Automatic Speech Recognition On Lrs2
Métriques
Test WER
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Test WER |
|---|---|
| deep-audio-visual-speech-recognition | 10.1 |
| audio-visual-recognition-of-overlapped-speech | 6.7 |
| audio-visual-speech-recognition-with-a-hybrid | 8.2 |
| leveraging-uni-modal-self-supervised-learning-1 | 2.7 |
| whispering-llama-a-cross-modal-generative | 6.6 |
| auto-avsr-audio-visual-speech-recognition | 1.5 |
| deep-audio-visual-speech-recognition | 9.7 |
| whisper-flamingo-integrating-visual-features | 1.3 |
| end-to-end-audio-visual-speech-recognition | 3.9 |