The Future of Information Extraction – Be Part of TUC 2024! ✨ Feb 15-16, In-Person and Online. Get your Ticket >>

Ottoman Turkish Print

Free Public AI Model for Handwritten Text Recognition with Transkribus

Ottoman Turkish Print

This print model, developed by the Digital Ottoman Corpora team, is trained on a broad range of late 19th to early 20th-century Ottoman Turkish periodicals.

It follows the “half-transcription” Latinization scheme suggested by the Turkish Historical Association for late Ottoman-era prints.

Model Overview

Name:
Ottoman Turkish_Print_2
Creator:
Digital Ottoman Corpora Team led by Suphan Kirmizialtin
Model ID:
57485
Century:
19th, 20th
Languages:
Ottoman Turkish
Script:
Arabic (Ottoman Turkish)
Engine:
PyLaia
Material:
Print
CER on validation set:
7.6 %
Simply upload a picture and test this model

By uploading an image, you accept our terms and conditions and our privacy policy

Ottoman Turkish_Print_2 is freely available to everyone

Get started with Transkribus and use it for your own Material
You can use this model to automatically transcribe Print documents with Handwritten Text Recgnition in Transkribus. This model can be used in the Transkribus Expert Client as well as in Transkribus Lite.
This AI model was trained to automatically convert text from images of historical Arabic (Ottoman Turkish) documents into editable and searchable text.