alephpi/Texo
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。
This tool helps scientists, engineers, and students convert images of mathematical formulas into editable LaTeX code. You input an image containing a mathematical expression, and it outputs the corresponding LaTeX text. Anyone who works with scientific papers, academic notes, or technical documents and needs to easily digitize or edit complex equations would find this valuable.
747 stars.
Use this if you need a fast and lightweight way to accurately convert images of mathematical equations into LaTeX format, even directly within your web browser.
Not ideal if you primarily need to convert handwritten equations, as its performance might vary more compared to printed or digital images.
Stars
747
Forks
43
Language
Python
License
AGPL-3.0
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/alephpi/Texo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
clusterzx/paperless-ai
An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure...
kha-white/manga-ocr
Optical character recognition for Japanese text, with the main focus being Japanese manga
alephpi/Texo-web
The web application for Texo, a minimalist SOTA LaTeX OCR model which contains only 20M...
bytefer/ollama-ocr
Implementing OCR with a local visual model run by ollama.
Dartvauder/NeuroSandboxWebUI
(Windows/Linux/MacOS) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on...