Handwriting Recognition Python Packages

ko-hand-ocr

Korean handwriting OCR — a 36M-param model trained from scratch on synthetic data only. No handwriting dataset, no inherited license terms. CPU-only.

hwrt

A toolset for handwriting recognition

ocr-tamil

OCR Tamil is a powerful tool that can detect and recognize text in Tamil images with high accuracy on Natural Scenes

manyhands

Run several local OCR models over the same page and show which words they disagree on. Nothing leaves the machine.

tagsort

Open-source engine that reads handwritten or printed specimen ID tags in photos, in any orientation. Returns tag text, position, angle and a calibrated confidence score. Lightweight ONNX core, versioned JSON contracts and pluggable backends, built to embed in mobile, web and research apps.

mcp-server-google-vision

MCP server providing OCR capabilities to LLMs via Google Cloud Vision API - Read scanned PDFs, handwritten text, and images with any orientation

tabellio

Image of a civil-registry / parish record to validated structured JSON. BYOK, provider-agnostic, no embedded model, no storage.

pycasia

A python library to work with the CASIA Chinese handwriting database.

lafhterlearn

Deep learning toolkit for building handwritten word recognition system without labeled data

numiner

MNIST like dataset creation tool for Handwritten Text Recognition.

keras-htr

A toolkit for training CNN-1DRNN-CTC model to perform line-level Handwritten Text Recognition

zpe-ink

Python .zpink digital-ink codec — bit-exact roundtrip on UJI, CROHME, DigiLeTs (Hausdorff = 0.0 px). PyPI: zpe-ink v0.1.1.