Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
mispeech
/
dasheng-denoiser
like
1
Follow
Horizon Team, Xiaomi MiLM Plus
89
Audio-to-Audio
Transformers
Safetensors
dashengdenoiser
feature-extraction
signal-processing
custom_code
arxiv:
2506.11514
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
dasheng-denoiser
476 MB
2 contributors
History:
3 commits
Heinrich Dinkel
updated README
7a87364
about 21 hours ago
.gitattributes
Safe
1.52 kB
initial commit
about 22 hours ago
README.md
2.08 kB
updated README
about 21 hours ago
config.json
603 Bytes
Upload folder using huggingface_hub
about 21 hours ago
configuration_dasheng_denoiser.py
1.28 kB
Upload folder using huggingface_hub
about 21 hours ago
model.safetensors
476 MB
xet
Upload folder using huggingface_hub
about 21 hours ago
modeling_dasheng_denoiser.py
3.15 kB
Upload folder using huggingface_hub
about 21 hours ago
modeling_dasheng_encoder.py
10.1 kB
Upload folder using huggingface_hub
about 21 hours ago
vocos.py
Safe
12.9 kB
Upload folder using huggingface_hub
about 21 hours ago
