Library/LaTeX-OCR
Library/LaTeX-OCRForked

lukas-blecher/LaTeX-OCR

LaTeX-OCR

pix2tex: Using a ViT to convert images of equations into LaTeX code.

Builder

lukas-blecher

lukas-blecher

lukas-blecher • individual

Stars

16,290

Using upstream star count

Forks

1,291

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Dec 11, 2020

Project creation date

README Summary

LaTeX-OCR (pix2tex) is a tool that uses a Vision Transformer (ViT) model to convert images of mathematical equations into LaTeX code. The project provides both a Python package and web interface for optical character recognition specifically designed for mathematical formulas and equations. It supports both handwritten and printed mathematical expressions with high accuracy.

AI Dev Skills

Unmapped

Vision Transformer ArchitectureOptical Character RecognitionSequence-to-Sequence ModelingComputer VisionMathematical Symbol RecognitionDeep LearningImage-to-Text Translation

Tags

Vision Transformer ArchitectureOptical Character RecognitionSequence-to-Sequence ModelingComputer VisionMathematical Symbol RecognitionDeep LearningImage-to-Text TranslationSelf-hostedMathematical Note TakingPublishingVision-Language ModelsAcademic ResearchEducationImageLaTeX Code GenerationOn-premiseAcademic Paper PreparationDocument ProcessingMultimodal ReasoningTextMathematical Equation DigitizationPython

Taxonomy

Recent Activity

Updated 1 years ago

7 Days

0

30 Days

0

90 Days

0

Quality

prototype
Quality
medium
Maturity
prototype

Categories

Dev Tools & AutomationPrimaryLearning ResourcesSearch & KnowledgeOther AI / MLRAG & RetrievalNLP & TextCoding & Dev ToolsMultimodal AIFoundation ModelsComputer Vision

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created
Dec 11, 2020
Forked
Mar 23, 2026
Your last push
1 years ago
Upstream last push
1 years ago
Tracked since
Jan 18, 2025

Similar Repos

pgvector cosine similarity · $0

Loading…