Qwen Asr Skill

Provides high-accuracy speech-to-text conversion supporting 22 Chinese dialects and 30 languages with automatic language detection, running on CPU.

This skill appears coherent with its stated purpose, but review and precautions are recommended before installing: 1) The skill will download ~6GB of model weights from Hugging Face on first run — ensure you have disk, CPU, and bandwidth capacity. 2) It runs a local web server that accepts file uploads; uploaded audio is stored temporarily in an uploads/ directory and then deleted — run in an isolated environment or container if you are cautious. 3) The code uses dotenv and standard environment variables — check any local .env before starting to avoid unintentionally exposing secrets or changing behavior (and be aware that a private HF model would require an HF token not declared in the SKILL.md). 4) The repository origin is listed as a placeholder in SKILL.md; verify the source URL and review the code before deployment. If you want higher assurance, run the skill inside a sandbox (container/VM) and inspect network traffic during first model download.

Type: OpenClaw Skill Name: qwen-asr-skill Version: 1.3.0 The skill bundle is a legitimate implementation of an Automated Speech Recognition (ASR) service using the Qwen3-ASR-0.6B model. The code consists of an Express.js server (index.js) that interfaces with a Python inference script (asr.py) via the python-shell library. It includes standard features such as file upload handling via multer, CPU performance optimizations (cpu-optimization.py), and dialect mapping (dialect-map.js). No evidence of data exfiltration, malicious execution, backdoors, or prompt injection was found; the logic is consistent with the stated purpose of providing local speech-to-text capabilities.