Speaker-Attributed Automatic Speech Recognition on AMI (test)
7.8WDERSAA+SID
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SAA+SIDTraining Mode=Best SAA+SID configuration2026.04 | 7.8 | 22.9 | |
| NemoDiarization Model=titanet_large, ASR Model=stt_en_conformer_ctc_large2026.04 | 13.7 | 52.5 | |
| PyAnnote+GraniteDiarization Tool=pyannote.audio-3.1, ASR Tool=Granite speech2026.04 | 19.7 | 39.9 | |
| PyAnnote+WhisperDiarization Tool=pyannote.audio-3.1, ASR Tool=Whisper (large v3)2026.04 | 23.4 | 43.2 |