Automatic Speech Recognition on LibriSpeech/EuroParlST/CoVoST2 Weighted Average (test)
5.9WERSeamlessM4T-v2-large (ASR/ST)
Evaluation results
| Method | Links | |
|---|---|---|
| SeamlessM4T-v2-large (ASR/ST)Model Category=SFM and Projector-only Model, Task Support=ASR/ST2026.07 | 5.9 | |
| BEST-IWSLT25-IFModel Category=Multimodally Trained Models2026.07 | 7.3 | |
| SpeechMapper + LoRA (C) setup 2Model Category=Multimodally Trained Models, LoRA=C, Setup=22026.07 | 7.4 | |
| SpeechMapper + LoRA (C) setup 1Model Category=Multimodally Trained Models, LoRA=C, Setup=12026.07 | 8.2 | |
| SpeechMapper (A)Model Category=SFM and Projector-only Model, Setup=A2026.07 | 14.2 |