transformers.js/pr_1452/en/api/generation/streamers.md

# generation/streamers


* [generation/streamers](#module_generation/streamers)
    * [.TextStreamer](#module_generation/streamers.TextStreamer)
        * [`new TextStreamer(tokenizer, options)`](#new_module_generation/streamers.TextStreamer_new)
        * [`.put(value)`](#module_generation/streamers.TextStreamer+put)
        * [`.end()`](#module_generation/streamers.TextStreamer+end)
        * [`.on_finalized_text(text, stream_end)`](#module_generation/streamers.TextStreamer+on_finalized_text)
    * [.WhisperTextStreamer](#module_generation/streamers.WhisperTextStreamer)
        * [`new WhisperTextStreamer(tokenizer, options)`](#new_module_generation/streamers.WhisperTextStreamer_new)
        * [`.put(value)`](#module_generation/streamers.WhisperTextStreamer+put)


* * *

<a id="module_generation/streamers.TextStreamer" class="group"></a>

## generation/streamers.TextStreamer

Simple text streamer that prints the token(s) to stdout as soon as entire words are formed.

**Kind**: static class of [<code>generation/streamers</code>](#module_generation/streamers)  

* [.TextStreamer](#module_generation/streamers.TextStreamer)
    * [`new TextStreamer(tokenizer, options)`](#new_module_generation/streamers.TextStreamer_new)
    * [`.put(value)`](#module_generation/streamers.TextStreamer+put)
    * [`.end()`](#module_generation/streamers.TextStreamer+end)
    * [`.on_finalized_text(text, stream_end)`](#module_generation/streamers.TextStreamer+on_finalized_text)


* * *

<a id="new_module_generation/streamers.TextStreamer_new" class="group"></a>

### `new TextStreamer(tokenizer, options)`

<table>
  <thead>
    <tr>
      <th>Param</th><th>Type</th><th>Default</th><th>Description</th>
    </tr>
  </thead>
  <tbody>
<tr>
    <td>tokenizer</td><td><code>*</code></td><td></td><td></td>
    </tr><tr>
    <td>options</td><td><code>Object</code></td><td></td><td></td>
    </tr><tr>
    <td>[options.skip_prompt]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether to skip the prompt tokens</p>
</td>
    </tr><tr>
    <td>[options.skip_special_tokens]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to skip special tokens when decoding</p>
</td>
    </tr><tr>
    <td>[options.callback_function]</td><td><code>function</code></td><td><code></code></td><td><p>Function to call when a piece of text is ready to display</p>
</td>
    </tr><tr>
    <td>[options.token_callback_function]</td><td><code>function</code></td><td><code></code></td><td><p>Function to call when a new token is generated</p>
</td>
    </tr><tr>
    <td>[options.decode_kwargs]</td><td><code>Object</code></td><td><code>{}</code></td><td><p>Additional keyword arguments to pass to the tokenizer&#39;s decode method</p>
</td>
    </tr>  </tbody>
</table>


* * *

<a id="module_generation/streamers.TextStreamer+put" class="group"></a>

### `textStreamer.put(value)`

Receives tokens, decodes them, and prints them to stdout as soon as they form entire words.

**Kind**: instance method of [<code>TextStreamer</code>](#module_generation/streamers.TextStreamer)  
<table>
  <thead>
    <tr>
      <th>Param</th><th>Type</th>
    </tr>
  </thead>
  <tbody>
<tr>
    <td>value</td><td><code>Array.&lt;Array&lt;bigint&gt;&gt;</code></td>
    </tr>  </tbody>
</table>


* * *

<a id="module_generation/streamers.TextStreamer+end" class="group"></a>

### `textStreamer.end()`

Flushes any remaining cache and prints a newline to stdout.

**Kind**: instance method of [<code>TextStreamer</code>](#module_generation/streamers.TextStreamer)  

* * *

<a id="module_generation/streamers.TextStreamer+on_finalized_text" class="group"></a>

### `textStreamer.on_finalized_text(text, stream_end)`

Prints the new text to stdout. If the stream is ending, also prints a newline.

