Speaker-Attributed Automatic Speech Recognition on GALE (test)
11.5WDERNemo
Evaluation results
| Method | Links | ||
|---|---|---|---|
| NemoDiarization Model=titanet_large, ASR Model=stt_en_conformer_ctc_large2026.04 | 11.5 | 21.5 | |
| SAA+SIDTraining Mode=Best SAA+SID configuration2026.04 | 12.2 | 22.6 | |
| PyAnnote+WhisperDiarization Tool=pyannote.audio-3.1, ASR Tool=Whisper (large v3)2026.04 | 12.7 | 29.2 | |
| PyAnnote+GraniteDiarization Tool=pyannote.audio-3.1, ASR Tool=Granite speech2026.04 | 12.7 | 30.6 |