Denoising Diffusion Probabilistic Model trained on teticio/audio-diffusion-instrumental-hiphop-256 to generate mel spectrograms of 256x256 corresponding to 5 seconds of audio. The audio consists of samples of instrumental Hip Hop music. 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.