General Portuguese

Free Public AI Model for Handwritten Text Recognition with Transkribus

General Portuguese

This is a combined model of two Portuguese sources housed at the Portuguese National Archive Torre do Tombo and State Archive of Bahia, Brazil.

There are handwritten and printed scripts of the Inquisition from Torre do Tombo together with the Notarial Books of Salvador da Bahia. To make the model even more general, a printed script from the middle of the 17th Century was added. Some documents are damaged.

This is the first attempt to create a general Portuguese Model with 64,842 words. Two different projects are working on the collections independently. As they progress in their work, new general models will be created, to attend to other collections.

Model Overview

Name:
General Portuguese M1
Creator:
Dr. Lucia Werneck Xavier
Model ID:
44949
Century:
17th
Languages:
Portuguese
Script:
Latin alphabet
Engine:
PyLaia
Material:
Handwritten, Print
CER on validation set:
3.80 %
Simply upload a picture and test this model

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

General Portuguese M1 is freely available to everyone

Get started with Transkribus and use it for your own Material
You can use this model to automatically transcribe Handwritten, Print documents with Handwritten Text Recgnition in Transkribus. This model can be used in the Transkribus Expert Client as well as in Transkribus Lite.
This AI model was trained to automatically convert text from images of historical Latin alphabet documents into editable and searchable text.