This model has a large train (1579200 words) and test set for German Kurrent (16th -18th century). The ground truth stems from different projects and partners and is biased towards Swiss documents. It is based on documents from a variety of archives and projects. Among others State Archives of Zurich (Stillstandsprotokolle, Ratsmanuale, Findmittel) and scholarly edition projects Königsfelden und Einsiedeln (Universitäten Zürich und Bern). The CER on the validation set is 8.42%.
- TranskribusTranskribus
Everything about Transkribus
Transkribus AppUse Transkribus in your Browser
Plans & PricingBuy Credits for Handwritten Text Recognition
Public AI ModelsExplore all publicly available models
metagrapho apiHandwritten Text Recognition api for Transkribus
Transkribus.aiText recognition with the click of a button
- ScanTent
- read&search
- AboutOur Members
See all of our great Members
Our TeamMeet the READ-COOP Team
Success StoriesHave a look at some exceptional Projects
- Resources
- Plans & Pricing