Repository Index

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

• extract-data
• layout-analysis
• ocr
• parser

OCR, layout analysis, reading order, table recognition in 90+ languages

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

• machine-learning
• transformer
• im2latex
• deep-learning

Translated[Captcha Recognition - Training] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.

• captcha-recognition
• tensorflow-tutorials
• ocr
• tensorflow

WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.

On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.