Promote Sign in Sign up

Multimodal model

Audio8-ASR-0.1B

Audio8-ASR-0.1B is Audio8’s compact multilingual automatic speech recognition model for transcribing short-form speech across Chinese, English, French, German, Japanese, Korean, and Cantonese.

AutoArk Multimodal Closed cc-by-nc-4.0
Open model card ↗
Type
Multimodal
Weights
Closed
Downloads
16k
Likes
81
Pipeline
automatic speech recognition
License
cc-by-nc-4.0

Model hub

Edge0/Audio8-ASR-0.1B

Repo
Edge0/Audio8-ASR-0.1B
Library
transformers
Access
Public
Technical tags and languages
en zh fr ja de ko transformers safetensors arkasr text-generation automatic-speech-recognition speech audio multilingual pytorch hotword audio8 custom_code
Open on Hugging Face

Papers

1

More from AutoArk

3

About AutoArk

1

AutoArk develops multimodal AI models, AI agents, the EVA OS platform for intelligent hardware, and AI-powered consumer devices such as educational companion robots.