README.md

---
tags:
- audio
- spectrograms
datasets:
- Rofla/dataset_AudioLDM2_Rofla_Hiphop
---
De-noising Diffusion Probabilistic Model trained on [teticio/audio-diffusion-256](https://huggingface.co/datasets/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.