Speech-to-text Translation on CoVoST-2 high-resource X-to-En (test)
37.6Quality Score (Fr)XLS-R (2B) + mBART-ML50N1
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| XLS-R (2B) + mBART-ML50N1Decoder=mBART-ML50N1, Encoder Size=2B2022.05 | 37.6 | 33.6 | 39.2 | 33.8 | 36.1 | — | |
| XMEF-X + mBART-ML50N1Decoder=mBART-ML50N12022.05 | 36.1 | 30.6 | 38.1 | 31.8 | 34.2 | — | |
| XMEF-En + mBART-ML50N1Decoder=mBART-ML50N12022.05 | 35 | 28.2 | 35.2 | 31.1 | 32.4 | — | |
| Wav2SeqBackbone=HuBERT-large2022.05 | 33.2 | 26.9 | 34 | 29.7 | 31 | — | |
| Wav2SeqBackbone=XLS-R (0.3B)2022.05 | 33 | 28 | 33.8 | 29.9 | 31.1 | — | |
| XLS-R (0.3B) + mBART-ML50N1Decoder=mBART-ML50N12022.05 | 32.9 | 26.7 | 34.1 | 28.7 | 30.6 | — | |
| XLSR-53 + mBART-ML50N1Decoder=mBART-ML50N12022.05 | 32.3 | 26.9 | 33.3 | 28.6 | 30.3 | — | |
| VP-100K + mBART-ML50N1Decoder=mBART-ML50N12022.05 | 30.4 | 23.4 | 31.1 | 25.7 | 27.7 | — | |
| Maestro2022.12 | — | — | — | — | — | 38.2 | |
| mSLAM-CTCParameters=2B2022.12 | — | — | — | — | — | 37.8 | |
| WhisperEvaluation protocol=Zero-Shot2022.12 | — | — | — | — | — | 36.2 | |
| XLS-RParameters=2B2022.12 | — | — | — | — | — | 36.1 | |
| XMEF-X2022.12 | — | — | — | — | — | 34.2 |