Transkribus: Difference between revisions

From CJH Wiki
Jump to navigation Jump to search
No edit summary
No edit summary
Line 4: Line 4:


=Overview=
=Overview=
Transkribus harnesses artificial intelligence in handwriting and text recognition technology to decipher digitized assets that contain handwritten historical documents and printed texts.
Transkribus harnesses artificial intelligence to help decipher digitized handwritten and printed historical documents and texts.  
 
 


=Resources=
=Resources=
Read-Coop, the cooperative developers that created Transkribus, offer a variety of video documentation on using the artificial intelligence tool.
Read-Coop, the cooperative developers that created Transkribus, offers many recorded webinars and tutorials on using the artificial intelligence tool. There is also the [https://help.transkribus.org/ Transkribus Help Center], which offers extensive documentation and a search bar for troubleshooting.  
==Starting to use Transkribus==
==Starting to use Transkribus==
[https://www.youtube.com/playlist?list=PL7UbQtd4qlhIMP1KfdjGW3C-KXTxw4KYb Getting Started with Transkribus]
[https://www.youtube.com/playlist?list=PL7UbQtd4qlhIMP1KfdjGW3C-KXTxw4KYb Getting Started with Transkribus]
==More Advanced Webinars==
==More Advanced Webinars==
*[https://www.youtube.com/watch?v=ZXZkjEa45Ew Transkribus Table Models Webinar (English)]
*[https://www.youtube.com/watch?v=fTNL_nIY104 Using Public AI Models with Transkribus Webinar (English)]
*[https://www.youtube.com/watch?v=fTNL_nIY104 Using Public AI Models with Transkribus Webinar (English)]
*[https://www.youtube.com/watch?v=DZtjK3DMa3A Training a custom Transkribus model]
*[https://www.youtube.com/watch?v=tBotbgO1O9U Expert Text Recognition Model Training with Transkribus (English Webinar)]
*[https://www.youtube.com/watch?v=xxFoHuFWvGw Publishing with Transkribus Sites Webinar (English)]
*[https://www.youtube.com/watch?v=xxFoHuFWvGw Publishing with Transkribus Sites Webinar (English)]
*[https://www.youtube.com/watch?v=igseuPPfAdU Baseline Models & Complex Layouts Webinar (English)]
*[https://www.youtube.com/watch?v=igseuPPfAdU Baseline Models & Complex Layouts Webinar (English)]


==Past User Conferences==
==Past User Conferences==
*[https://www.youtube.com/playlist?list=PL7UbQtd4qlhKC9sjUd0YnZLWjrPH6z4Ph Transkribus User Conference 2020]
*[https://www.youtube.com/playlist?list=PL7UbQtd4qlhJDqxXVek5XIkFGRPtflkys Transkribus User Conference 2022]
*[https://www.youtube.com/playlist?list=PL7UbQtd4qlhJDqxXVek5XIkFGRPtflkys Transkribus User Conference 2022]
*[2023]
*[https://www.youtube.com/playlist?list=PL7UbQtd4qlhJov-NtX7EJP9JtIeIrZ5a1 Transkribus User Conference 2024]
*[https://www.youtube.com/playlist?list=PL7UbQtd4qlhJov-NtX7EJP9JtIeIrZ5a1 Transkribus User Conference 2024]


Line 23: Line 30:
*[https://libguides.uno.edu/supremecourtlouisiana/transkribus Historical Archives of the Supreme Court of Louisiana: Transkribus]
*[https://libguides.uno.edu/supremecourtlouisiana/transkribus Historical Archives of the Supreme Court of Louisiana: Transkribus]
*[https://blog.transkribus.org/en/how-radboud-university-implemented-transkribus-as-an-institutional-service Transkribus as an Institutional Service]
*[https://blog.transkribus.org/en/how-radboud-university-implemented-transkribus-as-an-institutional-service Transkribus as an Institutional Service]
*[https://muse.jhu.edu/pub/56/article/930877 From Digitization and Images to Text and Content: Transkribus as a Case Study]


==More information on Language Models and Super Models in Transkribus==
==More information on Language Models and [https://help.transkribus.org/super-models Super Models] in Transkribus==
*[https://medium.com/data-science-at-microsoft/how-large-language-models-work-91c362f5b78f How Large Language Models Work]
*[https://medium.com/data-science-at-microsoft/how-large-language-models-work-91c362f5b78f How Large Language Models Work]
*[https://blog.transkribus.org/en/what-are-super-models-and-how-do-they-work What are Super Models]
*[https://blog.transkribus.org/en/what-are-super-models-and-how-do-they-work What are Super Models]
===Selected List of Available Large Language Super Models===
Depending on the scope and desired outcome for a Transkribus project, using a language super model may be easier than training AI to transcribe.
*The Text Titan I (GER, DUT, FRE, FIN, ENG, SWE)
*Dutch Dean (DUT)
*Dansk Dokumentalist (DAN)
*German Genius (GEN)
*Polski Bizon (POL)
*English Elder (ENG)
*Faucon Français (FRE)
*Spanish Sage (SPA)
A complete list of language models is available [https://app.transkribus.org/models here].


=To request exported files=
=To request exported files=

Revision as of 18:43, 9 June 2025

The Center implemented Transkribus in the Summer of 2025, together with staff from our Partner institutions, for various pilot projects. The new technology is also being incorporated into reference and research requests in the Lillian Goldman Reading Room, Ackman & Ziff Genealogy Institute, and throughout the Center.

To log into Transkribus, please visit https://app.transkribus.org

Overview

Transkribus harnesses artificial intelligence to help decipher digitized handwritten and printed historical documents and texts.


Resources

Read-Coop, the cooperative developers that created Transkribus, offers many recorded webinars and tutorials on using the artificial intelligence tool. There is also the Transkribus Help Center, which offers extensive documentation and a search bar for troubleshooting.

Starting to use Transkribus

Getting Started with Transkribus

More Advanced Webinars


Past User Conferences

Other pilot projects and use cases


More information on Language Models and Super Models in Transkribus

Selected List of Available Large Language Super Models

Depending on the scope and desired outcome for a Transkribus project, using a language super model may be easier than training AI to transcribe.

  • The Text Titan I (GER, DUT, FRE, FIN, ENG, SWE)
  • Dutch Dean (DUT)
  • Dansk Dokumentalist (DAN)
  • German Genius (GEN)
  • Polski Bizon (POL)
  • English Elder (ENG)
  • Faucon Français (FRE)
  • Spanish Sage (SPA)

A complete list of language models is available here.

To request exported files

Ethical Guidelines examples for Use of Artificial Intelligence in Archives