alphacep / vosk-server

WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
Apache License 2.0
896 stars 243 forks source link

The use of webrtc server codes #150

Closed ben-8878 closed 2 years ago

ben-8878 commented 2 years ago

When run the webrtc asr server,get follows errors;

Task exception was never retrieved
future: <Task finished name='Task-33' coro=<KaldiTask.__run_audio_xfer() done, defined at asr_server.py:65> exception=ValueError('Input frame pts 685440 != expected 680640; fix or set to None.')>
Traceback (most recent call last):
  File "asr_server.py", line 69, in __run_audio_xfer
    frame = self.__resampler.resample(frame)
  File "av/audio/resampler.pyx", line 38, in av.audio.resampler.AudioResampler.resample
  File "av/audio/resampler.pyx", line 122, in av.audio.resampler.AudioResampler.resample
ValueError: Input frame pts 685440 != expected 680640; fix or set to None.

Another problem is that after clicking “start button” few seconds,It gets no response,I must restart the ”start button” ,it will work.

nshmyrev commented 2 years ago

Looks like pyav issue:

https://github.com/PyAV-Org/PyAV/issues/281

not sure how to deal with that yet

ben-8878 commented 2 years ago

@nshmyrev another problem is that, I speak nothing,many texts have been recognized, whther i should adjust the silence weight?

nshmyrev commented 2 years ago

You need to report separate issue about this problem