This project's goal is to create a (probably over-engineered) solution to turn your bad subtitles and into great subtitles.
Install project dependencies and start with:
npm install
npm start
Run the detection example:
npm run detect
DeepSpeech is an open source Speech-To-Text engine, using a model trained by machine learning. https://deepspeech.readthedocs.io/en/r0.9/index.html
We use ffmpeg to take any input media and decode into raw PCM audio for deepspeech.