Real-time Subtitles Using Face Tracking

This is an updated personal subtitling and translation application for augmented reality, though the current version could also be used for Zoom, MS Teams, or other teleconferencing applications. I also have a version that can do post-processing on a recorded video, which might be useful for the hearing-impaired.

The end goal is to be able to do translations/subtitles in a language of your choice. I'm currently working on a custom large language model to handle this, so stay tuned! Incidentally, all of this code runs offline, with no calls to any systems like Whisper or ChatGPT.

Here is the link to the software on GitHub!
https://github.com/JEOresearch/transc...

Feel free to subscribe if you want to see the next iteration!