Skip to content
  • Pricing
pierreq.dubois · PyLaia · Published June 7, 2026

Notaires du XVIIIe siècle – (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 381 456 provenant de sept notaires: François Rageot de Beaurivage (1707-1753) : 234 pages, Etienne Jeanneau (1691-1749) : 237 pages, Jean-Baptiste Adhémar (1714-1754) : 180 pages, Joseph Dionne (1741-1779) : 242 pages, Simon Sanguinet père (1748-1771) : 207 pages, Louis Pillard (1736-1767) : 193 pages, Jean-Baptiste Jenvrin-Dufresne (1733-1750) : 227 pages. 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) as part of the project "Nouvelle-France numérique (NFN)" : Collaborative partnership for research data management. The model is composed of a training set of 381,456 words from the minute-books of the following seven notaries: François Rageot de Beaurivage, Etienne Jeanneau, Jean-Baptiste Adhémar, Joseph Dionne, Simon Sanguinet père, Louis Pillard, Jean-Baptiste Jenvrin-Dufresne All the deeds selected have been transcribed in full except for the presentation pages, which do not contain enough text.

Try this model

Drag an image here

Select a file...

PNG or JPG up to 10 Mb

Wolpi
AI Assistant

By uploading an image, you accept our terms and privacy policy.

Notaires du XVIIIe siècle – (1691-1779)
Use this modelOpen in Transkribus
Very low error rate4.34% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 4.34% 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.

Words381,456
Lines56,743
Training Pages1,517
Model ID581909
Languages
French
Centuries
18th c.