/**
 * ONNX weight parser for Kitten TTS.
 * Loads weights from the ONNX protobuf file and dequantizes them for WebGPU.
 */
interface OnnxTensor {
    name: string;
    dims: number[];
    dataType: number;
    rawData: Uint8Array;
}
/**
 * Minimal ONNX protobuf parser.
 * Only parses TensorProto initializers from the model graph.
 * Avoids pulling in a full protobuf library.
 */
export declare class OnnxParser {
    private buffer;
    private view;
    constructor(buffer: ArrayBuffer);
    /** Parse all initializer tensors from the ONNX model. */
    parseInitializers(): Map<string, OnnxTensor>;
    private parseTensorProto;
    private readTag;
    private readVarint;
    private skipField;
    private findField;
}
/**
 * Dequantize INT8 weights to float32.
 * ONNX uses: float_val = (int8_val - zero_point) * scale
 */
export declare function dequantizeInt8(quantized: Int8Array, scale: Float32Array, zeroPoint: Int8Array | null, shape: number[]): Float32Array;
/**
 * Dequantize UINT8 weights to float32.
 */
export declare function dequantizeUint8(quantized: Uint8Array, scale: Float32Array, zeroPoint: Uint8Array | null, shape: number[]): Float32Array;
/**
 * Convert float16 to float32.
 */
export declare function float16ToFloat32(f16: Uint16Array): Float32Array;
/**
 * Parse NPZ file (NumPy compressed archive) for voice embeddings.
 * NPZ is just a ZIP file containing .npy files.
 */
export declare function parseNpz(buffer: ArrayBuffer): Promise<Map<string, {
    shape: number[];
    data: Float32Array;
}>>;
/** Parse a .npy file, handling float32, float16, and int64 dtypes. Always returns Float32Array. */
export declare function parseNpyGeneric(buffer: ArrayBuffer, byteOffset?: number): {
    shape: number[];
    data: Float32Array;
    dtype: string;
};
export {};