pix2tex: Using a ViT to convert images of equations into LaTeX code.
$ git clone https://github.com/lukas-blecher/LaTeX-OCR.gitA minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | ่ถ ่ฝป้SOTA LaTeXๅ ฌๅผ่ฏๅซๆจกๅ๏ผไป 20Mๅๆฐ้๏ผๅฏๅจๆต่งๅจไธญ่ฟ่กใ่ฎญ็ปๅ จๆต็จไปฃ็ ๅผๆบ๏ผไปฅไพฟ่ชๅญฆๅค็ฐใ
Formula recognition based on LaTeX-OCR and ONNXRuntime.
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
Translate manga/image ไธ้ฎ็ฟป่ฏๅ็ฑปๅพ็ๅ ๆๅญ https://cotrans.touhou.ai/ (no longer working)
Data from GitHub ยท snapshot Sep 24, 2026