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
File size: 368 Bytes
13e5029 | 1 2 3 4 5 6 7 | pip install triton==2.3.0
CUDA_VISIBLE_DEVICES='0' python online_inference.py \
--config recipes/USEMamba_12x1_lr_00002_norm_05_vq_067_nfft_320_hop_160_NRIR_012_pha_0005_com_04_early_005_release_random_layer_GAN_longer_1k.yaml \
--Exit_layer 8 \
--look_ahead_frames 0 \
#--BWE 16000 \
# Exit_layer can be between 3~12 , look_ahead_frames can be between 0~2 |