Manual transcription → eScriptorium
Princeton University
The Cairo Geniza is a vast trove of medieval manuscripts documenting Jewish life across North Africa and the Middle East. In over 130 years, scholars had manually transcribed only about 5,000 of an estimated 30,000 documentary fragments. To break the bottleneck, Princeton's HTR4PGP project adopted eScriptorium to automate transcription of the remaining fragments in Hebrew, Aramaic and Judeo-Arabic. Working with torn fragments, informal hands and text blocks set at odd angles, the team pursued a 90% accuracy target. Moving from manual transcription to HTR dramatically accelerated access, rendering large swathes of the Geniza searchable for historians for the first time.
Original source
Handwritten Text Recognition — Princeton Geniza Lab (HTR4PGP)
Princeton Geniza Lab
The archived copy opens a snapshot on the Internet Archive's Wayback Machine, preserved for when the original moves or disappears.
The Archive Migration Review summarises this story in its own words and links to the original source for verification. We are editorially independent and not affiliated with the institution or software project named above. Summaries are compiled in good faith from publicly available accounts; corrections are welcome.