There is a newer version of the record available.

Published September 7, 2023 | Version pre-release
Software Open

CHAT models: Chinese Historical documents Automatic Transcription models

Description

This repository contains segmentation and transcription models for Chinese historical documents trained using the kraken OCR engine. This work is part of an ongoing project by the Numerica Sinologica consortium to build open-source digital tools for pre-modern Chinese studies.

Files

colibrisson/CHAT_models-pre-release.zip

Files (47.0 MB)

Name Size Download all
md5:73515cc5b293aed524dcfa9ab8334ffb
47.0 MB Preview Download

Additional details