Update app.py

app.py

@@ -32,12 +32,16 @@ def generate_response(prompt, max_tokens, temperature, top_p):
 
 def ocr_image(image_path):
     # Open the image from the file path
-    image = Image.open(image_path)
+    image = Image.open(image_path).convert("RGB")
+    
+    # Preprocess the image for the OCR model
     pixel_values = ocr_processor(images=image, return_tensors="pt").pixel_values
     
-    # Perform OCR
+    # Perform OCR inference
     outputs = ocr_model.generate(pixel_values)
-    text = ocr_processor.decode(outputs[0], skip_special_tokens=True)
+    
+    # Decode the generated tokens into text
+    text = ocr_processor.batch_decode(outputs, skip_special_tokens=True)[0]
     return text
 
 # Gradio UI