About
In this hands-on workshop, you will get an introduction to the handwritten text recognition application Transkribus. You will gain insight into the main features of the application, including how to create collections of digital images of historical documents, add metadata, navigate the workspace, share collections, and manage users.
You will acquire a basic understanding of machine learning for handwritten text recognition (HTR) and how to use public HTR models for your work. Building upon this, you can train your own model for layout and text recognition.
We will focus on getting used to the Transkribus web application and how to create and manage your own collection of digital images. We will look into how HTR works and what can - and cannot - be achieved through automatic text recognition with this tool.
We will provide practical advice and guidance tailored to your specific use of the platform.
Learning outcomes:
After attending this course, you will be able to:
- Use the Transkribus platform for the digitisation, AI-powered handwritten text recognition (HTR), transcription, and searching of historical documents you are researching.
- Understand how handwritten text recognition (HTR) works and have practised it
- Run layout detection and manual layout adjustment.
- Run text recognition using a public HTR model.
- Manually correct the output of automatic text recognition.
- Understand how to prepare for and run an HTR model training.
Registration:
Teachers
Annika Rockenberger, Alexandre Simon, Anne Sæbø, Lars Lørdahl
Course preparation
- Read more about Transkribus: https://www.transkribus.org
- Getting started with Transkribus: Registration & User Interface Overview
- You must bring a laptop with a browser like Microsoft Edge, Google Chrome or Firefox