Back
Question
Asked

Help needed - What is the best software to identify different voices?

I use OpenAI Whisper to transcribe voice to text - but I would appreciate if the software could identify and group comments by different voices. Is there any software allowing to identify voices?


I heard you can use pyannote with whisper to do diarization but I've never tried myself. See github.com/Vaibhavs10/insanel…

Reading up on those files, this should actually do the trick - thank you!

I'll report back once I used it. Also, this put me in the right direction as I now "diarisation" or "diarization" if you're american.