yuan2005 · PyLaia · Published February 2, 2026

John Locke HTR Model

Text Recognition

Description

This Handwritten Text Recognition (HTR) model is specifically optimized for transcribing the manuscripts of the philosopher John Locke (1632–1704). It was trained using the "B2022 English Model M4" as a base model to ensure high stability. It is highly suitable for researchers working on Locke's correspondence and philosophical drafts.

Try this model

Use this modelOpen in Transkribus
Low error rate6.11% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 6.11% 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.

Words14,548
Lines2,092
Training Pages98
Model ID502557
Languages
EnglishLatin
Centuries
16th c.17th c.18th c.