Transcribathon I: Arabic Texts

About

Arabic print has been relatively stable since the spread of the printing press in the 1800s, and an Automatic Text Recognition model that can transcribe such texts is therefore relevant for researchers using primary sources in the Arabic language for over two centuries.

The Transcribathon uses a late 19th-century clean print sample from the Muqtataf press in Cairo, Egypt. Once the transcribathon participants have developed a robust starting model based on this text, it will be available on Transkribus for further training on other Arabic print texts from different periods and presses.

This collaborative effort involves faculty and graduate students working on the Middle East at the Departments of Archaeology, Conservation and History (IAKH) and Culture, Religion, Asian and Middle Eastern Studies (IKOS), and the Faculty of Theology (TF). 

Programme

After a short introduction to the browser-based tool Transkribus, we will conduct three 45-minute transcription sprints. We will take screen breaks between the sprint sessions. The Transcribathon is closed with a wrap-up session where we look at how far we have gotten and which issues we have encountered and chart a way forward.

Victuals

We will serve hot and cold beverages & nibbles.

Host

The Transcribathon is organized by BærUt! Network and Skills Hub for Sustainable Digital Scholarly Editions.

BærUt! is a competence hub at the University of Oslo that promotes digital scholarly editions (DSEs). Our ambition is to consolidate expertise and knowledge in the field, gather researchers and practitioners, and, ultimately, create the foundation for a common platform for digital editions. We work closely with researchers, developers, and cultural institutions to digitize historical and cultural text documents and ensure these resources are accessible and useful for academic use.

Contact

For questions, please get in touch with BærUt!