Text-to-Audio Generation on MusicCaps (Qualitative Metrics)
92.1Structure: IntroStable Audio
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Stable Audio2024.02 | 92.1 | — | — | — | 94.7 | 65.7 | 89.4 | |
| MusicGenConfiguration=stereo2024.02 | 52.6 | — | — | — | 86.8 | 76.3 | 15.7 | |
| MusicGenModel Size=large2024.02 | 36.8 | — | — | — | — | 68.4 | 26.3 | |
| AudioLDM2Sampling Rate=48kHz2024.02 | 2.6 | — | — | — | — | 15.7 | 2.6 |