Apppublic

teticio/audio-diffusion

sourceHugging Facegpl-3.0updated 4y agoView on Hugging Face

54likes

setup.cfg21 linesDownload Raw Back to root

1[metadata]2name = audiodiffusion3version = attr: audiodiffusion.VERSION4description = Generate Mel spectrogram dataset from directory of audio files.5long_description = file: README.md6long_description_content_type = text/markdown7license = GPL38classifiers =9    Programming Language :: Python :: 310 11[options]12zip_safe = False13packages = audiodiffusion14install_requires =15    torch16    numpy17    Pillow18    diffusers>=0.12.019    librosa20    datasets>=2.9.021