cvssp/WavCaps download history
cvssp/WavCaps is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 47,346 times (1,635 in the last 7 days), and 178,364 times in total. It ranks #526 among datasets by monthly downloads.
WavCaps WavCaps is a ChatGPT-assisted weakly-labelled audio captioning dataset for audio-language multimodal research, where the audio clips are sourced from three websites (FreeSound, BBC Sound Effects, and SoundBible) and a sound event detection dataset (AudioSet Strongly-labelled Subse
Models trained on WavCaps
6 models list it as training data.
- declare-lab/TangoFlux 1.1K downloads in 30 days
- declare-lab/TangoFlux-base 25 downloads in 30 days
- Cactooz/DeepMMAudio 0 downloads in 30 days
- KarthikKB1998/CARD-Qwen3-4B-Phase1 – downloads in 30 days
- KarthikKB1998/CARD-Qwen3-4B-AudioCaps – downloads in 30 days
- KarthikKB1998/CARD-Qwen3-4B-Clotho – downloads in 30 days
Spaces using WavCaps
- Model Pulse 8 likes