lali_kakhidze · PyLaia · Published March 7, 2026
German_Kurrent_XIX_NAG_GEO_ISU (V2.0)
Text Recognition
Description
This model trained with an archival documents about German Colonists in Georgia in frame of a PhD research at Ilia State University (ISU), Tbilisi, Georgia. These documents are preserved in National Archives of Georgia (NAG) with open access. Research data are handwritten German language sources (in Kurrentschrift) about Katharinenfeld. Time period XIX (XX) century. This model is suitable for archival documents in German Kurrentschrift (used in Kaukasus). Model trained by Lali Kakhidze.
Try this model
Use this modelOpen in Transkribus
Low error rate9.67% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 9.67% 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.
Words36,792
Lines6,801
Training Pages170
Model ID526017