Transkribus · PyLaia · Published July 4, 2023

Test model Chinese

Text Recognition

Description

This is a first test model for Chinese texts using all available ground truth material within the platform trained by the Transkribus team. It is primarily meant to be used as a basemodel to enhance custom Chinese HTR models. If you're able to provide more Chinese ground truth material or you want to publish your own Chinese model, please let us know via info@readcoop.eu.

Try this model

Use this modelOpen in Transkribus
Low error rate7.5% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 7.5% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material.

Measured on the model's own validation data. Results on your documents may differ depending on handwriting style, document condition, language, and how closely your material resembles the training data.

Words16,557
Lines9,645
Training Pages374
Model ID53245
Languages
Chinese