Qwen 3 ASR 1.7B
Qwen develops the Qwen 3 ASR 1.7B model, an open-source audio model exceling at speech-to-text tasks, particularly in complex acoustic environments and challenging text patterns. It is notable for its ability to support language identification and speech recognition for 52 languages and dialects, leveraging large-scale speech training data and a strong foundation model.
Input
Output
Context
4K
Max Output
-
Parameters
1.7B
Technical Specifications
Model TypeAudio
Context Window4,096 tokens
Max Output TokensNot available
Parameters1.7B
Release DateJan 28, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Audio
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Qwen 3 ASR 1.7B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.