stt_de_conformer_transducer_large

Home/Models/nvidia/stt_de_conformer_transducer_large

nvidia/stt_de_conformer_transducer_large

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/stt_de_conformer_transducer_large
provider: nvidia
license: cc-by-4.0
language: de
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 46
likes: 8
created: —
last modified: 2025-02-27T13:02:50+00:00 (2025)
huggingface: https://huggingface.co/nvidia/stt_de_conformer_transducer_large
tags: nemoautomatic-speech-recognitionspeechaudioCTCConformerTransformerpytorchNeMohf-asr-leaderboarddedataset:VoxPopulidataset:multilingual_librispeechdataset:mozilla-foundation/common_voice_7_0arxiv:2005.08100license:cc-by-4.0model-indexregion:us

benchmark	category	score	context	conf	evidence
WER VoxPopuli	speech-asr	11.04		low	`\| 1.6.0 \| SentencePiece Unigram \| 1024 \| 4.40 \| 4.93 \| 3.22 \| 3.85 \| 11.04 \| 8.85 \|`
WER MLS	speech-asr	3.22		low	`\| 1.6.0 \| SentencePiece Unigram \| 1024 \| 4.40 \| 4.93 \| 3.22 \| 3.85 \| 11.04 \| 8.85 \|`

none scraped.