HF Model & Benchmark Matrix

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

low-frame-rate-speech-codec-22khz

nvidia/low-frame-rate-speech-codec-22khz

kind
original
quant
bf16 (16-bit)
family
misc
modality
feature-extraction
root model
nvidia/low-frame-rate-speech-codec-22khz
provider
nvidia
license
other
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
265
likes
20
created
—
last modified
2025-08-05T21:34:46+00:00 (2025)
huggingface
https://huggingface.co/nvidia/low-frame-rate-speech-codec-22khz
tags
nemofeature-extractionarxiv:2409.12117arxiv:2010.05646arxiv:2309.15505arxiv:2210.13438arxiv:2110.13900arxiv:2306.06546license:otherregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
MOSspeech-tts4.43low| MLS | 4.43 | 4.46 | 0.147 | 0.061 | 2.09 |
WER MLSspeech-asr4.43MLSmedium| MLS | 4.43 | 4.46 | 0.147 | 0.061 | 2.09 |
CERspeech-asr2.09low| MLS | 4.43 | 4.46 | 0.147 | 0.061 | 2.09 |

Discussions (0)

none scraped.

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