Audio Generation on AudioCaps
Metric: KL_passt (higher is better)
Metric: KL_passt (higher is better)
| # | Model↕ | KL_passt▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Stable Audio | 2.89 | No | Fast Timing-Conditioned Latent Audio Diffusion | 2024-02-07 | Code |
| 2 | Stable Audio 2.0 | 2.7 | No | Long-form music generation with latent diffusion | 2024-04-16 | Code |
| 3 | Stable Audio Open | 2.14 | No | Stable Audio Open | 2024-07-19 | Code |
| 4 | AudioLDM2-large | 1.68 | No | AudioLDM 2: Learning Holistic Audio Generation w... | 2023-08-10 | Code |
| 5 | AudioGen | 1.42 | No | AudioGen: Textually Guided Audio Generation | 2022-09-30 | Code |
| 6 | TangoFlux-base | 1.23 | No | TangoFlux: Super Fast and Faithful Text to Audio... | 2024-12-30 | Code |
| 7 | ETTA | 1.22 | No | ETTA: Elucidating the Design Space of Text-to-Au... | 2024-12-26 | Code |
| 8 | TangoFlux | 1.15 | No | TangoFlux: Super Fast and Faithful Text to Audio... | 2024-12-30 | Code |
| 9 | ETTA-FT-AC-100k | 1.13 | No | ETTA: Elucidating the Design Space of Text-to-Au... | 2024-12-26 | Code |