Love Data Week Workshop: Exploring Archives with OCR (and LLMs)

Description

The development of large language models like ChatGPT has made it increasingly easy to get started with rendering printed historical texts machine readable—the stumbling block for many digital humanities projects. This workshop will introduce participants to the basics of the practice through an easy-to-learn and easy-to-customize workflow, enabling participants to turn pictures into searchable documents. No coding experience is necessary.

See the entire schedule of Johns Hopkins Data Services' Love Data Week.