DARIAH EUHow do you correct things when the #AutomatedTextRecognition goes wrong? This module in the broader #ATRMadeEasy curriculum on #DARIAHCampus gives a helping hand, this #TrainingTuesday
Annika Rockenberger (she/they)🧵 2/ Continuing w/ a guidance session on how to use #Transkribus for #AutomatedTextRecognition where there are no or only a few public models available, this time for medieval #French #Latin & #Occitane. #HTR and #OCR are a common topics all across the Humanities and related disciplines and the Uni Oslo Library is about to become a member organisation of READCoop
I wrote a blog post about my quick shot test of #AutomatedTextRecognition #HTR using #OpenAI #ChatGPT4 on the #EthicaComplementoria print from 1674: https://greflinger.hypotheses.org/739
Automated Text Recognition with ChatGPT 4
During a presentation for the Digital Meetup at the Department of Archaeology, Conservation and History, the historian Ian Milligan (University of Waterloo) mentioned briefly the stunning results he got when using ChatGPT for automated text recognition of historical documents. I don’t remember which materials he had used, but I was keen to try it out […]
🧵 3/ #ResearchSupportPartnershipUiO continues after lunch w/ my "adopted" colleagues from the #History section. I had a coordinating & getting-to-know meeting to set up some presentations and show-and-tell sessions for the Depts. #DigitalMeetup that happens every #Tuesday. I offered to do short sessions on #TaDiRAH, #Transkribus, #Tropy and #Tesseract during the fall. I'll use the 1678 #Danish translation of the #EthicaComplementoria as an example for #AutomatedTextRecognition of C17th books!