Audio Generation on AudioCaps
Metric: IS (higher is better)
Metric: IS (higher is better)
| # | Model↕ | IS▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ETTA | 14.36 | No | ETTA: Elucidating the Design Space of Text-to-Au... | 2024-12-26 | Code |
| 2 | ETTA-FT-AC-100k | 14.29 | No | ETTA: Elucidating the Design Space of Text-to-Au... | 2024-12-26 | Code |
| 3 | Audiobox Sound | 12.7 | No | Audiobox: Unified Audio Generation with Natural ... | 2023-12-25 | - |
| 4 | TangoFlux | 12.2 | No | TangoFlux: Super Fast and Faithful Text to Audio... | 2024-12-30 | Code |
| 5 | Tango-AF&AC-FT-AC | 11.04 | No | Improving Text-To-Audio Models with Synthetic Ca... | 2024-06-18 | Code |
| 6 | TangoFlux-base | 10.7 | No | TangoFlux: Super Fast and Faithful Text to Audio... | 2024-12-30 | Code |
| 7 | AudioLDM2-large | 8.55 | No | AudioLDM 2: Learning Holistic Audio Generation w... | 2023-08-10 | Code |