+ National Archives releases first version of a Dutch handwriting model

The digitisation team around Liesbeth Keyser from the National Archives in the Netherlands is working hard on creating training data for their collections in order to prepare HTR processing on a large scale. As a first result a model based on 475.769 words is now made available for Transkribus users. The model shows a Character Error Rate of 7.48% on the training set and 6.15% on the validation set. It is based on the careful transcription of dozens of different handwritings and comprises scans from the Incoming Documents from the Dutch East India Company (Overgekomen Brieven en Papieren van de VOC) of the National Archives of the Netherlands and of 19th century Notarial deeds from the Noord-Hollands archief.  The model is named: NAN/NHA_GT_M3+ Enjoy!

 

 

SHARE THIS ARTICLE

Recent Posts

November 17, 2022
Transkribus
We are thrilled to announce that yesterday, we hit 100,000 users on the Transkribus platform! Even with our years-long highly ...
August 12, 2022
Handwritten Text Recognition
Ever had trouble reading someone else’s handwriting?  Well, it may reassure you to know that it’s not only humans that ...
July 22, 2022
Uncategorized
The latest version of Transkribus Lite is here and brings a number of new features. Here are the most important ...