Skip to content
  • Pricing
Les Gardenotes - NFN · PyLaia · Published May 26, 2026

Notaires Nouvelle-France XVIIe siècle - (1634-1729)

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 513 017 mots provenant de 10 notaires: Guillaume Audouart dit St-Germain (1634-1663) : 198 pages, Romain Becquet, (1665-1682) : 152 pages, Gilles Rageot, (1666-1691) : 225 pages, Antoine Adhémar dit St-Martin, (1668-1714) : 214 pages, Claude Maugue (1677-1696) : 90 pages, Étienne Jacob (1680-1726) : 211 pages, François Genaple, (1682-1709) : 226 pages, Daniel Normandin, (1686-1729) : 221 pages, Louis Chambalon (1692-1716) : 184 pages, Jean-Baptiste Pottier (1699-1711) : 135 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 513 017 words from the minute-books of the following ten notaries: Guillaume Audouart dit St-Germain, Romain Becquet, Gilles Rageot, Antoine Adhémar dit St-Martin, Claude Maugue, Étienne Jacob, François Genaple, Daniel Normandin, Louis Chambalon, Jean-Baptiste Pottier. 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 Nouvelle-France XVIIe siècle - (1634-1729)
Use this modelOpen in Transkribus
Low error rate5.46% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 5.46% 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.

Words513,017
Lines70,316
Training Pages1,856
Model ID575869
Languages
French
Centuries
17th c.18th c.