Maysee

Is there a workaround for this issue? I'm experiencing the same degradation in Japanese whispering audio.

The google.generativeai package should have been removed, in version 1.6.1 the 13-th line of chatbot.py is: https://github.com/zh-plus/openlrc/blob/b78547dfd6688bd1ca03f74f04b7626abf076fa2/openlrc/chatbot.py#L13 , having conflict with your error message: > File "/home/user00/gitspace/video_tools/.venv/lib/python3.10/site-packages/openlrc/chatbot.py", line 13, in...

Is it better to let users choose the VAD model from pyannote VAD or Silero VAD? I get better VAD segments for Chinese & Japanese audios with pyannote than Silero,...

Thank you for this detailed analysis. I do think the structure of openlrc.py is not good - the tight coupling between transcription and translation makes the code less maintainable and...

I think unifying the interfaces would be better than documenting differences. We could change both to Optional[List[dict]] where each dict has start/end times. This would make it possible to use...

There is an existing PR for Faster-Whisper to implement early stopping for non-voice audio, which can be found at https://github.com/SYSTRAN/faster-whisper/pull/1014. Until it's merged, there seems to be no straightforward solution...

It should be fixed with the latest version of Faster-Whisper in v1.6.0. Please reopen it if the issue persists.

Thanks! I've updated this dependency.

This streamlit GUI is not supported now. I'm planing to release a new GUI next month.

You must carefully turn the parameters for Silero VAD-v5 according to your audio. Related issue: #925, #934