I built a minimal C++ GUI application that uses whisper to generate captions for both videos and audio.

[iangitonga]

Hello,
I have built an application called Capgen, with a graphical user interface that utilizes the whisper neural network to generate native or translated transcriptions both audio and video file. Currently, the application is still in development but you can compile it and transcribe media on CPU.

The goal of the project is to build a desktop application that can be run on all desktop platforms including Linux, Windows and Apple. and most importantly, can be used by absolutely anyone. Feel free to check the code and contribute to it if you are interested. The code is at this repository:
https://github.com/iangitonga/capgenx

And finally, I am currently looking for a job and I am open to any offers. Feel free to email me at [email protected].