Metric: FD_openl3 (higher is better)
| # | Model↕ | FD_openl3▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | AudioLDM2-music | 354.05 | No | AudioLDM 2: Learning Holistic Audio Generation w... | 2023-08-10 | Code |
| 2 | TANGO-AF | 270.32 | No | Improving Text-To-Audio Models with Synthetic Ca... | 2024-06-18 | Code |
| 3 | MusicGen w/o melody (3.3B) | 197.12 | No | Simple and Controllable Music Generation | 2023-06-08 | Code |
| 4 | AudioLDM2-large | 190.16 | No | AudioLDM 2: Learning Holistic Audio Generation w... | 2023-08-10 | Code |
| 5 | Stable Audio Open | 127.2 | No | Stable Audio Open | 2024-07-19 | Code |
| 6 | Stable Audio | 108.69 | No | Fast Timing-Conditioned Latent Audio Diffusion | 2024-02-07 | Code |
| 7 | ETTA | 92.18 | No | ETTA: Elucidating the Design Space of Text-to-Au... | 2024-12-26 | Code |