ahmetbekcan/synthfusion-256

This model was trained on a small synthesizer dataset (about 5800 samples) using the Audio Diffusion Pipeline (https://huggingface.co/docs/diffusers/main/en/api/pipelines/audio_diffusion), based on the work of Robert Dargavel Smith (https://github.com/teticio/audio-diffusion). Example outputs and the running script can be found at https://github.com/ahmetbekcan/synthfusion.