Winter school of Handwritten Text Recognition of Medieval Manuscripts
We are witnessing a revolution in the study of manuscripts: Machine learning tools have been developed to enable automatic transcription of documents. These tools are now able to assist in the production of texts from medieval manuscripts with a level of accuracy that was previously unattainable. Today, libraries have used these tools to make their collections searchable, while researchers have accelerated the process of text editing and adopted them for use in the study of medieval documents.
After last year‘s success, we continue this year with another HTR Winter School in Vienna, focusing on the automatic recognition of handwritten texts in medieval documents. The course will have two main parts: 2 online sessions (Friday afternoons) and a two-day in-person workshop in Vienna. In between, we will use online platforms to coordinate our work between the sessions: Notion.so and Discord. During the first phase, participants will be briefly introduced to the theory of handwritten text recognition and comprehensively instructed in its practical application using the tool Transkribus (transkribus.eu).
We will work in four groups, focusing on four different periods and languages: Carolingian Latin, Late Medieval Latin, Byzantine Greek, and Late Medieval Czech. Each group will have its own supervisor(s), and their goal will be to train an HTR model for each type of writing and/or to improve an existing model.
During the in-person workshop in Vienna, we will finalize the projects and visit libraries in Vienna to view selected manuscripts in person. At the end of the course you will receive a certificate and the results will be published on Zenodo and HTR-United with the names of the contributors.
The Winter School is very kindly supported by READ-COOP, the company behind Transkribus software.
SCHEDULE
SESSION 1, Nov 17, Friday
What is HTR? A general introduction
Transkribus 1 (uploading documents, layout recognition, simple transcription)
Introduction into manuscripts and working in groups
Working in groups
SESSION 2, Dec 15, Friday
Transkribus 2 (training of models)
Working in groups
JAN 29, Monday
Finishing work on the transcription and models
Sharing is caring: How to share your data
Alternatives to Transkribus
JAN 30, Tuesday
Library visit
Presentation of results by working groups