HF Model & Benchmark Matrix

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

audio-codec-22khz

nvidia/audio-codec-22khz

kind
original
quant
bf16 (16-bit)
family
misc
modality
feature-extraction
root model
nvidia/audio-codec-22khz
provider
nvidia
license
other
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
57
likes
6
created
—
last modified
2025-08-05T23:52:39+00:00 (2025)
huggingface
https://huggingface.co/nvidia/audio-codec-22khz
tags
nemofeature-extractionarxiv:2010.05646arxiv:2309.15505arxiv:2406.05298arxiv:1811.02508license:otherregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr4.53CommonVoicemedium| CommonVoice | 4.53 | 3.55 | 0.93 | 0.100 | 0.057 | 7.63 |
WER MLSspeech-asr4.5MLS Englishmedium| MLS English | 4.50 | 3.69 | 0.94 | 0.066 | 0.033 | 8.33 |

Discussions (0)

none scraped.

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