OCR to extract text from images

A simple OCR Model that can easily extract text from an image.

GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.

Convert documents to markdown, extract raw text, and locate specific content

Convert PDF to markdown + JSON quickly with high accuracy

Detect and transcribe text in images with accurate bounding boxes, layout analysis, reding order, and table recognition, in 90 languages

Surya is a document OCR toolkit that does:

Nougat: Neural Optical Understanding for Academic Documents

End-to-End Document Image Enhancement Transformer

Convert scanned or electronic documents to markdown, very very very fast

Extract structured data from receipt images using Donut 🍩 (Document Understanding Transformer)

Document Image Parsing via Heterogeneous Anchor Prompting

Optical character recognition to turn images of latex equations into latex format.

Performs document image classification, document parsing and document visual question answering

PII Data Extraction from Text

LLaMA 3.1-8B, finetuned on a synthetic OCR dataset for superior OCR correction.