Audio-to-Audio
speechbrain
PyTorch
German
Speech Enhancement
RescueSpeech
SepFormer
Transformer
Search and Rescue
Eval Results (legacy)
Instructions to use speechbrain/sepformer_rescuespeech with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- speechbrain
How to use speechbrain/sepformer_rescuespeech with speechbrain:
from speechbrain.pretrained import SepformerSeparation model = SepformerSeparation.from_hparams( "speechbrain/sepformer_rescuespeech" ) model.separate_file("file.wav") - Notebooks
- Google Colab
- Kaggle
match at non-singleton dimension error for long file error
#3
by rastinrastini - opened
Hi,
Thanks for publishing your great work. when i give it audio around 5 minute get me following error:
"The size of tensor a (4982) must match the size of tensor b (2500) at non-singleton dimension 1"
but for small file it worked. how can handle it?