Create app.py

app.py

@@ -0,0 +1,31 @@
+import gradio as gr
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+import requests
+from PIL import Image
+
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-printed")
+model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-printed")
+
+def process_image(image):
+    # prepare image
+    pixel_values = processor(image, return_tensors="pt").pixel_values
+
+    # generate (no beam search)
+    generated_ids = model.generate(pixel_values)
+
+    # decode
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+    return generated_text
+
+title = "Demo: TrOCR"
+
+#css = """.output_image, .input_image {height: 600px !important}"""
+
+iface = gr.Interface(
+            fn=process_image, 
+            inputs=gr.inputs.Image(type="pil"), 
+            outputs=gr.outputs.Textbox(),
+            title=title,
+        )
+iface.launch(debug=True)