Skip to content
  • Pricing
b.j.m.caers · PyLaia · Published December 3, 2024

Middle Dutch Book Hands, 14th-15th Ct

Text Recognition

Description

Model trained on various Middle Dutch hands in manuscripts dating to the fourteenth and fifteenth centuries. Manuscripts contained text in verse as well as prose. Model was trained to solve common abbreviations, in the sense that abbreviations were spelled out in transcriptions and tagged. Automated transcriptions will attempt to solve abbreviations.

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.

Middle Dutch Book Hands, 14th-15th Ct
Use this modelOpen in Transkribus
Very low error rate3.88% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 3.88% 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.

Words64,513
Lines10,246
Training Pages136
Model ID236429
Languages
Dutch Middle (ca.1050-1350)Dutch
Centuries
14th c.15th c.