, and business intelligence.\n\nThe dataset contains 50+ attributes covering key information about each place.\n\nOur POI data is quality controlled and designed to support reliable location intelligence and analysis. Quadrant provides flexible delivery and commercial options, including one off datasets, on demand data, annual subscriptions, and data enrichment services for existing databases.\n\nKey benefits include:\n\n• 300 million+ places globally\n• Coverage across 200+ countries and territories\n• 50+ POI attributes\n• Validated and structured POI data\n• Broad category coverage, excluding sensitive locations\n• Flexible geographic coverage\n• Data available in CSV, XLS, JSON, and Parquet formats\n• Yearly or on demand refresh options\n• One off, on demand, annual subscription, and data enrichment options\n• Tailored datasets aligned with your business requirements\n• Expert technical support from our in house data specialists\n• Quality controlled data designed for analytics and AI"
    },
    {
      "id": "6ac65f69d5858b1b317ac903",
      "collection": "location-data",
      "title": "United States Mobile Location Data",
      "slug": "location-mobile-us",
      "url": "/data-catalog/location-data/location-mobile-us",
      "featured": false,
      "datasetId": "LOCATION_MOBILE_US",
      "category": "Mobile GPS Location Data",
      "qtyAvailable": "5 billion+ daily location events",
      "geographicCoverage": "United States",
      "coverageLevel": "Country",
      "numberOfAttributes": "17",
      "attributes": [
        "device_id",
        "id_type",
        "latitude",
        "longitude",
        "horizontal_accuracy",
        "timestamp",
        "ip_address",
        "device_os",
        "user_agent",
        "country",
        "source_id",
        "publisher_id",
        "geohash",
        "H3",
        "consent",
        "device_manufacturer",
        "device_model"
      ],
      "dataFormat": [
        "CSV",
        "XLS",
        "JSON",
        "Parquet"
      ],
      "licenseType": [
        "One-off",
        "On-demand",
        "Annual subscription"
      ],
      "refreshCadence": [
        "Daily"
      ],
      "yearOfCollection": [
        "2022",
        "2023",
        "2024",
        "2025",
        "2026"
      ],
      "dataCoveragePeriod": [
        "2022",
        "2023",
        "2024",
        "2025",
        "2026"
      ],
      "languages": [],
      "generationSource": "Trusted industry developer partners and a broad network of apps. Data is ethically sourced from opted-in, first-party devices.",
      "annotation": "",
      "source": "Quadrant",
      "privacyPolicyUrl": "https://www.quadrant.io/privacy-policy",
      "datasetDescription": "Mobile location data for the United States, with 5 billion+ daily location events from opted-in devices.\n\nQuadrant (an Appen Company) provides privacy first location data and foot traffic data for AI, analytics, and business intelligence. Our enterprise grade datasets helps organizations uncover meaningful geographic patterns across industries, including retail, commercial real estate, transportation, urban planning, financial services, market research, tourism, and consumer insights. Whether you are evaluating site performance, measuring market activity, building predictive models, or analyzing movement trends, our data provides a trusted foundation for scalable analysis.\n\nQuadrant location data contains 17 attributes covering device, location, time, source, consent, and geographic information.\n\nQuadrant offers flexible geographic coverage that adapts to your business requirements. We are not limited to predefined geographic boundaries, so we can support reporting and analysis at the city, county, state, regional, and national levels, making it easier to analyze points of interest, compare markets, evaluate trade areas, and understand mobility across locations.\n\nKey benefits include:\n\n• United States coverage with 5 billion+ daily location events\n• Privacy first and quality controlled location data\n• AI ready and analytics friendly datasets\n• Flexible geographic reporting at the city, county, state, regional, and national levels\n• Historical data available from 2022 onwards\n• Daily data refresh\n• Tailored datasets aligned with your business requirements\n• Expert technical support from our in house data specialists\n• In house quality assurance and quality flags for deduplication, one ping devices, teleportation, and more\n• Flexible commercial models including one off, on demand, and annual subscriptions\n• Data available in CSV, XLS, JSON, and Parquet formats"
    },
    {
      "id": "6ac65f67af428ccbf01616ba",
      "collection": "location-data",
      "title": "Mobile Location Data",
      "slug": "location-mobile-global",
      "url": "/data-catalog/location-data/location-mobile-global",
      "featured": false,
      "datasetId": "LOCATION_MOBILE_GLOBAL",
      "category": "Mobile GPS Location Data",
      "qtyAvailable": "50 billion+ daily location events from 1 billion+ opted-in devices",
      "geographicCoverage": "200+ countries and territories",
      "coverageLevel": "Global",
      "numberOfAttributes": "17",
      "attributes": [
        "device_id",
        "id_type",
        "latitude",
        "longitude",
        "horizontal_accuracy",
        "timestamp",
        "ip_address",
        "device_os",
        "user_agent",
        "country",
        "source_id",
        "publisher_id",
        "geohash",
        "H3",
        "consent",
        "device_manufacturer",
        "device_model"
      ],
      "dataFormat": [
        "CSV",
        "XLS",
        "JSON",
        "Parquet"
      ],
      "licenseType": [
        "One-off",
        "On-demand",
        "Annual subscription"
      ],
      "refreshCadence": [
        "Daily"
      ],
      "yearOfCollection": [
        "2022",
        "2023",
        "2024",
        "2025",
        "2026"
      ],
      "dataCoveragePeriod": [
        "2022",
        "2023",
        "2024",
        "2025",
        "2026"
      ],
      "languages": [],
      "generationSource": "Trusted industry developer partners and a broad network of apps. Data is ethically sourced from opted-in, first-party devices.",
      "annotation": "",
      "source": "Quadrant",
      "privacyPolicyUrl": "https://www.quadrant.io/privacy-policy",
      "datasetDescription": "Quadrant (an Appen Company) provides privacy first global location data and foot traffic data for AI, analytics, and business intelligence.\n\nQuadrant provides data for more than 200 countries and territories. Our enterprise grade datasets helps organizations uncover meaningful geographic patterns across industries, including retail, commercial real estate, transportation, urban planning, financial services, market research, tourism, and consumer insights. Whether you are evaluating site performance, measuring market activity, building predictive models, or analyzing movement trends, our data provides a trusted foundation for scalable analysis.\n\nQuadrant location data contains 17 attributes covering device, location, time, source, consent, and geographic information.\n\nQuadrant offers flexible geographic coverage that adapts to your business requirements. We are not limited to predefined geographic boundaries, so we can support reporting and analysis at the city, county, state, regional, and national levels, making it easier to analyze points of interest, compare markets, evaluate trade areas, and understand mobility across locations.\n\nKey benefits include:\n\n• Global coverage across more than 200 countries and territories\n• 1 billion+ opted in devices and 50 billion+ daily global location events\n• Privacy first and quality controlled location data\n• AI ready and analytics friendly datasets\n• Flexible geographic reporting at the city, county, state, regional, and national levels\n• Historical data available from 2022 onwards\n• Daily data refresh\n• Tailored datasets aligned with your business requirements\n• Expert technical support from our in house data specialists\n• In house quality assurance and quality flags for deduplication, one ping devices, teleportation, and more\n• Flexible commercial models including one off, on demand, and annual subscriptions\n• Data available in CSV, XLS, JSON, and Parquet formats"
    }
  ]
}