Music Generation on Song Describer Dataset no-singing (test)
79.09FDopenl3Stable Audio 2
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Stable Audio 2channels/sr=2/44.1kHz, output length=2m, inference time=13s2024.04 | 79.09 | 0.35 | 0.4 | |
| Stable Audio 2channels/sr=2/44.1kHz, output length=4m 45s, inference time=13s2024.04 | 81.96 | 0.34 | 0.39 | |
| MusicGen-large-stereochannels/sr=2/32kHz, output length=2m, inference time=6m 38s2024.04 | 204.03 | 0.49 | 0.28 | |
| MusicGen-large-stereochannels/sr=2/32kHz, output length=4m 45s, inference time=12m 53s2024.04 | 218.02 | 0.5 | 0.27 |