HF Model & Benchmark Matrix

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

T-one

t-tech/T-one

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
—
provider
t-tech
license
apache-2.0
language
ru
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
978
likes
98
created
—
last modified
2025-07-30T11:07:43+00:00 (2025)
huggingface
https://huggingface.co/t-tech/T-one
tags
onnxsafetensorsconformerstreamingasrstttelephonyrussianspeecht-techt-oneautomatic-speech-recognitionrulicense:apache-2.0region:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr19.0mediumCommonVoice 19
WER Common Voicespeech-asr5.32CommonVoice 19 (test split)medium| CommonVoice 19 (test split) | 5.32 | **2.68** | 3.14 | 6.22 | 11.3 | 5.78 |

Discussions (0)

none scraped.

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