Skip to content
  • Pricing
homor.peter · PyLaia · Published April 21, 2026

Hungarian Higher Education Council Minutes

Text Recognition

Description

This specialized Handwritten Text Recognition (HTR) model is designed for Hungarian cursive manuscripts, specifically late 19th and early 20th-century institutional records. The model was trained on a 571-page dataset from the Royal Hungarian Agricultural Academy Council Minutes in Magyaróvár (1884–1909). As a reliable research tool for documents from similar periods, this model is an excellent choice for both targeted archival projects and broader historical digitization initiatives.

Try this model

Drag an image here

Select a file...

PNG or JPG up to 10 Mb

Wolpi
AI Assistant

By uploading an image, you accept our terms and privacy policy.

Hungarian Higher Education Council Minutes
Use this modelOpen in Transkribus
Very low error rate4.46% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 4.46% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. This is a larger model trained on diverse material, which generally makes it more robust across different handwriting styles. That said, larger training sets also make it harder to push the CER down further.

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.

Words112,062
Lines20,890
Training Pages571
Model ID553657
Languages
Hungarian
Centuries
19th c.20th c.