Create app.py

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+from transformers import AutoProcessor, AutoModelForImageTextToText
+from PIL import Image
+
+# Load Meta-Llama Vision-Instruct model
+processor = AutoProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
+model = AutoModelForImageTextToText.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
+
+def extract_text_from_image(image):
+    """
+    Function to extract text from a handwritten image using the Meta-Llama model.
+    """
+    try:
+        # Preprocess the image
+        inputs = processor(images=image, return_tensors="pt").to("cuda")
+        
+        # Generate predictions
+        outputs = model.generate(**inputs)
+        
+        # Decode the generated text
+        extracted_text = processor.decode(outputs[0], skip_special_tokens=True)
+        
+        return extracted_text
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+# Define Gradio interface
+title = "Handwritten Text Extraction"
+description = """
+Upload a handwritten image, and this app will use Meta-Llama Vision-Instruct to extract text from the image.
+"""
+
+demo = gr.Interface(
+    fn=extract_text_from_image,
+    inputs=gr.Image(type="pil", label="Upload Handwritten Image"),
+    outputs=gr.Textbox(label="Extracted Text"),
+    title=title,
+    description=description,
+)
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)