Research + corpus-building uses. Benchmarks don’t count.
The drawers
A tool can be filed in more than one drawer
DRAWER I
AI & History
Machine learning, vision-language models and speech models. Every card here carries notes on where your sources go, how it was tested, and how it fails.
Guide cards
Counts research and corpus-building uses in the window, plus “I’m using this now” check-ins. Benchmarks don’t count.
tool · No. 015AI
eScriptorium
Open-source web platform for transcribing historical manuscripts and print: segment pages, run or train models, correct and export. Strong on Hebrew, Arabic and other non-Latin scripts.
At a glance
Maker
EPHE–PSL, Paris
Released
2018–19
Licence
Open source (MIT)
Cost
Free; self-host or use an institution’s server
Runs
Web app on a self-hosted or institutional server
Skill
No code to use; IT help to install
Historian’s notes
Where your sources goNo central cloud. Your sources stay on whichever server hosts it.
How it’s been testedError rates of 2.8–8.9% on medieval Hebrew manuscripts (Tikkoun Sofrim, DH2019).
Known problems on historical sourcesNeeds a good amount of consistent training data. Reading order fails on complex layouts. Vertical scripts are not supported.
Used in research0
No published research uses found yet. Using it in a project? Tell us.
Nobody has said they’re using it in 2026 yet.
“I’m using this now” asks you to sign in with ORCID.
One count per person per year; it adds to Trending, and names are never shown.