HF Model & Benchmark Matrix

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

stt_fr_fastconformer_hybrid_large_pc

nvidia/stt_fr_fastconformer_hybrid_large_pc

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/stt_fr_fastconformer_hybrid_large_pc
provider
nvidia
license
cc-by-4.0
language
fr
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
587
likes
7
created
—
last modified
2025-02-27T13:09:01+00:00 (2025)
huggingface
https://huggingface.co/nvidia/stt_fr_fastconformer_hybrid_large_pc
tags
nemoautomatic-speech-recognitionspeechaudioTransducerFastConformerCTCTransformerpytorchNeMohf-asr-leaderboardfrdataset:multilingual_librispeechdataset:mozilla-foundation/common_voice_12_0dataset:VoxPopuliarxiv:2305.05084license:cc-by-4.0model-indexregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
WER VoxPopulispeech-asr5.86low| 1.18.0 | SentencePiece Unigram | 1024 | 6.84 | 7.92 | 5.0 | 5.21 | 5.86 | 6.49 |
WER MLSspeech-asr5.0low| 1.18.0 | SentencePiece Unigram | 1024 | 6.84 | 7.92 | 5.0 | 5.21 | 5.86 | 6.49 |

Discussions (0)

none scraped.

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