whisper-large-v3-high-mixed-nl

Home/Models/yuriyvnv/whisper-large-v3-high-mixed-nl

yuriyvnv/whisper-large-v3-high-mixed-nl

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: openai/whisper-large-v3
provider: yuriyvnv
license: apache-2.0
language: nl
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 145
likes: 4
created: —
last modified: 2026-05-20T17:34:10+00:00 (2026)
huggingface: https://huggingface.co/yuriyvnv/whisper-large-v3-high-mixed-nl
tags: transformerssafetensorswhisperautomatic-speech-recognitiondutchspeechaudiosynthetic-dataasrhf-asr-leaderboardnldataset:mozilla-foundation/common_voice_17_0dataset:yuriyvnv/synthetic_transcript_nlarxiv:2212.04356base_model:openai/whisper-large-v3base_model:finetune:openai/whisper-large-v3license:apache-2.0model-indexendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
WER	speech-asr	20.29	Test WER (MLS)	medium	`\| Test WER (MLS) \| 20.29% \|`
WER Common Voice	speech-asr	17.0		medium	`Common Voice 17.0`
QuALITY	knowledge	5.7	Mid-High Quality Filtered + CV	medium	`\| Mid-High Quality Filtered + CV \| 1,270 \| 0.0570 \| 3.63% \| 4.48% \| 17.25% \|`
WER Common Voice	speech-asr	5.49	Common Voice Only	medium	`\| Common Voice Only \| 680 \| 0.0549 \| 3.56% \| 4.39% \| 22.43% \|`
QuALITY	knowledge	5.2	High-Quality Filtered + CV	medium	`\| High-Quality Filtered + CV \| 890 \| 0.0520 \| 3.57% \| 4.43% \| 20.29% \|`
WER	speech-asr	4.43	Test WER (Common Voice)	medium	`\| Test WER (Common Voice) \| 4.43% \|`
WER	speech-asr	3.57	Validation WER	medium	`\| Validation WER \| 3.57% \|`
WER	speech-asr	3.56		low	`\| Common Voice Only \| 680 \| 0.0549 \| 3.56% \| 4.39% \| 22.43% \|`

none scraped.