After creating speaker embeddings, the pipeline uses agglomerative clustering (from scikit-learn) to group embeddings by speaker, with the number of clusters determined by the user-specified speaker count.

factualpending

Speaker

One Little Coder

Evidence Quote

“it's going to fit the embeddings for the number of clusters that you have selected which is two and it is going to label the speakers like speaker one speaker two”

Source

OpenAI Whisper Speaker Diarization - Transcription with Speaker Names— 1littlecoder
Created: 8/13/2026, 9:45:15 AM

Your notes

Loading notes...