stt_pl_fastconformer_hybrid_large_pc

Home/Models/nvidia/stt_pl_fastconformer_hybrid_large_pc

nvidia/stt_pl_fastconformer_hybrid_large_pc

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/stt_pl_fastconformer_hybrid_large_pc
provider: nvidia
license: cc-by-4.0
language: pl
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 471
likes: 5
created: —
last modified: 2025-02-27T13:08:20+00:00 (2025)
huggingface: https://huggingface.co/nvidia/stt_pl_fastconformer_hybrid_large_pc
tags: nemoautomatic-speech-recognitionspeechaudioTransducerFastConformerCTCTransformerpytorchNeMohf-asr-leaderboardpldataset:multilingual_librispeechdataset:mozilla-foundation/common_voice_12_0dataset:VoxPopuliarxiv:2305.05084license:cc-by-4.0model-indexregion:us

benchmark	category	score	conf	evidence
WER Common Voice	speech-asr	12.0	medium	`Common Voice 12`
WER VoxPopuli	speech-asr	11.29	low	`\| 1.18.0 \| SentencePiece Unigram \| 1024 \| 5.99 \| 8.67 \| 7.15 \| 5.78 \| 11.29 \| 8.45 \|`
WER MLS	speech-asr	7.15	low	`\| 1.18.0 \| SentencePiece Unigram \| 1024 \| 5.99 \| 8.67 \| 7.15 \| 5.78 \| 11.29 \| 8.45 \|`

none scraped.