Text To Music Generation On Musiccaps
评估指标
FAD
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | FAD |
|---|---|
| musiclm-generating-music-from-text | 9.6 |
| stable-audio-open | 3.51 |
| 2406-15487 | 2.21 |
| musiclm-generating-music-from-text | 4.0 |
| audioldm-2-learning-holistic-audio-generation | 3.13 |
| quality-aware-masked-diffusion-transformer | 1.65 |
| fast-timing-conditioned-latent-audio | - |
| flux-that-plays-music | 1.43 |
| musiclm-generating-music-from-text | 13.4 |
| jen-1-text-guided-universal-music-generation | 2.00 |
| simple-and-controllable-music-generation | 5.0 |
| melfusion-synthesizing-music-from-image-and | 1.12 |
| noise2music-text-conditioned-music-generation | 2.134 |
| audioldm-2-learning-holistic-audio-generation | - |
| uniaudio-an-audio-foundation-model-toward-1 | 3.65 |
| audioldm-2-learning-holistic-audio-generation | 2.93 |
| noise2music-text-conditioned-music-generation | 3.840 |
| etta-elucidating-the-design-space-of-text-to | 1.91 |
| simple-and-controllable-music-generation | 3.8 |
| efficient-neural-music-generation | 5.41 |
| simple-and-controllable-music-generation | 3.4 |