L'équipe de l'APAD / Jean-Luc Lauzon · PyLaia · Published November 30, 2024
Les notaires montréalais: Basset, Bénigne Nouvelle-France, 17e siècle
Text Recognition
Description
Modèle développé avec le projet: "Donner le goût de l'archive à l'ère numérique" (https://donner-le-gout-de-larchive.weebly.com), de l’Université de Montréal, Bibliothèque et archives nationales du Québec, Société de recherches Archiv-Histo et l’Atelier Permanent d'analyse documentaire- Volet transcription. Modèle fait à partir des actes 1 à 600 du notaire Bénigne Basset du 1er octobre 1657 au 8 avril 1670.
This model was developed as part of the project ‘Donner le goût de l'archive à l'ère numérique’ (https://donner-le-gout-de-larchive.weebly.com) at the Université de Montréal, Bibliothèque et archives nationales du Québec, Société de recherches Archiv-Histo and Atelier Permanent d'analyse documentaire- Volet transcription. Based on deeds 1 to 600 by notary Bénigne Basset from October 1, 1657 to April 8, 1670.
Try this model
Use this modelOpen in Transkribus
Low error rate6.58% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 6.58% 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.
Words345,668
Lines57,518
Training Pages2,108
Model ID234109