Qwen ASR (C-based Offline)

Offline Chinese and mixed Chinese-English speech-to-text recognition in pure C without Python or FFmpeg dependencies, suitable for edge devices.

Key points before installing/using: - The packaging is inconsistent: SKILL.md says 'no FFmpeg' but run.sh calls ffmpeg. Expect to need system tools: git, make, a C toolchain, BLAS (OpenBLAS/MKL), and ffmpeg. - The skill does not auto-download models: you must run the upstream download_model.sh manually (this requires internet and TTY). After that, inference can be offline. Verify the model source and license before downloading (~1.7–4.5GB each). - The runner compiles and executes code from ~/.openclaw/workspace/qwen-asr. Only proceed if you trust the upstream repository (https://github.com/antirez/qwen-asr) — inspect its code and the download script (download_model.sh) yourself. - Run builds in a sandbox/container or non-privileged account if possible, and do not run as root. Check disk space and memory requirements before use. - Because metadata omitted required binaries and contradicted the README, treat this as a poorly packaged integration rather than clearly malicious — but verify upstream sources and inspect scripts before running them.

Type: OpenClaw Skill Name: rightister-qwen-asr Version: 1.0.0 The skill is a legitimate wrapper for the qwen-asr C implementation by antirez, providing offline Chinese speech-to-text capabilities. The execution script (scripts/run.sh) handles audio preprocessing via FFmpeg and manages model inference safely, requiring manual user intervention for repository cloning and model downloads rather than performing automated remote execution. While the script contains a minor functional bug in temporary directory creation (mktemp usage), it lacks any indicators of malicious intent, data exfiltration, or prompt injection.