Open ShunyaYamagami opened 1 year ago
@ShunyaYamagami you can use python package created by me: https://pypi.org/project/speechlib/ This is Github repo: https://github.com/NavodPeiris/speechlib
this package can do transcription, speaker diarization and speaker recognition all together and give a transcript with actual speaker names!
When performing diarization on a conversation with multiple speakers, I want to not only recognize that different individuals are speaking but also simultaneously identify who is speaking and even detect their pre-registered names. I believe that recognizing the speaker names from their pre-registered voiceprints would be a good approach. Does pyannote provide a best practice for this out of the box?