This ground-truth text corpus is built from rare, early 20th-century Persian books printed in intricate Nastaliq script using lithography. It provides transcriptions cross-checked by native-speaking experts to support the training and fine-tuning of OCR and vision-language models (VLMs) on this challenging historical script.
Potential Use Cases
- OCR/VLM Training on Complex Nastaliq Script: Expert-verified ground-truth transcriptions can be used to train or fine-tune OCR and vision-language models (VLMs) to recognize the interconnected letters and complex forms of Persian Nastaliq script.
- Historical Persian Text Resource Development: Expert-verified transcriptions can be used to develop digital text resources from historical Persian Nastaliq documents, supporting text-based research on historical literature.