sakubun VS SudachiPy

I made a (completely free!) tool called sakubun - it helps you practice kanji, and improves your vocabulary. You can check it out here: https://sakubun.xyz

It's not the exact same thing, but what you're saying reminds me of my project sakubun - it gives you reading practice that consists only of kanji you already know. It allows you to import from anki, and uses the tatoeba project for its sentence database.

You could check out my website which has quizzes for reading practice, sakubun

I've made a tool called sakubun - https://sakubun.herokuapp.com - it helps you practice the kanji you've learnt, and exposes you to new words made up of those kanji.

I'm glad you like it! There's a link to the GitHub repo in the footer of the home page, or you could click here: https://github.com/cubetastic33/sakubun

The website works on all devices, and you can also install it like an app if you'd like - instructions for that are provided in the website. It's completely free and open source software, and the backend is written in rust. Please feel free to contribute if you'd like! You can find the GitHub repo here.

The current readings were generated with SudachiPy, with a little processing. UniDic seems pretty interesting, I'll check it out. Do you know how well its accuracy is, compared to Sudachi?

There are free tools for both of these things. I made game2text to do OCR and script matching. It includes a segmentation and normalization library Sudachi but I have not used its normalization feature for the app. I'm not sure anyone else even wants this feature but it will be pretty straightforward to add it if you're familiar with Python and vanilla Javascript.

spaCy uses SudachiPy internally (see the doc comment about that), so if you don't need any of spaCy's extra features or want more control over the tokenization, you could use SudachiPy directly.