AlibabaQwen ASR
Qwen3-ASR-0.6B
Qwen3-ASR-0.6B uses the Qwen3-Omni foundation and supports both streaming and offline recognition.
Practical use
Practical guidance. Evaluate it on microphone audio from the intended device. Check names and numbers separately from ordinary prose; those errors often have a larger effect on downstream search or form entry.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | Qwen/Qwen3-ASR-0.6B |
| Languages | 30 languages and 22 Chinese dialects, with language identification.Qwen3-ASR-0.6B model card |
| Licence | Apache 2.0.Qwen3-ASR-0.6B model card |
Related models
- Qwen3-ASR-1.7B
Alibaba · Qwen ASR
Speech recognition model for streaming and recorded audio in 30 languages and 22 Chinese dialects.
Launch date not confirmedDownloadable - Qwen Audio 3.1 ASR Flash
Alibaba · Qwen ASR
Speech recognition model for short messages, continuous streams and recorded files.
Launch date not confirmedAPI - Qwen3-ForcedAligner-0.6B
Alibaba · Qwen ASR
Speech alignment model that assigns timestamps to supplied text in 11 languages.
Launch date not confirmedDownloadable