Update Arabic-HLR-Model/README.md

Arabic-HLR-Model/README.md

@@ -25,7 +25,7 @@ pipeline_tag: image-to-text
 ## Model Description
 A lightweight DenseNet121-Transformer architecture for Arabic handwritten line recognition,
 pre-trained on the Kurdish DASTNUS dataset and fine-tuned on the KHATT Arabic handwritten dataset.
-Uses a triple unified vocabulary covering Kurdish, Arabic, and Urdu scripts (192 tokens). The KHATT dataset is publicly available at https://www.kaggle.com/datasets/iraqyomar/khatt-arabic-hand-written-lines/code
+Uses a triple unified vocabulary covering Kurdish, Arabic, and Urdu scripts (192 tokens). The KHATT dataset is publicly available at https://www.kaggle.com/datasets/iraqyomar/khatt-arabic-hand-written-lines/code (We only used Unique Handwritten Lines)
 
 ## Architecture
 - **CNN Backbone:** DenseNet-121 (pretrained on ImageNet)