teticio/audio-diffusion-breaks-256 download history
teticio/audio-diffusion-breaks-256 is an image to image dataset on the Hugging Face Hub. In the last 30 days it was downloaded 85 times (30 in the last 7 days), and 2,448 times in total. It ranks #127,810 among datasets by monthly downloads.
30,000 256x256 mel spectrograms of 5 second samples that have been used in music, sourced from WhoSampled and YouTube. The code to convert from audio to spectrogram and vice versa can be found in https://github.com/teticio/audio-diffusion along with scripts to train and run inference using De-noisin
Models trained on audio-diffusion-breaks-256
1 models list it as training data.
- teticio/audio-diffusion-breaks-256 8 downloads in 30 days