stt_de_fastconformer_hybrid_large_pc

Home/Models/nvidia/stt_de_fastconformer_hybrid_large_pc

nvidia/stt_de_fastconformer_hybrid_large_pc

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/stt_de_fastconformer_hybrid_large_pc
provider: nvidia
license: cc-by-4.0
language: de
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 636
likes: 6
created: —
last modified: 2025-02-27T13:06:01+00:00 (2025)
huggingface: https://huggingface.co/nvidia/stt_de_fastconformer_hybrid_large_pc
tags: nemoautomatic-speech-recognitionspeechaudioTransducerFastConformerCTCTransformerpytorchNeMohf-asr-leaderboarddedataset:multilingual_librispeechdataset:mozilla-foundation/common_voice_12_0dataset:VoxPopuliarxiv:2305.05084license:cc-by-4.0model-indexregion:us

benchmark	category	score	context	conf	evidence
WER VoxPopuli	speech-asr	11.03		low	`\| 1.18.0 \| SentencePiece Unigram \| 1024 \| 4.36 \| 5.1 \| 3.33 \| 3.87 \| 11.03 \| 8.88 \|`
WER MLS	speech-asr	3.33		low	`\| 1.18.0 \| SentencePiece Unigram \| 1024 \| 4.36 \| 5.1 \| 3.33 \| 3.87 \| 11.03 \| 8.88 \|`

none scraped.