Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
sp-uhh
/
speech-enhancement-sgmse
like
12
Follow
Signal Processing Group at University of Hamburg
8
Audio-to-Audio
PyTorch
5 datasets
English
speech-enhancement
dereverberation
diffusion-models
generative-models
audio-processing
arxiv:
2406.06185
arxiv:
2409.10753
License:
mit
Model card
Files
Files and versions
Community
1
3d9f50f
speech-enhancement-sgmse
Ctrl+K
Ctrl+K
2 contributors
History:
34 commits
Shokoufehhh
Update README.md
3d9f50f
verified
8 months ago
logs
Upload 40 files
11 months ago
preprocessing
Upload 40 files
11 months ago
sgmse
Upload 40 files
11 months ago
.gitattributes
Safe
1.52 kB
initial commit
11 months ago
.gitignore
Safe
5.52 kB
Upload 40 files
11 months ago
LICENSE
Safe
1.1 kB
Upload 40 files
11 months ago
README.md
9.43 kB
Update README.md
8 months ago
app.py
Safe
148 Bytes
Added app.py for audio-to-audio interface
11 months ago
calc_metrics.py
Safe
3.16 kB
Upload 40 files
11 months ago
config.yaml
Safe
2.84 kB
Upload config.yaml
10 months ago
custom_pipeline.py
Safe
2.82 kB
Add custom pipeline file
9 months ago
diffusion_process.png
Safe
244 kB
Upload 40 files
11 months ago
enhancement.py
Safe
3.15 kB
Upload 40 files
11 months ago
requirements.txt
Safe
240 Bytes
Upload 40 files
11 months ago
requirements_version.txt
Safe
397 Bytes
Upload 40 files
11 months ago
train.py
Safe
4.74 kB
Upload 40 files
11 months ago
train_vb_29nqe0uh_epoch=115.ckpt
pickle
Detected Pickle imports (5)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch.DoubleStorage"
,
"sgmse.data_module.SpecsDataModule"
How to fix it?
1.31 GB
LFS
Upload train_vb_29nqe0uh_epoch=115.ckpt
9 months ago
