# Meeting transcription optimization

An end-to-end speaker diarization model based on the Sortformer architecture, which resolves permutation issues in diarization by ordering speech segments according to speaker arrival time, supporting recognition of up to 4 speakers.

This is a speaker segmentation model based on pyannote.audio, capable of detecting speech activity, speaker changes, and overlapping speech.

Pyannote.audio's speaker diarization pipeline for automatic detection and segmentation of different speakers in audio

This is a powerset-encoded speaker diarization model capable of processing 10-second audio clips to identify multiple speakers and their overlapping speech.