Create app.py

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import torch
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+from PIL import Image
+import time
+
+MODEL = "microsoft/trocr-small-printed"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load once at startup
+processor = TrOCRProcessor.from_pretrained(MODEL)
+model = VisionEncoderDecoderModel.from_pretrained(MODEL).to(device)
+
+def extract_text(image):
+    if image is None:
+        return "⚠️ Please upload an image."
+
+    start_time = time.time()
+
+    if not isinstance(image, Image.Image):
+        image = Image.fromarray(image)
+
+    pixel_values = processor(images=image, return_tensors="pt").pixel_values.to(device)
+
+    generated_ids = model.generate(pixel_values)
+    text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+    runtime = round(time.time() - start_time, 2)
+
+    return f"""📝 Extracted Text:
+
+{text}
+
+⏱ Processed in {runtime} seconds
+"""
+
+demo = gr.Interface(
+    fn=extract_text,
+    inputs=gr.Image(type="pil", label="Upload Image"),
+    outputs=gr.Textbox(label="OCR Result"),
+    title="🖼 Image → Text Demo",
+    description="Upload an image with printed text. Powered by Microsoft TrOCR running locally on Hugging Face Spaces.",
+    examples=[
+        ["https://huggingface.co/datasets/nielsr/image_dummy/raw/main/receipt.png"]
+    ]
+)
+
+if __name__ == "__main__":
+    demo.launch()