Audio Generation On Classical Music 5 Seconds
Métriques
Bits per byte
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Bits per byte | Paper Title | Repository |
|---|---|---|---|
| Sparse Transformer 152M (strided) | 1.97 | Generating Long Sequences with Sparse Transformers | |
| VAB-Encodec (Ours) | 40 | From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation |
0 of 2 row(s) selected.