Speech Recognition On Libricss
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 |
|---|---|---|---|
| GSS + Transducer | 3.30 | GPU-accelerated Guided Source Separation for Meeting Transcription | |
| TS-SEP | 3.27 | TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings |
0 of 2 row(s) selected.