HF Model & Benchmark Matrix

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

stt_ru_conformer_transducer_large

nvidia/stt_ru_conformer_transducer_large

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/stt_ru_conformer_transducer_large
provider
nvidia
license
cc-by-4.0
language
ru
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
56
likes
21
created
—
last modified
2025-02-18T13:38:36+00:00 (2025)
huggingface
https://huggingface.co/nvidia/stt_ru_conformer_transducer_large
tags
nemoautomatic-speech-recognitionspeechaudioTransducerConformerTransformerpytorchNeMohf-asr-leaderboardrudataset:mozilla-foundation/common_voice_10_0dataset:SberDevices/Golosdataset:Russian-LibriSpeechdataset:SOVA-Datasetarxiv:2005.08100license:cc-by-4.0model-indexregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr10.0mediumCommon Voice 10.0

Discussions (0)

none scraped.

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