Qwen3-ASR-0.6B-ONNX

This repository contains an ONNX Runtime export of Qwen3-ASR-0.6B.

Usage

Please use the inference and deployment scripts from:

This export package already includes:

  • encoder.onnx
  • decoder.onnx
  • tokenizer assets
  • feature extractor config
  • chat template
  • metadata for runtime loading

Notes

  • This repository is intended for ONNX Runtime inference.
  • Exported and packaged from the Qwen3-ASR model family.
  • For deployment details, benchmark notes, and service scripts, refer to the GitHub repository above.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support