stt_uz_fastconformer_hybrid_large_pc

Home/Models/nvidia/stt_uz_fastconformer_hybrid_large_pc

nvidia/stt_uz_fastconformer_hybrid_large_pc

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/stt_uz_fastconformer_hybrid_large_pc
provider: nvidia
license: cc-by-4.0
language: uz
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 134
likes: 11
created: —
last modified: 2025-02-18T13:20:48+00:00 (2025)
huggingface: https://huggingface.co/nvidia/stt_uz_fastconformer_hybrid_large_pc
tags: nemoautomatic-speech-recognitionspeechaudioTransducerFastConformerCTCTransformerpytorchNeMohf-asr-leaderboarduzdataset:mozilla-foundation/common-voice-17-0dataset:UzbekVoicedataset:google/fleursarxiv:2305.05084license:cc-by-4.0model-indexregion:us

benchmark	category	score	context	conf	evidence
WER	speech-asr	17.52		low	`\| FLEURS DEV (used as test) \| 17.52 \| 16.20 \| 12.20 \| 10.73 \|`
WER FLEURS	speech-asr	17.52	FLEURS DEV (used as test)	medium	`\| FLEURS DEV (used as test) \| 17.52 \| 16.20 \| 12.20 \| 10.73 \|`

none scraped.