intermediateactive

Texo

A minimalist SOTA LaTeX OCR model which contains only 20M parameters and runs in browser. Containing full training pipeline suitable for self-study. | 超轻量SOTA LaTeX公式识别模型,20M参数量,可在浏览器中运行。包含训练全流程代码,适合自学。

Author:alephpi
Stars:301
Language:Python
Updated:November 8, 2025

Texo

A minimalist SOTA LaTeX OCR model which contains only 20M parameters and runs in browser. Containing full training pipeline suitable for self-study. | 超轻量SOTA LaTeX公式识别模型,20M参数量,可在浏览器中运行。包含训练全流程代码,适合自学。

Overview

Texo Logo

Key Features

  • computer-vision
  • deep-learning
  • distillation-model
  • formula
  • formulanet
  • hydra
  • latex
  • latex-ocr
  • machine-learning
  • math
  • math-formula-recognition
  • ocr
  • ocr-recognition
  • python
  • pytorch
  • pytorch-lightning
  • transformers
  • unimernet
  • vision-encoder-decoder

Statistics

  • ⭐ Stars: 301
  • 🍴 Forks: 13
  • 📝 Language: Python
  • 📜 License: AGPL-3.0

Links

Getting Started

Visit the GitHub repository for installation instructions and documentation.


This project information was automatically generated from GitHub. Last updated: 11/8/2025

Related Projects

FeaturedAdvancedActive
180

DeepSeek OCR

Extract text from images and documents with unprecedented accuracy using DeepSeek OCR's state-of-the-art deep learning models.

By TimmyOVO
PythonApache-2.0
IntermediateActive
12

Deep ORC App

Transform physical documents into digital text with Deep ORC App's state-of-the-art optical character recognition technology.

By Rohan Dumasia
PythonMIT
IntermediateActive
320

Chonkie

Optimize your text processing workflows with Chonkie - a high-performance library for intelligent document chunking and segmentation.

By Chonkie Inc
PythonApache-2.0