HyperAI

Audio Generation On Classical Music 5 Seconds

Metrics

Bits per byte

Results

Performance results of various models on this benchmark

Model Name
Bits per byte
Paper TitleRepository
Sparse Transformer 152M (strided)1.97Generating Long Sequences with Sparse Transformers
VAB-Encodec (Ours)40From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation
0 of 2 row(s) selected.