What I would dream about is the ability to read Manwha with it. That's probably a bit hard as the text is inside images, but maybe with some image recognition it might be possible...?
I absolutely want that I well! I took the fastai course and made some attempt at building my own custom OCR. I got some result but not good enough for production (after all I'm totally new to the domain lol). I still believe it is possible, but time wise, I had to go work on other tasks first. Ideally I want something that works client side, should run on mobile (think wasm onnx or something like that) and is specialized for webtoon. I don't know if I'm dreaming too big or not but I want to give a second try in the future.