| name | parakeet-stt |
|---|---|
| description | Transcribe audio files to text locally using Parakeet via onnx-asr. |
Transcribe local audio files to text using Parakeet STT models through onnx-asr.
uvinPATHffmpegfor non-WAV input conversion
~/.pi/agent/skills/parakeet-stt/mise.tomlpins[email protected]anduv.~/.pi/agent/skills/parakeet-stt/scripts/stt.pyis auv --scriptentrypoint.~/.pi/agent/skills/parakeet-stt/scripts/stt.shis the redistributable wrapper.~/.pi/agent/skills/parakeet-stt/scripts/stt.py.locklocks script deps.
cd ~/.pi/agent/skills/parakeet-stt
mise install
mise trust# transcribe wav/mp3/ogg/oga/opus
~/.pi/agent/skills/parakeet-stt/scripts/stt.sh /path/to/audio.wav
# choose model explicitly
~/.pi/agent/skills/parakeet-stt/scripts/stt.sh /path/to/audio.wav --model nemo-parakeet-tdt-0.6b-v2- CPU-only runtime:
onnxruntime(notonnxruntime-gpu). - First run downloads model weights/cache.
- Default model:
nemo-parakeet-tdt-0.6b-v2.