MediaPipe Task that performs text proofreading.
Signature:
export declare class TextProofreader extends TaskRunner
Extends: TaskRunner
Methods
| Method | Modifiers | Description |
|---|---|---|
| close() | Closes the TextProofreader and frees resources. | |
| createFromModelBuffer(wasmFileset, modelAssetBuffer, maxNumTokens) | static |
Initializes the Wasm runtime and creates a new text proofreader based on the provided model asset buffer. |
| createFromModelPath(wasmFileset, modelAssetPath, maxNumTokens) | static |
Initializes the Wasm runtime and creates a new text proofreader based on the path to the model asset. |
| createFromOptions(wasmFileset, textProofreaderOptions) | static |
Initializes the Wasm runtime and creates a new text proofreader based on the provided options. |
| proofread(text) | Proofreads the given text. | |
| proofreadStreaming(text, progressListener) | Proofreads the given text and invokes progressListener with each newly generated part of the proofread text.Only one proofread can be in flight at a time. As the underlying Wasm engine runs single-threaded, the calling browser thread remains blocked for the duration of this inference call, and the listener is invoked synchronously. Run the task in a Web Worker to keep the UI thread responsive. |
|
| setOptions(options) | Sets the initial options for the text proofreader. LiteRT LM Tasks do not support updating options after initialization. |
TextProofreader.close()
Closes the TextProofreader and frees resources.
Signature:
close(): void;
Returns:
void
TextProofreader.createFromModelBuffer()
Initializes the Wasm runtime and creates a new text proofreader based on the provided model asset buffer.
Signature:
static createFromModelBuffer(wasmFileset: WasmFileset, modelAssetBuffer: Uint8Array | ReadableStreamDefaultReader, maxNumTokens?: number): Promise<TextProofreader>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. |
| modelAssetBuffer | Uint8Array | ReadableStreamDefaultReader | An array or a stream containing a binary representation of the model. |
| maxNumTokens | number | The maximum number of tokens. |
Returns:
Promise<TextProofreader>
TextProofreader.createFromModelPath()
Initializes the Wasm runtime and creates a new text proofreader based on the path to the model asset.
Signature:
static createFromModelPath(wasmFileset: WasmFileset, modelAssetPath: string, maxNumTokens?: number): Promise<TextProofreader>;
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 model asset. |
| maxNumTokens | number | The maximum number of tokens. |
Returns:
Promise<TextProofreader>
TextProofreader.createFromOptions()
Initializes the Wasm runtime and creates a new text proofreader based on the provided options.
Signature:
static createFromOptions(wasmFileset: WasmFileset, textProofreaderOptions: TextProofreaderOptions): Promise<TextProofreader>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. |
| textProofreaderOptions | TextProofreaderOptions | The options for TextProofreader. |
Returns:
Promise<TextProofreader>
TextProofreader.proofread()
Proofreads the given text.
Signature:
proofread(text: string): TextProofreaderResult;
Parameters
| Parameter | Type | Description |
|---|---|---|
| text | string | The input text to be proofread. The proofread text and the corrections. |
Returns:
TextProofreader.proofreadStreaming()
Proofreads the given text and invokes progressListener with each newly generated part of the proofread text.
Only one proofread can be in flight at a time. As the underlying Wasm engine runs single-threaded, the calling browser thread remains blocked for the duration of this inference call, and the listener is invoked synchronously. Run the task in a Web Worker to keep the UI thread responsive.
Signature:
proofreadStreaming(text: string, progressListener?: ProofreaderProgressListener): Promise<TextProofreaderResult>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| text | string | The input text to be proofread. |
| progressListener | ProofreaderProgressListener | An optional listener that receives each newly generated part of the proofread text. A promise that resolves to the complete proofread text and the corrections. |
Returns:
Promise<TextProofreaderResult>
TextProofreader.setOptions()
Sets the initial options for the text proofreader. LiteRT LM Tasks do not support updating options after initialization.
Signature:
setOptions(options: TextProofreaderOptions): Promise<void>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| options | TextProofreaderOptions | The options for the text proofreader. |
Returns:
Promise<void>