search

sensein / b2aiprep

Apache License 2.0
5 stars 6 forks source link

Add VAD support #10

Open satra opened 7 months ago

satra commented 7 months ago

files could have a lot of silence before or after. Add VAD functionality and add it optionally to the b2ai feature pipeline.

GasserElbanna commented 7 months ago

Some options to consider:

fabiocat93 commented 7 months ago

A simpler implementation for removing silence from start and end of audio files is here:

Also, a note on pyannote-audio: since the last version, it's recommended to use the speaker-diarization pipeline and not the segmentation model because it works better in terms of diarization error rate