Speaker-attributed Automatic Speech Recognition on LSMix 3
21.7cpWERDiCoW v3.3
Evaluation results
| Method | Links | |
|---|---|---|
| DiCoW v3.3Model Category=Specialized MT-ASR Models, Diarization System=DiariZen2026.06 | 21.7 | |
| DixtralModel Category=General Purpose Spoken LMs, Diarization System=DiariZen2026.06 | 23.5 | |
| Voxtral MTv2Model Category=Specialized MT-ASR Models2026.06 | 42.3 | |
| VibeVoiceModel Category=Specialized MT-ASR Models2026.06 | 72.8 | |
| Gemini 3.0 FlashModel Category=General Purpose Spoken LMs2026.06 | 84.7 |