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
Question About the Discriminator Implementation
#1
by yezhangyinge - opened
Thank you for open-sourcing such a great model. I’m trying to reproduce the results, but I couldn’t find a detailed description of the discriminator implementation in either the paper or the repository. Would it be possible to release the discriminator code as well?