Local Speech Recognition (Windows · Qwen3-ASR · OpenVINO)

Model: snake7gun/Qwen3-ASR-0.6B-fp16-ov (ModelScope FP16)
SKILL_VERSION: 'v1.0.1'

First time? Before using this skill, run these two scripts once in a terminal:

python setup.py          # creates venv, installs dependencies (~5 min)
python download_model.py # downloads the model (~2 GB, resumable)

Both scripts are in the skill directory alongside this SKILL.md.

Agent Routing (When To Call acoustic_pipeline.py)

Use acoustic_pipeline.py as the default agent entry when any of these are true: