Model HTR Latin Sermons 11th–12th C.: Metodologie, transkripce, testování a evaluace
Model HTR Latin Sermons 11th–12th C.: Methodology, Transcription, Testing, and Evaluation
Author(s): Michaela Falátková, Barbora KulhováSubject(s): Studies of Literature, Middle Ages, Methodology and research technology, ICT Information and Communications Technologies, History of Sciences
Published by: Univerzita Hradec Králové, Filozofická fakulta
Keywords: HTR; Latin homilies; medieval manuscripts; Transkribus; Digital Humanities;
Summary/Abstract: This study introduces the methodology behind creating a Handwritten Text Recognition (HTR) model for Latin homilies from the 11th–12th centuries. The Latin Sermons 11th–12th C. model was trained on data originating from eight manuscripts held in libraries across five European countries, written in late Carolingian and early Gothic minuscule. The article focuses on preparing training data, selecting transcription rules, and testing parameters such as data volume, number of epochs, and the use of a base model. The final model achieved a Character Error Rate (CER) of 5.7 % and demonstrated high adaptability, thereby opening new possibilities for use within Digital Humanities.
Journal: Historia Aperta
- Issue Year: 2025
- Issue No: 54
- Page Range: 9-33
- Page Count: 25
- Language: Czech
