Texo
by alephpi (personal account)
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型，仅20M参数量，可在浏览器中运行。训练全流程代码开源，以便自学复现。 (description from the project’s GitHub page)
Repository facts
- Stars
- 909
- Forks
- 55
- Open issues and pull requests
- 0
- Primary language
- Python
- License
- GNU Affero General Public License v3.0 (AGPL-3.0)
- Owner
- alephpi · Personal account
- Created
- Jul 29, 2025
- Last push
- Sep 18, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 484: lukas-blecher/LaTeX-OCR
pix2tex: Using a ViT to convert images of equations into LaTeX code.
16,591 starsPythonMITLast push Jan 18, 2025
Rank 2,406: breezedeus/Pix2Text
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative…
3,274 starsJupyter NotebookMITLast push Aug 23, 2026
Rank 4,301: RQLuo/MixTeX-Latex-OCR
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
1,640 starsPythonAGPL-3.0Last push Apr 24, 2025
Rank 8,180: arcships/light-ocr
Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores & coordinates. npm: @arcships/light-ocr
639 starsC++Apache-2.0Last push Oct 8, 2026
Rank 2,794: kha-white/manga-ocr
Optical character recognition for Japanese text, with the main focus being Japanese manga
2,808 starsPythonApache-2.0Last push Jul 19, 2026
Rank 1,497: ashleve/lightning-hydra-template
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
5,367 starsPythonNo license file detectedLast push Jun 11, 2026