Sources & licenses
Cut Studio credits & licenses
Cut Studio was built for LoschaZ. Speech recognition runs in your browser with open-source software and open models:
What we built
The editor, the cut logic, the pause and sound detection, the hesitation lists, the MP3 and WAV readers, the export engine with its sound fades, the subtitle timing and the EDL and FCPXML cut lists were written for LoschaZ. The MP4 and Matroska readers and the MP4 writer are the ones LoschaZ wrote for the Video Compressor.
Components & licenses
- Transformers.js 4.3.1 by Hugging Face – Apache License 2.0 (license). Served from this website.
- ONNX Runtime Web by Microsoft – MIT License. Its WebAssembly engine is loaded from cdn.jsdelivr.net.
- Whisper speech recognition models by OpenAI – MIT License; the ONNX versions with word timing (base, small) by the ONNX Community are loaded from Hugging Face.
Our changes
The library and the models are used unchanged.