EnCLAP++-large

Reported on 5 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio5 results

Audio captioningonAudioCaps
FENSE· uses extra data· 2024-09-02
0.665
best: 0.668 (SLAM-AAC)
SOTA
EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance arXiv:2409.01201
Audio captioningonAudioCaps
CIDEr· uses extra data· 2024-09-02
0.823
best: 50.2 (Audio Flamingo)
EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance arXiv:2409.01201
Audio captioningonAudioCaps
METEOR· uses extra data· 2024-09-02
0.269
best: 20.5 (Audio Flamingo)
EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance arXiv:2409.01201
Audio captioningonAudioCaps
SPICE· uses extra data· 2024-09-02
0.197
best: 15.1 (Audio Flamingo)
EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance arXiv:2409.01201
Audio captioningonAudioCaps
SPIDEr· uses extra data· 2024-09-02
0.51
best: 32.6 (Audio Flamingo)
EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance arXiv:2409.01201