chidiwilliams / buzz

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
https://chidiwilliams.github.io/buzz
MIT License
11.95k stars 899 forks source link

Transcript with Person names #887

Closed adijahangir123 closed 4 weeks ago

adijahangir123 commented 4 weeks ago

Is it possible to somehow add functionality which enables user to identify person speaking without listening to original audio. Even if it labels them as person A and person B etc

raivisdejus commented 4 weeks ago

Theoretically it is possible. Technically the feature is called Speaker Diarization and there are solutions that do this. Some future version may get this feature. Will close this issue as this feature already has been requested in https://github.com/chidiwilliams/buzz/issues/492