Qwen
Qwen: Qwen3 ASR 0.6B
qwen/qwen3-asr-0.6b
Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference plus segment-level and word-level timestamps.
Input
$3.33
/ 1M tokens · Token reference
Output
$0
/ 1M tokens · Token reference
Context window
Not published
tokens
Transcription output · Token reference fields do not establish an output-unit price.
Limits
Parameters
938,008,576
Model facts
Author
Qwen
Tokenizer
Qwen3
Modality
Audio -> Transcription
License
Apache-2.0
Created
Aug 13, 2026
Hugging Face
Qwen/Qwen3-ASR-0.6B
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · AudioOutput · Transcription