The Future of Information Extraction – Be Part of TUC 2024! ✨ Feb 15-16, In-Person and Online. Get your Ticket >>

Dutch notarial 17th century super model_v2

Free Public AI Model for Handwritten Text Recognition with Transkribus

Dutch notarial 17th century super model_v2

Consisting of 18 different notarial handwritings from the 17th century (every handwriting consists of 73-3207 scans training material).

In total 11.783 scans training material and 375 scans validation material.
Notaries included: Bruijningh, Mathijsz, Schaef, De Winter, Westfrisius, Van der Groe, A. van de Ven, Van Sevenhoven, Des Pommare, Borsselaer, Pondt, De Vos, J. van de Ven, Venkel, Stafmaeker Varlet, Van Breugel, Lock and Doornick.

Collection: Amsterdam City Archives.

Model Overview

Name:
Notarial 17th Century Super Model_v2
Creator:
Amsterdam City Archives
Model ID:
40382
Century:
17th
Languages:
Dutch
Script:
Latin alphabet
Engine:
PyLaia
Material:
Handwritten
CER on validation set:
4.80 %
Simply upload a picture and test this model

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

Notarial 17th Century Super Model_v2 is freely available to everyone

Get started with Transkribus and use it for your own Material
You can use this model to automatically transcribe Handwritten documents with Handwritten Text Recgnition in Transkribus. This model can be used in the Transkribus Expert Client as well as in Transkribus Lite.
This AI model was trained to automatically convert text from images of historical Latin alphabet documents into editable and searchable text.