Text-to-audio generation on VGGSound (test)
1.17KL DivergenceAudioLDM 2
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| AudioLDM 2Model Type=Specialized Models2026.06 | 1.17 | 6.96 | 19.65 | 6.32 | 0.38 | |
| MAGNeTModel Type=Specialized Models2026.06 | 1.28 | 6.12 | 28.8 | 4.8 | 0.335 | |
| UATModel Type=Unified Models2026.06 | 1.28 | 9.34 | 22.07 | 4.91 | 0.434 | |
| AudioXModel Type=Specialized Models2026.06 | 1.29 | 8.97 | 21.09 | 5.31 | 0.439 | |
| Audio-OmniModel Type=Unified Models2026.06 | 1.33 | 8.31 | 53.97 | 4.56 | 0.407 | |
| Tango 2Model Type=Specialized Models2026.06 | 1.48 | 6.21 | 31.01 | 4.33 | 0.337 | |
| AudioLDMModel Type=Specialized Models2026.06 | 1.49 | 6.41 | 35.66 | 9.88 | 0.432 | |
| Stable Audio OpenModel Type=Specialized Models2026.06 | 1.89 | 6.67 | 39.25 | 7.75 | 0.304 | |
| Unified-IO 2Model Type=Unified Models2026.06 | 2.25 | 3.96 | 80.94 | 21.02 | 0.174 | |
| UniAudio 2.0Model Type=Unified Models2026.06 | 2.69 | 5.34 | 49.39 | 10.25 | 0.151 |