|
Download README.md from teamup-tech/DeepFilterNet-weights: direct link, hf CLI and curl.
- Browser
- Download file 897 Bytes
-
https://huggingface.co/teamup-tech/DeepFilterNet-weights/resolve/main/README.md
- Command line
-
hf download hf://teamup-tech/DeepFilterNet-weights/README.md
-
curl -L -o README.md https://huggingface.co/teamup-tech/DeepFilterNet-weights/resolve/main/README.md
897 Bytes
metadata
license: mit
The pretrained DeepFilterNet3 model for the DeepFilterNet Space, mirrored because the deepfilternet package otherwise downloads it from the main branch of its GitHub repository. The files are unchanged, in the layout init_df(model_base_dir=...) reads.
DeepFilterNet3/: extracted from https://github.com/Rikorose/DeepFilterNet/raw/d375b2d8309e0935d165700c91da9de862a99c31/models/DeepFilterNet3.zip (SHA-25649c52edc8947ae1f9bf50d81530beaf3a2c3245aeaf34b6f31ff535cd22284d2).config.ini: SHA-256415eb925d44990d938fb739f514aa3662c1ec0ea836cff044fa1291b82cb4290checkpoints/model_120.ckpt.best: SHA-25623b92884f63ccf54bb026014604625ab231657b6480df65db4095c4c171e6003
Everything in the DeepFilterNet repository, the models included, is dual-licensed MIT or Apache-2.0 by Hendrik Schröter.