Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
nvidia
/
RE-USE
like
34
Follow
NVIDIA
53.3k
Audio-to-Audio
MambaSSM
Safetensors
universal speech enhancement
multiple input sampling rates
language-agnostic
arxiv:
2603.02641
License:
other
Model card
Files
Files and versions
xet
Community
Use this model
main
RE-USE
39.5 MB
Ctrl+K
Ctrl+K
1 contributor
History:
31 commits
szuweifu
Update README.md
fe51d64
verified
about 6 hours ago
long_noisy_audio
Upload 2 files
5 days ago
models
Upload generator_SEMamba_time_d4.py
about 6 hours ago
noisy_audio
Upload 2 files
5 days ago
recipes
Upload 11 files
9 days ago
utils
Upload 11 files
9 days ago
.gitattributes
1.65 kB
Upload 2 files
5 days ago
README.md
7.67 kB
Update README.md
about 6 hours ago
config.json
830 Bytes
Add SEMamba safetensors checkpoint and config
about 6 hours ago
inference.py
4.77 kB
Upload 2 files
about 6 hours ago
inference.sh
395 Bytes
Upload 11 files
9 days ago
inference_chunk.py
6.22 kB
Upload 2 files
about 6 hours ago
inference_chunk.sh
473 Bytes
Upload 11 files
9 days ago
model.safetensors
38.6 MB
xet
Add SEMamba safetensors checkpoint and config
about 6 hours ago
