ARK-ASR-0.6B

Home/Models/Audio8/ARK-ASR-0.6B

Audio8/ARK-ASR-0.6B

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: —
provider: Audio8
license: apache-2.0
language: zh, en, de, ja, fr, ko, es, pl, it, ro, hu, cs
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 2,049
likes: 47
created: —
last modified: 2026-06-27T14:50:28+00:00 (2026)
huggingface: https://huggingface.co/Audio8/ARK-ASR-0.6B
tags: transformerssafetensorsarkasrtext-generationautomatic-speech-recognitionspeechaudiopytorchark-asrcustom_codezhendejafrkoesplitrohucsnlfi

benchmark	category	score	conf	evidence
WER AMI	speech-asr	11.54	high	`\| Ark-ASR \| 11.54% \| 10.07% \| 8.95% \| 1.87% \| 3.89% \| 2.89% \| 6.63% \| 6.55% \|`
WER Earnings-22	speech-asr	10.07	high	`\| Ark-ASR \| 11.54% \| 10.07% \| 8.95% \| 1.87% \| 3.89% \| 2.89% \| 6.63% \| 6.55% \|`
WER GigaSpeech	speech-asr	8.95	high	`\| Ark-ASR \| 11.54% \| 10.07% \| 8.95% \| 1.87% \| 3.89% \| 2.89% \| 6.63% \| 6.55% \|`
WER VoxPopuli	speech-asr	6.63	high	`\| Ark-ASR \| 11.54% \| 10.07% \| 8.95% \| 1.87% \| 3.89% \| 2.89% \| 6.63% \| 6.55% \|`
WER SPGISpeech	speech-asr	2.89	high	`\| Ark-ASR \| 11.54% \| 10.07% \| 8.95% \| 1.87% \| 3.89% \| 2.89% \| 6.63% \| 6.55% \|`

none scraped.