Audio Generation On Classical Music 5 Seconds

评估指标

Bits per byte

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
VAB-Encodec (Ours)40From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation
Sparse Transformer 152M (strided)1.97Generating Long Sequences with Sparse Transformers
0 of 2 row(s) selected.
Audio Generation On Classical Music 5 Seconds | SOTA | HyperAI超神经