Update README.md

README.md

@@ -1,35 +1,30 @@
 ---
 license: apache-2.0
 language:
-- fa
+  - fa
 pipeline_tag: image-to-text
 widget:
-- src: https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/papers/attention.png
-  example_title: "Persian OCR"
+  - src: https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/papers/attention.png
+    example_title: "Persian OCR"
 ---
 
----
 # Persian-OCR
 
-Persian-OCR is a deep learning model for **Optical Character Recognition (OCR)** 
-designed specifically for Persian text. The model uses a **CNN + Transformer architecture** 
-trained with CTC loss to extract text from images.
+**Persian-OCR** is a deep learning model for **Optical Character Recognition (OCR)**, designed specifically for Persian text.  
+The model uses a **CNN + Transformer architecture** trained with **CTC loss** to extract text from images.
 
 ## Files
 
-- `pytorch_model.bin` : PyTorch model weights
-- `vocab.json` : Character vocabulary
-- `config.json` : Model configuration
+- `pytorch_model.bin` : PyTorch model weights  
+- `vocab.json` : Character vocabulary  
+- `config.json` : Model configuration  
 
 ## Installation
 
 ```bash
-!pip install torch torchvision huggingface_hub
-
+pip install torch torchvision huggingface_hub
 
 
-## Usage Example
-
 
 import torch
 import json
@@ -72,9 +67,13 @@ weights_path = hf_hub_download("farbodpya/Persian-OCR", "pytorch_model.bin")
 model = CNN_Transformer_OCR(num_classes=len(idx_to_char)+1)
 model.load_state_dict(torch.load(weights_path, map_location="cpu"))
 model.eval()
+
 # -----------------------------
-# 9️⃣ Example usage
+# 5️⃣ Example usage
 # -----------------------------
-img_path = "/content/Screenshot 2025-09-19 145016.png" 
+img_path = "sample.png"
 text = ocr_page(img_path, model, idx_to_char, visualize=True)
-print("\n=== Final OCR Page ===\n", text)
+print("\n=== Final OCR Page ===\n", text)
+
+
+