simulstream.server.speech_processors.remote.http_proxy_speech_processor
Classes
|
HTTP-based proxy implementation of |
- class simulstream.server.speech_processors.remote.http_proxy_speech_processor.HttpProxySpeechProcessor(config)
HTTP-based proxy implementation of
SpeechProcessor.This class does not perform speech processing locally. Instead, it forwards all method calls to a remote speech processor exposed via HTTP, maintaining a dedicated session on the server side.
Each instance of this class corresponds to exactly one remote session.
- clear()
Clear internal states, such as history of cached audio and/or tokens, in preparation for a new stream or conversation.
- end_of_stream() IncrementalOutput
This method is called at the end of audio chunk processing. It can be used to emit hypotheses at the end of the speech to conclude the output.
- Returns:
The incremental output (new and deleted tokens/strings).
- Return type:
- classmethod load_model(config)
Load and initialize the underlying speech model.
- Parameters:
config (SimpleNamespace) – Configuration of the speech processor.
- process_chunk(waveform: float32) IncrementalOutput
Process a chunk of waveform and produce incremental output.
- Parameters:
waveform (np.float32) – A 1D NumPy array of the audio chunk. The array is PCM audio normalized to the range
[-1.0, 1.0]sampled atsimulstream.server.speech_processors.SAMPLE_RATE.- Returns:
The incremental output (new and deleted tokens/strings).
- Return type:
- set_source_language(language)
Set the source language for the speech processor.
- Parameters:
language (str) – Language code (e.g.,
"en","it").
- set_target_language(language)
Set the target language for the speech processor (for translation).
- Parameters:
language (str) – Language code (e.g.,
"en","it").