1.3 : HTR fine tuning for medieval manuscripts models: strategies and evaluation

Durée : 00:39:51 -Réalisation : 23 juin 2022 -Mise en ligne : 6 octobre 2022
  • document 1 document 2 document 3
  • niveau 1 niveau 2 niveau 3
  • audio 1 audio 2 audio 3

par Sergio Torres Aguilar (ENC) et Vincent Jolivet (ENC)

In this presentation we intend to explore different practical questions about HTR modeling in order to determine at what point a model reaches the necessary robustness and a sufficiently broad-level of generalization to serve as a pre-trained base to raise a new specialized model. For this end, we use several HTR ground-truth documents from medieval cartularies and registers ranging from 12th to 15th centuries and we will evaluate two aspects: (1) the creation of robust models by trying to calculate the learning break‑point and the minimum amount of ground truth necessary to achieve good generalization performances from a limited collection of documents and (2) the process of fine‑tuning in the aim to quickly specialize a robust model, used here as a pre-trained base, on a type of source other than those used during training.

Lieu de réalisation
École nationale des chartes
Langue :
Yanet Hernandez (Montage), Sergio Torres Aguilar (Intervenant), Vincent Jolivet (Intervenant)
Conditions d'utilisation
Droit commun de la propriété intellectuelle
Citer cette ressource :
Sergio Torres Aguilar, Vincent Jolivet. ENC. (2022, 23 juin). 1.3 : HTR fine tuning for medieval manuscripts models: strategies and evaluation. [Vidéo]. Canal-U. (Consultée le 24 mars 2023)

Dans la même collection

Sur le même thème