5 projects
tetrak-translit
Detect, transliterate and fold Armenian, Georgian, Russian and Syriac text — ALA-LC, ISO 9985 and ISO 9984, BGN/PCGN, the Georgian national system, Hübschmann-Meillet and Western pronunciation, plus one canonical index form for cross-script search
tetrak-authority
A name authority from a dated Wikidata snapshot: variant names in every language, fold keys for retrieval and the VIAF, GND, ISNI and GeoNames identifiers, for catalogue search across scripts
tetrak
Local-first transcription pipelines for archival material, and the harnesses that measure them
tetrak-hy-trainer
Training pipeline for an Armenian text recogniser, packaged as an EasyOCR custom model
tetrak-easyocr-armenian
Armenian language support for EasyOCR — a trained recognition model, installable as a custom network
