ephremishac · PyLaia · Published May 31, 2026
Garshuni-Arabic (Syriac Serto Script)
Text Recognition
Description
Model trained on several Garshuni-Arabic manuscripts, especially on colophons and the Syro-Coptic Synaxarion manuscript of Aleppo. This first public model of the Syriac-Arabic allography was prepared by Ephrem Aboud Ishac (IMAFO, Austrian Academy of Sciences, Vienna) in collaboration with Coptic monks in Egypt from the Monastery of Saint Mina (Western Desert, Alexandria) and the Monastery of Saint Anthony the Great (Eastern Desert, Red Sea Mountains), in the framework of the Austrian FWF Project: Identifying Scattered Puzzles of Syriac Liturgy Manuscripts (P 36649-G).
Try this model
Drag an image here
Select a file...PNG or JPG up to 10 Mb
Wolpi
AI Assistant
By uploading an image, you accept our terms and privacy policy.
Use this modelOpen in Transkribus
Very low error rate2.97% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 2.97% 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.
Words79,679
Lines19,312
Training Pages326
Model ID578529