How to identify different speakers using whisper?

[stoictalks]

Currently whisper isn’t able to identify different speakers like

Speaker 1: …
Speaker 2: …
Speaker 3: …

Is it possible to identify each speaker individually by their tone or something?Or, can we connect any other tool with whisper to identify different speakers

[_j]

Can Whisper distinguish two speakers?

This is not a feature of Whisper, there are other systems that can do this, but they typically are good at spotting who is saying what and when, but not nearly as good as whisper at determining what was said. A popular method is to combine the two and use time stamps to sync up the accurate whisper word detection with the other systems ability to detect who sad it and when.

[stoictalks]

Hi, thanks. Can you please share some references on how to combine the two and use time stamps to sync.

We currently use Riverside.fm to record our podcast. It’s speaker recognition is good but transcription is not as accurate as whisper.

[eslof.github]

I think the term is “speaker diarization”, and I see some guides online using “pyannote.audio” together with Whisper to achieve this