Speaker identification with pyannote

[evashipova]

Deal colleagues,

first of all, thanks a lot for the amazing tool!

I've read somewhere in the discussions here that speaker identification / speaker tracking is possible using pyannote.audio but requires additional coding efforts. Has anyone already tried this or maybe have any ideas? Let's say, I want to be able not just to differentiate between the speakers (e.g. a professor and a student) but also to know who of them is the professor so that I can process the professor's words later and ignore the student's words. I would then train the system using voice samples of the specific professor.

Thanks in advance!