# Speaker ID + Diarization FT: pyannote.audio + WavLM — Multi-Speaker Separation

> Source: https://sukruyusufkaya.com/en/learn/fine-tuning-cookbook/ftc-speaker-id-diarization-pyannote
> Updated: 2026-05-14T14:42:55.231Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part VII — Speech & Audio Fine-Tuning
**TLDR:** Meeting/call center transcripts: 'who's speaking + what'. pyannote.audio (HF), WavLM speaker embeddings, diarization pipeline (VAD → embedding → clustering). Call center case: customer vs operator separation, FT on RTX 4090 + 100h TR call dataset.