Model comparison
pyannote/speaker-diarization-3.1 vs StarCoder2 15B
Capability radar, value bars, and side-by-side posture.
pyannote/speaker-diarization-3.1
Not scored
value score
StarCoder2 15B
70
value score
pyannote/speaker-diarization-3.1 ctx
—
StarCoder2 15B ctx
16K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- StarCoder2 15B70
Attribute tape
| Field | pyannote/speaker-diarization-3.1 | StarCoder2 15B |
|---|---|---|
| Developer | Hugging Face | Hugging Face |
| Context | — | 16K |
| Modalities | Automatic-speech-recognition | Text, Code |
| Openness | — | Open Weights |
| Speed | — | — |
| Price | — | — |
| Value score | — | 70 |
| Summary | pyannote/speaker-diarization-3.1 is an end-to-end speaker diarization pipeline that answers 'who spoke when?' in multi-speaker audio recordings. Version 3.1 removes the onnxruntime dependency, running speaker segmentation and embedding entirely in PyTorch via pyannote.audio 3.1+. | BigCode open coding model on Hugging Face. |