No model card yet.
License
other
Tasks
audio-to-audio
Frameworks
mamba-ssm
Hardware-aware snippets
Runtime-specific quick starts for nvidia/RE-USE. Detected hardware: No explicit hardware metadata.
Task: audio-to-audioTransformers
NVIDIA CUDA path
Best default for NVIDIA GPUs and hosted accelerator nodes.
pip install torch transformers accelerate
python - <<'PY'
from transformers import pipeline
model_id = "nvidia/RE-USE"
pipe = pipeline(
task="audio-to-audio",
model=model_id,
device_map="auto",
model_kwargs={"torch_dtype": "auto"},
)
print(pipe("Hello from Inferix"))
PYModel lineage
1 reposBase model
nvidia/RE-USE
Finetuned
1RE-USEselected
Quantizations
0No quantization variants detected.
Model info
Namespace
nvidia
Visibility
public
Downloads
0
Likes
0
License: other
Evaluation results
Entries
0
Tasks
0
Datasets
0
No evaluation results published yet.
Metadata links
Base model
Not specifiedTrained on datasets
No linked datasets
Linked papers
No linked papers
Inference providers
0/0 fitNot available for inference yet.
Spaces using this model
No spaces linked yet.
Part of collections
No public collections include this model.
Tags
importedhuggingfaceminiomamba-ssmsafetensorsspeech-enhancementuniversal speech enhancementmultiple input sampling rateslanguage-agnosticaudio-to-audioarxiv:2603.02641license:otherregion:us