This open model uses image-to-text recognition to transcribe handwritten historical Swedish documents. It is intended for archivists, historians, and developers building document digitization workflows.
In the Foundation models & chat space, Trocr Base Handwritten Hist Swe 2 takes a focused approach. It focuses on transcribing handwritten historical Swedish documents without manually reading and typing the text. Trocr Base Handwritten Hist Swe 2 is an open-source project aimed at digital archivists, historians, and machine-learning developers. Trocr Base Handwritten Hist Swe 2 is open source under the Open Source license. Trocr Base Handwritten Hist Swe 2 is available on the web and API, and it can be self-hosted.
It is developed by AI Riksarkivet / AIRA (Sweden). Among its 6 catalogued features are handwriting recognition, image-to-text transcription, and historical document OCR. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do