hviske-v5.3

Home/Models/syvai/hviske-v5.3

syvai/hviske-v5.3

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: syvai/hviske-v5.1
provider: syvai
license: cc-by-nc-4.0
language: da
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,727
likes: 9
created: —
last modified: 2026-06-08T17:36:02+00:00 (2026)
huggingface: https://huggingface.co/syvai/hviske-v5.3
tags: transformerssafetensorscohere_asrautomatic-speech-recognitionaudiospeech-recognitiontranscriptiondanishhf-asr-leaderboardcustom_codedadataset:CoRal-project/coral-v3base_model:syvai/hviske-v5.1base_model:finetune:syvai/hviske-v5.1license:cc-by-nc-4.0endpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
WER	speech-asr	10.26		low	\| `read_aloud` \| 9,122 \| 10.26% \| 9.37% \| 4.17% \| 3.80% \|
CER	speech-asr	4.17		low	\| `read_aloud` \| 9,122 \| 10.26% \| 9.37% \| 4.17% \| 3.80% \|

none scraped.