Israeli Researchers Launch AI To Transcribe Geniza

Israeli researchers this week launched MiDRASH, an ERC-funded AI project led by the National Library of Israel to transcribe the Cairo Geniza's medieval manuscripts. Backed by a €10 million grant, the effort has begun digitizing hundreds of thousands of fragments and plans to process ten million additional images, with the full searchable corpus expected online within a year.
Key Points
- 1Trains AI to transcribe 400,000 Geniza fragments and scale to 10 million manuscript images.
- 2Unlocks medieval Hebrew, Aramaic, Judeo-Arabic, and Yiddish texts, revealing lost religious and social history.
- 3Enables searchable, comparable corpora for scholars, accelerating editions, citation mapping, and historical research.
Scoring Rationale
Large ERC-funded, open-source AI initiative unlocking vast medieval corpus; impact limited by niche manuscript domain and specialized scripts.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems

