diffusion model for Audio
Pytorch Transformers
python3 main.py --config audio.yml --doc "test" --ni
You can edit the config file to adjust the num_samples and length(t_size).
See sampling in the config file
Use --sequence {number of intermediates} option.
If you want to get all samples, --sequence -1 or --sequence 0
python3 main.py --config audio.yml --doc "test" --sample --sequence 10 --timesteps 1000 --ni@article{song2020denoising,
title={Denoising Diffusion Implicit Models},
author={Song, Jiaming and Meng, Chenlin and Ermon, Stefano},
journal={arXiv:2010.02502},
year={2020},
month={October},
abbr={Preprint},
url={https://arxiv.org/abs/2010.02502}
}