Goals
Our group will pursue two aims:
To contribute training data focused on medieval Latin texts to the ground truth of the Carolingian Minuscule Model (CMM), which was originally created by Tim Geelhaar and is now housed at Transkribus and curated by the Institute for Medieval Research. This is a unique opportunity to contribute to the current main model for early medieval manuscripts.
To practice and evaluate workflows in different HTR platforms, such as Transkribus and eScriptorium, as well as Vision Language Models. Hybrid workflows will also be considered.
Requirements
The applicant should possess a sufficient knowledge of medieval Latin to correct the automatic transcription (e.g., recognising proper Latin words, separating words appropriately...).
The applicant has to have a good knowledge of Latin palaeography to resolve abbreviations, interpret ligatures, etc.
Supervisors
Cinzia Grifoni
Department of History, University of Vienna
Jeremy Thompson
Göttingen University
Gerda Heydemann
Friedrich Meinecke Insitut für Geschichte und Historische Kulturwissenschaften, Freie Universität Berlin