Speech Recognition On Librispeech Train Clean
Métriques
Word Error Rate (WER)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| wav2vec_wav2letter | 2.8 | Self-training and Pre-training are Complementary for Speech Recognition |
0 of 1 row(s) selected.