Update README.md

README.md

@@ -30,14 +30,25 @@ Qaari 0.1 Urdu is a fine-tuned version of [Qwen/Qwen2-VL-2B](https://huggingface
 | vs. Qwen Base | 97.35% | 98.32% | 91.55% |
 | vs. Tesseract | 86.25% | 87.11% | 82.60% |
 
-## Use Cases
 
-- Document digitization for Urdu texts
-- Historical manuscript preservation
-- Automated data entry from Urdu documents
-- Academic research on Urdu texts
-- Government document processing
-- Digital libraries for Urdu literature
+## Supported Fonts
+The model was fine-tuned on the following fonts:
+- AlQalam Taj Nastaleeq Regular
+- Alvi Nastaleeq Regular
+- Gandhara Suls Regular
+- Jameel Noori Nastaleeq Regular
+- NotoNastaliqUrdu-Regular
+
+## Supported Font Sizes
+The model has been tested and optimized for the following font sizes:
+- 14pt
+- 16pt
+- 18pt
+- 20pt
+- 24pt
+- 32pt
+- 40pt
+
 
 ## Usage
 
@@ -64,10 +75,12 @@ print(text)
 
 ## Limitations
 
-- Designed specifically for Urdu text recognition; may not perform optimally for other languages
-- Performance may vary with image quality, font styles, and background noise
-- Works best with clear, well-lit images of printed Urdu text
-- May struggle with handwritten Urdu text with significant variations
+- Performance may degrade when using fonts not included in the fine-tuning dataset
+- Font sizes outside the supported range may result in suboptimal rendering
+- The model may not handle complex ligatures in non-Nastaleeq scripts effectively
+- Performance on digital-only displays has not been fully optimized
+- Low-resolution print environments might experience quality degradation
+- Custom font modifications or non-standard Nastaleeq variants might not render as expected
 
 ## Training Details
 
@@ -76,15 +89,14 @@ This model was fine-tuned from Qwen2-VL-2B using a dataset of Urdu text images w
 ### Training Dataset
 
 - **Dataset Type**: Paired Urdu text images with ground truth transcriptions
-- **Size**: [Insert dataset size]
-- **Source**: [Insert source information if public]
+- **Size**: 10,000
+- **Source**: Syntehtic Dataset
 
 ### Training Configuration
 
 - **Base Model**: Qwen/Qwen2-VL-2B
-- **Training Framework**: [Insert framework used, e.g., HuggingFace Transformers]
-- **Hardware**: [Insert training hardware details]
-- **Training Time**: [Insert approximate training time]
+- **Hardware**: A6000 GPU 
+- **Training Time**: 24 Hours
 
 ## Citation
 
@@ -92,11 +104,11 @@ If you use this model in your research, please cite:
 
 ```
 @misc{qaari-0.1-urdu,
-  author = {[Your name]},
+  author = {Ahmed Wasfy},
   title = {Qaari 0.1 Urdu: OCR Model for Urdu Language},
   year = {2025},
   publisher = {HuggingFace},
-  howpublished = {\url{https://huggingface.co/your-username/qaari-0.1-urdu}}
+  howpublished = {\url{https://huggingface.co/oddadmix/Qaari-0.1-Urdu-OCR-Qwen2VL-2B}}
 }
 ```
 
@@ -104,6 +116,3 @@ If you use this model in your research, please cite:
 
 This model is subject to the [license terms](https://huggingface.co/Qwen/Qwen2-VL-2B/blob/main/LICENSE) of the base Qwen2-VL-2B model.
 
-## Contact
-
-[Your contact information or preferred way for users to reach out with questions or feedback]