Create app.py

app.py

@@ -0,0 +1,31 @@
+import gradio as gr
+from PIL import Image
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+
+# Load model once
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
+model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
+
+def predict(image):
+    if image is None:
+        return "Please upload an image."
+
+    image = image.convert("RGB")
+
+    pixel_values = processor(images=image, return_tensors="pt").pixel_values
+    generated_ids = model.generate(pixel_values)
+
+    text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    return text
+
+# Gradio UI
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Textbox(label="Extracted Text"),
+    title="📝 Handwritten Text Recognition",
+    description="Upload a handwritten image and extract text using TrOCR model."
+)
+
+if __name__ == "__main__":
+    interface.launch()