Speech To Speech Translation On Fleurs X Eng
Métriques
ASR-BLEU
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | ASR-BLEU |
|---|---|
| seamlessm4t-massively-multilingual-multimodal | 20.4 |
| robust-speech-recognition-via-large-scale-1 | 23.5 |
| seamlessm4t-massively-multilingual-multimodal | 25.8 |
| gentranslate-large-language-models-are | 32.3 |
| gentranslate-large-language-models-are | 30.1 |
| audiolm-a-language-modeling-approach-to-audio | 24.0 |
| seamlessm4t-massively-multilingual-multimodal | 29.4 |