Update app.py

app.py

@@ -1,3 +1,5 @@
+import os
+import tempfile
 from hezar.models import Model
 from hezar.utils import load_image, draw_boxes
 from transformers import TrOCRProcessor, VisionEncoderDecoderModel
@@ -12,13 +14,13 @@ trocr_model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-ha
 
 def recognize_handwritten_text(image):
     try:
-        # Ensure image is a PIL image and convert to NumPy array
-        if not isinstance(image, Image.Image):
-            image = Image.fromarray(np.array(image)).convert("RGB")
-        image_np = np.array(image)
+        # Save the uploaded image to a temporary file
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp_file:
+            image.save(tmp_file.name, format="JPEG")
+            tmp_path = tmp_file.name
         
-        # Load image with hezar utils
-        processed_image = load_image(image_np)
+        # Load image with hezar utils using file path
+        processed_image = load_image(tmp_path)
         
         # Detect text regions with CRAFT
         outputs = craft_model.predict(processed_image)
@@ -47,7 +49,11 @@ def recognize_handwritten_text(image):
         return result_pil, f"Recognized text: {text_data}"
     
     except Exception as e:
-        return Image.fromarray(image_np), f"Error: {str(e)}"
+        return Image.fromarray(np.array(image)), f"Error: {str(e)}"
+    finally:
+        # Clean up temporary file
+        if 'tmp_path' in locals():
+            os.unlink(tmp_path)
 
 # Create Gradio interface
 interface = gr.Interface(