OPFS cache workflow: Download model fills the browser cache (watch the event log),
then Transcribe runs from cached weights. Pick any audio file, or use the
bundled sample at /audio.mp3 (drop your own file at public/audio.mp3 to replace it).
Model credits: Parakeet TDT 0.6B v3 by NVIDIA, licensed under CC BY 4.0. Changes: converted to ONNX and quantized by istupakov/ysdede; runs with parakeet.js (MIT). Parakeet CTC 0.6B by NVIDIA, licensed under CC BY 4.0. Changes: converted to ONNX and quantized by onnx-community. Whisper by OpenAI (MIT). Moonshine by Useful Sensors (MIT). Distil-Whisper by Hugging Face (MIT). Lite-Whisper by efficient-speech (Apache-2.0). ONNX exports by onnx-community. All third-party notices.