@picovoice/cheetah-web/dist/types/cheetah.d.ts

Cheetah Speech-to-Text engine for web browsers (via WebAssembly)

import { CheetahModel, CheetahOptions, CheetahTranscript } from './types';
export declare class Cheetah {
    private _module?;
    private readonly _pv_cheetah_process;
    private readonly _pv_cheetah_flush;
    private readonly _pv_cheetah_delete;
    private readonly _version;
    private readonly _sampleRate;
    private readonly _frameLength;
    private readonly _processMutex;
    private readonly _objectAddress;
    private readonly _inputBufferAddress;
    private readonly _isEndpointAddress;
    private readonly _transcriptAddressAddress;
    private readonly _messageStackAddressAddressAddress;
    private readonly _messageStackDepthAddress;
    private static _wasmSimd;
    private static _wasmSimdLib;
    private static _wasmPThread;
    private static _wasmPThreadLib;
    private static _sdk;
    private static _cheetahMutex;
    private readonly _transcriptCallback;
    private readonly _processErrorCallback?;
    private constructor();
    /**
     * Get Cheetah engine version.
     */
    get version(): string;
    /**
     * Get frame length.
     */
    get frameLength(): number;
    /**
     * Get sample rate.
     */
    get sampleRate(): number;
    /**
     * Set base64 wasm file with SIMD feature.
     * @param wasmSimd Base64'd wasm file to use to initialize wasm.
     */
    static setWasmSimd(wasmSimd: string): void;
    /**
     * Set base64 SIMD wasm file in text format.
     * @param wasmSimdLib Base64'd SIMD wasm file in text format.
     */
    static setWasmSimdLib(wasmSimdLib: string): void;
    /**
     * Set base64 wasm file with SIMD and pthread feature.
     * @param wasmPThread Base64'd wasm file to use to initialize wasm.
     */
    static setWasmPThread(wasmPThread: string): void;
    /**
     * Set base64 SIMD and thread wasm file in text format.
     * @param wasmPThreadLib Base64'd wasm file in text format.
     */
    static setWasmPThreadLib(wasmPThreadLib: string): void;
    static setSdk(sdk: string): void;
    /**
     * Creates an instance of the Picovoice Cheetah Speech-to-Text engine.
     * Behind the scenes, it requires the WebAssembly code to load and initialize before
     * it can create an instance.
     *
     * @param accessKey AccessKey obtained from Picovoice Console (https://console.picovoice.ai/)
     * @param transcriptCallback User-defined callback to run after receiving transcript result.
     * @param model Cheetah model options.
     * @param model.base64 The model in base64 string to initialize Cheetah.
     * @param model.publicPath The model path relative to the public directory.
     * @param model.customWritePath Custom path to save the model in storage.
     * Set to a different name to use multiple models across `cheetah` instances.
     * @param model.forceWrite Flag to overwrite the model in storage even if it exists.
     * @param model.version Version of the model file. Increment to update the model file in storage.
     * @param options Optional configuration arguments.
     * @param options.device String representation of the device (e.g., CPU or GPU) to use. If set to `best`, the most
     * suitable device is selected automatically. If set to `gpu`, the engine uses the first available GPU device. To
     * select a specific GPU device, set this argument to `gpu:${GPU_INDEX}`, where `${GPU_INDEX}` is the index of the
     * target GPU. If set to `cpu`, the engine will run on the CPU with the default number of threads. To specify the
     * number of threads, set this argument to `cpu:${NUM_THREADS}`, where `${NUM_THREADS}` is the desired number of
     * threads.
     * @param options.endpointDurationSec Duration of endpoint in seconds. A speech endpoint is detected when there is a
     * chunk of audio (with a duration specified herein) after an utterance without any speech in it. Set to `0`
     * to disable endpoint detection.
     * @param options.enableAutomaticPunctuation Flag to enable automatic punctuation insertion.
     * @param options.processErrorCallback User-defined callback invoked if any error happens
     * while processing the audio stream. Its only input argument is the error message.
     *
     * @returns An instance of the Cheetah engine.
     */
    static create(accessKey: string, transcriptCallback: (cheetahTranscript: CheetahTranscript) => void, model: CheetahModel, options?: CheetahOptions): Promise<Cheetah>;
    static _init(accessKey: string, transcriptCallback: (cheetahTranscript: CheetahTranscript) => void, modelPath: string, options?: CheetahOptions): Promise<Cheetah>;
    /**
     * Processes a frame of audio. The required sample rate can be retrieved from '.sampleRate' and the length
     * of frame (number of audio samples per frame) can be retrieved from '.frameLength' The audio needs to be
     * 16-bit linearly-encoded. Furthermore, the engine operates on single-channel audio.
     *
     * @param pcm A frame of audio with properties described above.
     */
    process(pcm: Int16Array): Promise<void>;
    /**
     * Marks the end of the audio stream, flushes internal state of the object, and returns any remaining transcribed
     * text.
     *
     * @return Any remaining transcribed text. If none is available then an empty string is returned.
     */
    flush(): Promise<void>;
    private cheetahFlush;
    /**
     * Releases resources acquired by WebAssembly module.
     */
    release(): Promise<void>;
    onmessage(e: MessageEvent): Promise<void>;
    private static initWasm;
    /**
     * Lists all available devices that Cheetah can use for inference.
     * Each entry in the list can be the used as the `device` argument for the `.create` method.
     *
     * @returns List of all available devices that Cheetah can use for inference.
     */
    static listAvailableDevices(): Promise<string[]>;
    private static getMessageStack;
    private static wrapAsyncFunction;
}
//# sourceMappingURL=cheetah.d.ts.map