Text-to-Audio Retrieval on VGGSounder
33.8mAPAuroLA
Evaluation results
| Method | Links | |
|---|---|---|
| AuroLAPre-training setting=Full AudioVerse training2026.02 | 33.8 | |
| AuroLAPre-training setting=PT2026.02 | 29.3 | |
| OnePeacePre-training setting=PT2026.02 | 27.9 | |
| VASTPre-training setting=PT2026.02 | 27.1 | |
| WavCapsPre-training setting=Standard2026.02 | 25.8 | |
| PE-AVPre-training setting=PT2026.02 | 21.1 | |
| CLAP (fusion)Pre-training setting=Standard, Model Variant=Fusion2026.02 | 20.5 | |
| ReCLAPPre-training setting=Standard2026.02 | 15.5 |