Audio-to-Audio
MambaSSM
Safetensors
streaming speech-enhancement
speech-enhancement
universal speech enhancement
multiple input sampling rates
language-agnostic
Instructions to use nvidia/Real-time_RE-USE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MambaSSM
How to use nvidia/Real-time_RE-USE with MambaSSM:
from mamba_ssm import MambaLMHeadModel model = MambaLMHeadModel.from_pretrained("nvidia/Real-time_RE-USE") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -179,4 +179,11 @@ Please consider to cite our paper and this framework, if they are helpful in you
|
|
| 179 |
|
| 180 |
and
|
| 181 |
|
| 182 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
|
| 180 |
and
|
| 181 |
|
| 182 |
+
```bibtex
|
| 183 |
+
@article{fu2026one,
|
| 184 |
+
title={One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications},
|
| 185 |
+
author={Fu, Szu-Wei and Chao, Rong and Yang, Xuesong and Huang, Sung-Feng and Juki{\'c}, Ante and Tsao, Yu and Wang, Yu-Chiang Frank},
|
| 186 |
+
journal={arXiv preprint arXiv:2606.25621},
|
| 187 |
+
year={2026}
|
| 188 |
+
}
|
| 189 |
+
```
|