tetrak-hy-trainer
scattercode/tetrak-hy-trainer
Training pipeline for an Armenian text recogniser — synthetic data generation, CTC model training, and packaging as an EasyOCR custom model
armenian-nlpocrtext-recognitionctceasyocrmachine-learningsynthetic-datamodel-trainingcomputer-visionarmenian-language
Summary
Python training pipeline for an Armenian text recogniser built around synthetic data generation, CTC model training, and packaging as an EasyOCR custom model. The repository documents a trained and evaluated v6 model, provenance/release flow, and integration with a separate installable EasyOCR Armenian backend. It is niche but substantial, with clear architecture, evaluation notes, and real-world OCR utility for Armenian text.