Create app.py

app.py

@@ -0,0 +1,67 @@
+from transformers import pipeline
+from PIL import Image
+import gradio as gr
+
+# Initialize TrOCR pipeline for specialized OCR
+ocr_pipeline = pipeline("image-to-text", model="microsoft/trocr-base-printed")
+
+def extract_text_from_image(image):
+    if image is None:
+        return "No image provided. Please upload an image file."
+    
+    try:
+        # Convert Gradio image to PIL Image
+        pil_image = Image.fromarray(image)
+        
+        # Extract text from image using TrOCR
+        result = ocr_pipeline(pil_image)
+        
+        # Return the extracted text
+        return result[0]['generated_text']
+    except Exception as e:
+        return f"Error during text extraction: {str(e)}"
+
+# Gradio interface
+with gr.Blocks(title="Image Text Extractor") as demo:
+    gr.Markdown("# 📷 Image Text Extractor")
+    gr.Markdown("Extract text from images using Microsoft's TrOCR model")
+    
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(
+                type="numpy",
+                label="Upload Image"
+            )
+            extract_btn = gr.Button("Extract Text", variant="primary")
+            
+        with gr.Column():
+            text_output = gr.Textbox(
+                lines=10,
+                label="Extracted Text",
+                interactive=False
+            )
+    
+    extract_btn.click(
+        extract_text_from_image,
+        inputs=image_input,
+        outputs=text_output
+    )
+    
+    gr.Examples(
+        examples=[
+            ["example1.jpg"],
+            ["example2.png"]
+        ],
+        inputs=[image_input],
+    )
+    
+    gr.Markdown("### About This Model")
+    gr.Markdown("- **Model**: [microsoft/trocr-base-printed](https://huggingface.co/microsoft/trocr-base-printed)")
+    gr.Markdown("- **Task**: Optical Character Recognition (OCR)")
+    gr.Markdown("- **Architecture**: Transformer-based OCR (TrOCR)")
+    gr.Markdown("- **Capabilities**: Specialized for printed text extraction")
+    gr.Markdown("- **Note**: First processing may take 15-25 seconds (model loading)")
+    gr.Markdown("- **Supported Formats**: JPG, PNG, JPEG")
+
+if __name__ == "__main__":
+    demo.launch()