Speech recognition broken down by speakers

#167
by tur0kmag - opened

Is it possible to perform speech recognition broken down by speakers?

tur0kmag changed discussion title from peech recognition broken down by speakers to Speech recognition broken down by speakers

Hi, Do you mean speaker diarization?

I mean, as a result of recognition, I need to get the following:
Speaker 1: Hello. How are you?
Speaker 2: Everything is fine!

I think you should look in to this model https://huggingface.co./pyannote/speaker-diarization.
Because I don't think whisper models alone can be used for this.
https://medium.com/@xriteshsharmax/speaker-diarization-using-whisper-asr-and-pyannote-f0141c85d59a check out this blog.

Sign up or log in to comment