YoHa2024NKU
Lab · part of the Ethiopian AI ecosystem
A fine-tuned TrOCR model for printed Tigrinya text recognition using the Ge'ez script. Adapted from microsoft/trocr-base-printed using vocabulary extension and Word-Aware Loss Weighting to resolve wor
0
models
0
datasets
1
repos
0
spaces
Footprint shape — each axis normalized against the ecosystem-wide maximum. A fuller polygon means this org publishes across every channel.
