Create app.py

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from PIL import Image
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+
+# Load the model and processor
+processor = TrOCRProcessor.from_pretrained("kkatiz/thai-trocr-thaigov-v2")
+model = VisionEncoderDecoderModel.from_pretrained("kkatiz/thai-trocr-thaigov-v2")
+
+# Define the prediction function
+def predict(image):
+    image = image.convert("RGB")
+    pixel_values = processor(image, return_tensors="pt").pixel_values
+    generated_ids = model.generate(pixel_values)
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    return generated_text
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Image(type="pil"),
+    outputs="text",
+    title="Thai Image-to-Text Prediction",
+    description="Upload an image, and the model will predict the text in the image.",
+)
+
+# Launch the app
+iface.launch()