Project Donner le goût de l'archive à l'ère numérique · PyLaia · Published January 11, 2023

Notaires montréalais: Adhemar, A (Nelle-France 17e s.) / Montreal notaries: Adhemar (New-Fr...

Text Recognition

Description

Model developed by the partnership project: "Donner le goût de l'archive à l'ère numérique"/ "Giving a taste of the archives in the digital age" (https://donner-le-gout-de-larchive.weebly.com), from Université de Montréal, Université du Québec à Rimouski and Université de Sherbrooke, Bibliothèque et archives nationales du Québec, Société de recherches Archiv-Histo and Atelier Permanent d'analyse documentaire- Volet transcription. Contains the difficult handwriting of Antoine Adhemar dit Saint-Martin (1639-1714) whose exceptional longevity as a notary (1668-1714) made him one of the most important notaries in New-France. Data were trained on 146 pages extracted from 31 of the 35 Registres du Bailliage de Montréal and Adhemar’s own notary clerk’s office (32091 pages/ 9440 deeds).

Try this model

Use this modelOpen in Transkribus
Low error rate8.1% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 8.1% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material.

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.

Words21,072
Lines3,442
Training Pages133
Model ID49239
Languages
French