The Future of Information Extraction – Be Part of TUC 2024! ✨ Feb 15-16, In-Person and Online. Get your Ticket >>

Portuguese Handwriting 16th-19th century

Free Public AI Model for Handwritten Text Recognition with Transkribus

Portuguese Handwriting 16th-19th century

This is a generic model created in the framework of the TraPrInq Project (01.2022 to 07.2023) funded by the FCT (Portuguese Agency for Scientific Research), by a Luso-Brazilian team of paleographers: 
Hervé Baudry,  Susana Tavares Pedro, Carla Vieira, Jorge Ferreira Paulo, Leonor Dias Garcia,
Ana Margarida Dias da Silva, Maria Olinda Alves Pereira, Mário Soares Fatela, Marize Helena de Campos, Natalia Casagrande Salvador, Suzana Maria de Sousa Santos Severs .

This HTR-model is based on the trial records of the Portuguese Inquisition produced between 1536 (some documents even before) and 1821. It contains a careful transcription of 6226 pages (Validation Set: 505 p; Training Set: 5721 p) extracted from 830 processes, mainly by the Lisbon court, with a total of 1268040 words (VS: 107760 words; TS: 1160280).

Digitised files can be found on the search portal of the Portuguese National Archive (Arquivo Nacional da Torre do Tombo, Lisbon). The model proved its efficacy with documents from non-inquisitorial areas.

The transcription reproduces the spelling of words and abbreviations, uses special characters for baseline abbreviation signs and a single COMBINING MACRON for all superscript abbreviation signs, and modernises word separation.

The detailed transcription protocol and character list are available at: (scroll down to #4)

More info on the project at and

Model Overview

Portuguese Handwriting 16th-19th c.
Hervé Baudry and the TraPrInq Project Team
Model ID:
16th, 17th, 18th, 19th
Latin alphabet
CER on validation set:
5.20 %
Simply upload a picture and test this model

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

Portuguese Handwriting 16th-19th c. 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 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.