teticio's picture
Update README.md
ad0f10b
metadata
tags:
  - audio
  - spectrograms
datasets:
  - teticio/audio-diffusion-256

Latent De-noising Diffusion Probabilistic Model trained on teticio/audio-diffusion-256 to generate mel spectrograms of 256x256 corresponding to 5 seconds of audio. 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.