Audio-to-Audio
speechbrain
English
Source Separation
Speech Separation
Audio Source Separation
WHAM!
SepFormer
Transformer
audio-source-separation
Instructions to use speechbrain/sepformer-whamr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- speechbrain
How to use speechbrain/sepformer-whamr with speechbrain:
from speechbrain.pretrained import SepformerSeparation model = SepformerSeparation.from_hparams( "speechbrain/sepformer-whamr" ) model.separate_file("file.wav") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- a976dc936b7a36e2774468e8ee482899a69d16d5e2377f19a158533e039e220a
- Size of remote file:
- 206 MB
- SHA256:
- cdf3e25f345002a7a23c56501f6b37438ac59edd907df0699694fb15857e3fd6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.