**Kind**: instance method of [<code>TextStreamer</code>](#module_generation/streamers.TextStreamer)  
<table>
  <thead>
    <tr>
      <th>Param</th><th>Type</th>
    </tr>
  </thead>
  <tbody>
<tr>
    <td>text</td><td><code>string</code></td>
    </tr><tr>
    <td>stream_end</td><td><code>boolean</code></td>
    </tr>  </tbody>
</table>


* * *

<a id="module_generation/streamers.WhisperTextStreamer" class="group"></a>

## generation/streamers.WhisperTextStreamer

Utility class to handle streaming of tokens generated by whisper speech-to-text models.
Callback functions are invoked when each of the following events occur:
 - A new chunk starts (on_chunk_start)
 - A new token is generated (callback_function)
 - A chunk ends (on_chunk_end)
 - The stream is finalized (on_finalize)

**Kind**: static class of [<code>generation/streamers</code>](#module_generation/streamers)  

* [.WhisperTextStreamer](#module_generation/streamers.WhisperTextStreamer)
    * [`new WhisperTextStreamer(tokenizer, options)`](#new_module_generation/streamers.WhisperTextStreamer_new)
    * [`.put(value)`](#module_generation/streamers.WhisperTextStreamer+put)


* * *

<a id="new_module_generation/streamers.WhisperTextStreamer_new" class="group"></a>

### `new WhisperTextStreamer(tokenizer, options)`

<table>
  <thead>
    <tr>
      <th>Param</th><th>Type</th><th>Default</th><th>Description</th>
    </tr>
  </thead>
  <tbody>
<tr>
    <td>tokenizer</td><td><code>*</code></td><td></td><td></td>
    </tr><tr>
    <td>options</td><td><code>Object</code></td><td></td><td></td>
    </tr><tr>
    <td>[options.skip_prompt]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether to skip the prompt tokens</p>
</td>
    </tr><tr>
    <td>[options.callback_function]</td><td><code>function</code></td><td><code></code></td><td><p>Function to call when a piece of text is ready to display</p>
</td>
    </tr><tr>
    <td>[options.token_callback_function]</td><td><code>function</code></td><td><code></code></td><td><p>Function to call when a new token is generated</p>
</td>
    </tr><tr>
    <td>[options.on_chunk_start]</td><td><code>function</code></td><td><code></code></td><td><p>Function to call when a new chunk starts</p>
</td>
    </tr><tr>
    <td>[options.on_chunk_end]</td><td><code>function</code></td><td><code></code></td><td><p>Function to call when a chunk ends</p>
</td>
    </tr><tr>
    <td>[options.on_finalize]</td><td><code>function</code></td><td><code></code></td><td><p>Function to call when the stream is finalized</p>
</td>
    </tr><tr>
    <td>[options.time_precision]</td><td><code>number</code></td><td><code>0.02</code></td><td><p>Precision of the timestamps</p>
</td>
    </tr><tr>
    <td>[options.skip_special_tokens]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to skip special tokens when decoding</p>
</td>
    </tr><tr>
    <td>[options.decode_kwargs]</td><td><code>Object</code></td><td><code>{}</code></td><td><p>Additional keyword arguments to pass to the tokenizer&#39;s decode method</p>
</td>
    </tr>  </tbody>
</table>


* * *

<a id="module_generation/streamers.WhisperTextStreamer+put" class="group"></a>

### `whisperTextStreamer.put(value)`

**Kind**: instance method of [<code>WhisperTextStreamer</code>](#module_generation/streamers.WhisperTextStreamer)  
<table>
  <thead>
    <tr>
      <th>Param</th><th>Type</th>
    </tr>
  </thead>
  <tbody>
<tr>
    <td>value</td><td><code>Array.&lt;Array&lt;bigint&gt;&gt;</code></td>
    </tr>  </tbody>
</table>


* * *



<EditOnGithub source="https://github.com/huggingface/transformers.js/blob/main/docs/source/api/generation/streamers.md" />