Creator(s)
City Archives of Amsterdam
Language(s)
Centuries
18th
CER on Validation Set
5.4%
Size (Nr. of Words)
622,904
Model ID
48426
This is the first 18th Century general model created by the City Archives of Amsterdam. It is based on thousands of scans from in total 15 different notaries who worked in Amsterdam during the 18th Century. The number of trained words is 622904 and the CER is 7.50% on the validation set.
All notaries (except Van Hoorn and Van Esterwege) have 10 scans validation included (2671 scans training, 130 validation)):
Maten de Jonge (200)
Van Homrigh (127)
Zweerts (200)
Ardinois (200)
Pot (152)
Staal (300)
Van den Brink (300)
Van Esterwege (103)
Van Hoorn (58)
De Fremeri (231)
Barels de Jonge (110)
Des Pommare (110)
Van Loon (110))
Verleij (300)
Van Heel (300)
You can use this model to automatically transcribe Handwritten documents with Handwritten Text Recgnition in Transkribus.