transformers.js/pr_1649/en/api/generation/streamers.md

generation/streamers

• generation/streamers
  • .TextStreamer
    • new TextStreamer(tokenizer, options)
    • .put(value)
    • .end()
    • .on_finalized_text(text, stream_end)
  • .WhisperTextStreamer
    • new WhisperTextStreamer(tokenizer, options)
    • .put(value)

---

generation/streamers.TextStreamer

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

Kind: static class of generation/streamers

• .TextStreamer
  • new TextStreamer(tokenizer, options)
  • .put(value)
  • .end()
  • .on_finalized_text(text, stream_end)

---

new TextStreamer(tokenizer, options)

  ParamTypeDefaultDescription




tokenizerPreTrainedTokenizer

optionsObject

[options.skip_prompt]booleanfalseWhether to skip the prompt tokens


[options.skip_special_tokens]booleantrueWhether to skip special tokens when decoding


[options.callback_function]functionFunction to call when a piece of text is ready to display


[options.token_callback_function]functionFunction to call when a new token is generated


[options.decode_kwargs]Object{}Additional keyword arguments to pass to the tokenizer's decode method

  

---

textStreamer.put(value)

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

Kind: instance method of TextStreamer

  ParamType




valueArray
  

---

textStreamer.end()

Flushes any remaining cache and prints a newline to stdout.

Kind: instance method of TextStreamer

---

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 TextStreamer

  ParamType




textstring

stream_endboolean
  

---

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 generation/streamers

• .WhisperTextStreamer
  • new WhisperTextStreamer(tokenizer, options)
  • .put(value)

---

new WhisperTextStreamer(tokenizer, options)

  ParamTypeDefaultDescription




tokenizerWhisperTokenizer

optionsObject

[options.skip_prompt]booleanfalseWhether to skip the prompt tokens


[options.callback_function]functionFunction to call when a piece of text is ready to display


[options.token_callback_function]functionFunction to call when a new token is generated


[options.on_chunk_start]functionFunction to call when a new chunk starts


[options.on_chunk_end]functionFunction to call when a chunk ends


[options.on_finalize]functionFunction to call when the stream is finalized


[options.time_precision]number0.02Precision of the timestamps


[options.skip_special_tokens]booleantrueWhether to skip special tokens when decoding


[options.decode_kwargs]Object{}Additional keyword arguments to pass to the tokenizer's decode method

  

---

whisperTextStreamer.put(value)

Kind: instance method of WhisperTextStreamer

  ParamType




valueArray
  

---