| Benchmark | Model | Rank | Results |
|---|---|---|---|
| audio-tagging-on-audioset | BEATs (10 models) | #3 | mean average precision: 0.506 |
| audio-classification-on-audioset | BEATs (Audio-only, Ensemble) | #4 | Test mAP: 0.506 |
| audio-classification-on-audioset | BEATs (Audio-only, Single) | #16 | Test mAP: 0.486 |
| audio-classification-on-balanced-audio-set | BEATs | #4 | Mean AP: 38.9 |
| audio-classification-on-esc-50 | BEATs | #4 | Top-1 Accuracy: 98.1PRE-TRAINING DATASET: AudioSet… |
| keyword-spotting-on-google-speech-commands | BEATs (iter3) | #31 | Google Speech Commands V2 35: 98.3 |