Downstream Audio Generation
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-To-Audio | Downstream Audio Generation TTA | FAD1.987 | 8 | |
| Text-To-Music | Downstream Audio Generation (TTM) | FAD3.366 | 8 | |
| Text-To-Speech | Downstream Audio Generation TTS | WER3.03 | 8 |
Showing 3 of 3 rows