Audio-to-Audio
speechbrain
English
Source Separation
Speech Separation
Audio Source Separation
Libri3Mix
SepFormer
Transformer
audio-source-separation
Instructions to use hahmadraz/sepformer-libri3mix-48k-epoch93_latest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- speechbrain
How to use hahmadraz/sepformer-libri3mix-48k-epoch93_latest with speechbrain:
from speechbrain.pretrained import SepformerSeparation model = SepformerSeparation.from_hparams( "hahmadraz/sepformer-libri3mix-48k-epoch93_latest" ) model.separate_file("file.wav") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 04e66fef3d2df1e501d67a9a9d62c963d2549ca916dd88bce2b6e741f26a6936
- Size of remote file:
- 17.3 kB
- SHA256:
- c6883820c87b284aa9c7510357ae4e62a18badd5cac47ef1c53745691f2e44e7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.