Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
speechbrain
/
sepformer-wsj03mix
like
7
Follow
SpeechBrain
623
Audio-to-Audio
speechbrain
WSJ0-3Mix
English
Source Separation
Speech Separation
Audio Source Separation
WSJ0-3Mix
SepFormer
Transformer
audio-source-separation
arxiv:
2010.13154
arxiv:
2106.04624
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Use this model
main
sepformer-wsj03mix
320 MB
7 contributors
History:
30 commits
Adel-Moumen
Update README.md
21e78b4
verified
almost 2 years ago
.gitattributes
1.04 kB
pushing the sepformer wsj0-3mix model
almost 5 years ago
CKPT.yaml
92 Bytes
pushing the sepformer wsj0-3mix model
almost 5 years ago
README.md
4.09 kB
Update README.md
almost 2 years ago
brain.ckpt
28 Bytes
xet
pushing the sepformer wsj0-3mix model
almost 5 years ago
config.json
52 Bytes
Create config.json
over 4 years ago
counter.ckpt
3 Bytes
xet
pushing the sepformer wsj0-3mix model
almost 5 years ago
decoder.ckpt
17.2 kB
xet
pushing the sepformer wsj0-3mix model
almost 5 years ago
encoder.ckpt
17.3 kB
xet
pushing the sepformer wsj0-3mix model
almost 5 years ago
hyperparams.yaml
1.52 kB
cleaned inference hyparam file
over 4 years ago
hyperparams_train.yaml
4.14 kB
cleaned inference hyparam file
over 4 years ago
lr_scheduler.ckpt
2.22 kB
xet
pushing the sepformer wsj0-3mix model
almost 5 years ago
masknet.ckpt
113 MB
xet
pushing the sepformer wsj0-3mix model
almost 5 years ago
optimizer.ckpt
206 MB
xet
pushing the sepformer wsj0-3mix model
almost 5 years ago
test_mixture_3spks.wav
33.1 kB
adding a 3 speaker mixture example
almost 5 years ago
