---
tags:
- audio
- spectrograms
datasets:
- teticio/audio-diffusion-breaks-256
---
Denoising Diffusion Probabilistic Model trained on [teticio/audio-diffusion-breaks-256](https://huggingface.co/datasets/teticio/audio-diffusion-breaks-256) to generate mel spectrograms of 256x256 corresponding to 5 seconds of audio. The audio consists of 30,000 samples that have been used in music, sourced from [WhoSampled](https://whosampled.com) and [YouTube](https://youtube.com). 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.