Audio-to-Audio
speechbrain
English
Source Separation
Speech Separation
Audio Source Separation
WSJ02Mix
SepFormer
Transformer
audio-source-separation
Instructions to use admin-spsoft/Speechbrain_SPSoft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- speechbrain
How to use admin-spsoft/Speechbrain_SPSoft with speechbrain:
from speechbrain.pretrained import SepformerSeparation model = SepformerSeparation.from_hparams( "admin-spsoft/Speechbrain_SPSoft" ) model.separate_file("file.wav") - Notebooks
- Google Colab
- Kaggle
Download requirements.txt from admin-spsoft/Speechbrain_SPSoft: direct link, hf CLI and curl.
- Browser
- Download file 52 Bytes
-
https://huggingface.co/admin-spsoft/Speechbrain_SPSoft/resolve/main/requirements.txt
- Command line
-
hf download hf://admin-spsoft/Speechbrain_SPSoft/requirements.txt
-
curl -L -o requirements.txt https://huggingface.co/admin-spsoft/Speechbrain_SPSoft/resolve/main/requirements.txt
52 Bytes
| speechbrain==1.0.3 | |
| torch | |
| torchaudio | |
| soundfile | |
| numpy | |