antirez/qwen-asr

C inference for Qwen3-ASR 0.6b and 1.7b transcriptions models

C594 stars74 forks

What it does

The Qwen3-ASR repository provides a pure C implementation for speech-to-text transcription using Qwen3-ASR models. It is lightweight, requiring minimal dependencies, and supports both offline and streaming modes, making it accessible for various hardware setups.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-02-21

Creator kit

Hook

Transform audio into text effortlessly with Qwen3-ASR's lightweight C implementation!

Content angles

Create a tutorial on how to set up Qwen3-ASR for real-time transcription.
Compare the performance of Qwen3-ASR's 0.6B and 1.7B models on different hardware.
Develop a video showcasing the integration of Qwen3-ASR with ffmpeg for audio processing.

Who should care

Developers and researchers interested in speech recognition and audio processing.