Performs embedding extraction on audio.
Signature:
export declare class AudioEmbedder extends AudioTaskRunner<AudioEmbedderResult[]>
Extends: AudioTaskRunner<AudioEmbedderResult[]>
Methods
| Method | Modifiers | Description |
|---|---|---|
| createFromModelBuffer(wasmFileset, modelAssetBuffer) | static |
Initializes the Wasm runtime and creates a new audio embedder based on the provided model asset buffer. |
| createFromModelPath(wasmFileset, modelAssetPath) | static |
Initializes the Wasm runtime and creates a new audio embedder based on the path to the model asset. |
| createFromOptions(wasmFileset, audioEmbedderOptions) | static |
Initializes the Wasm runtime and creates a new audio embedder from the provided options. |
| embed(audioData, sampleRate) | Performs embeding extraction on the provided audio clip and waits synchronously for the response. | |
| setOptions(options) | Sets new options for the audio embedder.Calling setOptions() with a subset of options only affects those options. You can reset an option back to its default value by explicitly setting it to undefined. |
AudioEmbedder.createFromModelBuffer()
Initializes the Wasm runtime and creates a new audio embedder based on the provided model asset buffer.
Signature:
static createFromModelBuffer(wasmFileset: WasmFileset, modelAssetBuffer: Uint8Array): Promise<AudioEmbedder>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. |
| modelAssetBuffer | Uint8Array | A binary representation of the TFLite model. |
Returns:
Promise<AudioEmbedder>
AudioEmbedder.createFromModelPath()
Initializes the Wasm runtime and creates a new audio embedder based on the path to the model asset.
Signature:
static createFromModelPath(wasmFileset: WasmFileset, modelAssetPath: string): Promise<AudioEmbedder>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. |
| modelAssetPath | string | The path to the TFLite model. |
Returns:
Promise<AudioEmbedder>
AudioEmbedder.createFromOptions()
Initializes the Wasm runtime and creates a new audio embedder from the provided options.
Signature:
static createFromOptions(wasmFileset: WasmFileset, audioEmbedderOptions: AudioEmbedderOptions): Promise<AudioEmbedder>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. |
| audioEmbedderOptions | AudioEmbedderOptions | The options for the audio embedder. Note that either a path to the TFLite model or the model itself needs to be provided (via baseOptions). |
Returns:
Promise<AudioEmbedder>
AudioEmbedder.embed()
Performs embeding extraction on the provided audio clip and waits synchronously for the response.
Signature:
embed(audioData: Float32Array, sampleRate?: number): AudioEmbedderResult[];
Parameters
| Parameter | Type | Description |
|---|---|---|
| audioData | Float32Array | An array of raw audio capture data, like from a call to getChannelData() on an AudioBuffer. |
| sampleRate | number | The sample rate in Hz of the provided audio data. If not set, defaults to the sample rate set via setDefaultSampleRate() or 48000 if no custom default was set. The embedding resuls of the audio |
Returns:
AudioEmbedder.setOptions()
Sets new options for the audio embedder.
Calling setOptions() with a subset of options only affects those options. You can reset an option back to its default value by explicitly setting it to undefined.
Signature:
setOptions(options: AudioEmbedderOptions): Promise<void>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| options | AudioEmbedderOptions | The options for the audio embedder. |
Returns:
Promise<void>