Hi. I apologise for asking but I am OVERWHELMED with the sheer volume of documentation, options & models for Speechbrain - it looks great, and it's clear a huge amount of work has gone into it, but as a novice to this kind of thing (even though I'm an experienced Python dev), I'm feeling quite lost.

I want to enrol multiple voiceprints (MANY!) then identify & diarize speakers in phone call recordings (there may be serveral speakers, as calls get tranferred within the phone systm), using those voiceprints.

BTW: No every speaker will have been enrolled (only call-centre agents - not their customers).

The problem I have is I simple don't know where to start....

If someone could point me to a worked example of something like, or close to, what I'm looking for, that would be great. Or even just point me to the correct part of the documentation, and give me a hint as to which Huggingface model I might start with (for voiceprints), I'd be grateful.

Thanks, in advance....