margret.jona.gisladottir · PyLaia · Published December 15, 2025

Jón Ólafsson from Grunnavík

Text Recognition

Description

Model for early 18th century Icelandic handwriting. It was trained on two handwritten manuscripts, AM 995 4to and JS 83 II fol. The base model was Icelandic late 18th century (experimental). The author and scribe of both of these manuscripts was Jón Ólafsson from Grunnavík (1705–1779). The script is kurrent and several abbreviations are used, such as f’ = ‘fyrer’ and ꝥ = ‘þad’ which have been suspended. The vowels with double acute, a̋ and ő, and with diaeresis, ï and j̈, kept as they are, but the letters ỏ and ø have been standardized to ö. The idea behind this author module is to make it easier to decode other manuscripts written by the prolific Icelandic scholar Jón Ólafsson. The model should also be useful for transcription of other handwritten text from the 18th century.

Try this model

Jón Ólafsson from Grunnavík
Use this modelOpen in Transkribus
Low error rate7.89% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 7.89% 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.

Words32,519
Lines3,675
Training Pages100
Model ID452705
Languages
Icelandic
Centuries
18th c.