Text-to-Audio Generation on AudioSet (eval)
24.26FDAudioLDM-L-Full
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| AudioLDM-L-FullModel Size=L, Training Data=Full2023.01 | 24.26 | 7.67 | 2.07 | |
| AudioLDM-LModel Size=L2023.01 | 27.51 | 7.18 | 2.49 | |
| AudioLDM-SModel Size=S2023.01 | 28.08 | 6.78 | 2.51 | |
| DiffSound2023.01 | 50.4 | 4.19 | 3.63 |