Automatic Speech Recognition on Common Voice Spanish (test)
24.58WERWSM
Evaluation results
| Method | Links | |
|---|---|---|
| WSMSSL Model=mHuBERT, Version=Ours2026.02 | 24.58 | |
| WSMSSL Model=XLS-R, Version=Ours2026.02 | 26.42 | |
| mHuBERTSSL Model=mHuBERT, Version=Baseline2026.02 | 27.38 | |
| WSMSSL Model=MMS, Version=Ours2026.02 | 27.44 | |
| XLS-RSSL Model=XLS-R, Version=Baseline2026.02 | 28.09 | |
| WSMSSL Model=HuBERT, Version=Ours2026.02 | 28.55 | |
| MMSSSL Model=MMS, Version=Baseline2026.02 | 29.32 | |
| HuBERTSSL Model=HuBERT, Version=Baseline2026.02 | 29.99 | |
| WSMSSL Model=wav2vec 2.0, Version=Ours2026.02 | 33.97 | |
| wav2vec 2.0SSL Model=wav2vec 2.0, Version=Baseline2026.02 | 34.3 | |
| WSMSSL Model=data2vec, Version=Ours2026.02 | 35.71 | |
| data2vecSSL Model=data2vec, Version=Baseline2026.02 | 36.14 |