HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Real-time_RE-USE

nvidia/Real-time_RE-USE

kind
original
quant
bf16 (16-bit)
family
misc
modality
audio-to-audio
root model
nvidia/Real-time_RE-USE
provider
nvidia
license
other
language
—
context
—
library
mamba-ssm
vRAM (GB)
—
size on disk
—
downloads
608
likes
31
created
—
last modified
2026-06-30T09:47:21+00:00 (2026)
huggingface
https://huggingface.co/nvidia/Real-time_RE-USE
tags
mamba-ssmsafetensorsstreaming speech-enhancementspeech-enhancementuniversal speech enhancementmultiple input sampling rateslanguage-agnosticaudio-to-audioarxiv:2603.02641arxiv:2606.25621license:otherregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr19.0mediumCommonVoice 19.0

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.