Text Recognition Python Packages

tika

Tika-Python is a Python binding to the Apache Tika™ REST services allowing Tika to be called natively in the Python community.

python-doctr

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

onnxtr

OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless, high-performing & accessible OCR

docling-ocr-onnxtr

OnnxTR OCR plugin for Docling

winocr

Windows.Media.Ocr

fastmrz

⚡Extracting the Machine Readable Zone (MRZ) from passport or any document images

meikiocr

high-speed, high-accuracy, local ocr for japanese video games

parisaocr

Open-source OCR for printed Persian: PP-OCR line detection and a Kraken recognizer trained on Persian books. پریسا اوسی‌آر: اوسی‌آر متن‌باز برای متن چاپی فارسی

mmocr

OpenMMLab Text Detection, Recognition and Understanding Toolbox

documentai-std

DocumentAI-std is a Python library designed to facilitate and standardize document analysis and processing tasks. It offers functionality for handling document elements, performing optical character recognition (OCR), and managing document datasets.

trdg

A synthetic data generator for text recognition

vkit-nightly

Boosting Document Intelligence

torchfree-ocr

This package is EasyOCR-based optical character recognition. Unlike EasyOCR, the package uses a pre-saved with onnx language models, so it doesn't need a 1-2 Gb pytorch dependency. This is particularly useful for developing and packaging light-weight applications that utilize text recognition.

netra-ocr

A Squeeze-and-Excitation Transformer Network for Khmer Optical Character Recognition

turboocr-engine-cpu

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

nano-ocr

A Lightweight OCR model and Engine for low computation devices, edge applications and embedded system

natocr

Python wrapper around the Native OCR engines that ship with macOS and Windows

synthtiger

Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021

htrflow

HTRflow is the underlying engine for our HTR-pipeline

turboocr-engine-openvino

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

scanlayer

A Python library around Tesseract OCR that turns a scan or photo into a searchable PDF, or exports raw OCR as text, JSON, TSV, or hOCR with automatic deskew, noise reduction, and multi-column reading order.

sinapsis-ocr

Sinapsis templates supporting different OCR techniques

sinapsis-easyocr

Sinapsis templates supporting different OCR techniques

apparser

Apparser is a Python library for automating desktop applications and interacting with UIs using AI-powered tools such as OCR and object detection models.