Audio Captioning on ASFx (eval)
19.36SPIDErWhisper-Cards
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Whisper-CardsTraining data=Pixtral audiocards (descriptive caption)2026.02 | 19.36 | 53.4 | |
| Whisper-CardsTraining data=Pixtral audiocards (full card)2026.02 | 18.61 | 51.78 | |
| Audio Flamingo 3Mode=think2026.02 | 9.61 | 42.61 | |
| GAMA2026.02 | 9.3 | 45.7 | |
| Whisper-BaselineTraining data=Pixtral captions2026.02 | 7.98 | 49.78 | |
| Audio Flamingo 32026.02 | 5.27 | 32.1 | |
| WavCaps HTSAT2026.02 | 3.98 | 35.27 | |
| WavCaps CNN142026.02 | 3 | 32.2 | |
| Audio Flamingo 22026.02 | 1.68 | 30.08 |