The challenges of HTR model training: Feedbacks from the project Donner le gout de l'archive a l'ere numerique

The arrival of handwriting recognition technologies offers new possibilities to research in heritage studies. However, it is now necessary to reflect on the experiences and the practices developed by research teams. Our use of the Transkribus platform since 2018 has led us to search for the most significant ways to improve the performance of our handwritten recognition models (HTR) which are made to transcribe French handwriting dating from the 17th century. This article therefore reports on the impacts of creating transcribing protocols, using the lexical elements at full scale and determining the best way to use base model in order to help to increase the performance of HTR models. Combining all of these elements can indeed increase the performance of a single model by more than 20% (reaching a Character Error Rate below 5%). It also discusses some challenges regarding the collaborative nature of HTR platforms such as Transkribus and the way researchers can share their data generated in the process of creating or training handwritten text recognition models.