pierreq.dubois · PyLaia · Published July 14, 2025
Notaires (6) début 18e siècle de la Nouvelle-France (1691-1779)
Text Recognition
Description
[English version below]
Modèle développé par le regroupement Les Gardenotes (Québec,CA) (lesgardenotes.org) dans le cadre du projet Nouvelle-France numérique (NFN) : Partenariat collaboratif de gestion des données de recherche (nouvellefrancenumerique.info/).
Le modèle est composé de : jeu d'entraînement de 315 935 mots provenant de: 235 pages de François Rageot de Beaurivage, 234 pages d'Etienne Jeanneau, 179 pages de Jean-Baptiste Adhémar, 180 pages de Joseph Dionne, 209 pages de Simon Sanguinet père et de 195 pages de Louis Pillard.
Tous les actes choisis ont été transcrits au complet sauf les pages de présentation qui ne contiennent pas assez de texte. Transcription : Les Gardenotes. Entraînement du modèle : Pierre Dubois. Graphie des notaires : https://lesgardenotes.org/ressources/
[English version]
Model developed by the group “Les Gardenotes” (Quebec,CA) (lesgardenotes.org) as part of the project "Nouvelle-France numérique (NFN)" : Collaborative partnership for research data management (nouvellefrancenumerique.info/). The model is composed of a training set of 315 935 words from the minute-books of the following six notaries: François Rageot de Beaurivage, Etienne Jeanneau, Jean-Baptiste Adhémar, Joseph Dionne, Simon Sanguinet père and Louis Pillard.
All the deeds selected have been transcribed in full except for the presentation pages, which do not contain enough text.
Try this model
Use this modelOpen in Transkribus
Very low error rate4.86% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 4.86% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. This is a larger model trained on diverse material, which generally makes it more robust across different handwriting styles. That said, larger training sets also make it harder to push the CER down further.
Measured on the model's own validation data. Results on your documents may differ depending on handwriting style, document condition, language, and how closely your material resembles the training data.
Words315,935
Lines47,305
Training Pages1,232
Model ID372105