feat: app.py created with text and imports

app.py

@@ -0,0 +1,42 @@
+import torch
+
+from PIL import Image
+from transformers import VisionEncoderDecoderModel, VisionEncoderDecoderConfig  # , DonutProcessor
+
+
+def demo_process(input_img):
+    global pretrained_model, task_prompt, task_name
+    # input_img = Image.fromarray(input_img)
+    output = pretrained_model.inference(image=input_img, prompt=task_prompt)["predictions"][0]
+    return output
+
+task_prompt = f"<s>"
+
+st.text('This model is trained with receipt images -> SROIE dataset.')
+ 
+"""image = Image.open("./sample_image_1.png")
+image.save("receipt1.png")
+image = Image.open("./sample_image_2.png")
+image.save("receipt2.png")
+
+pretrained_model = VisionEncoderDecoderModel.from_pretrained("unstructured/donut-base-sroie")
+pretrained_model.encoder.to(torch.bfloat16)
+pretrained_model.eval()
+
+# replace for streamlit widgets
+demo = gr.Interface(
+    fn=demo_process,
+    inputs= gr.inputs.Image(type="pil"),
+    outputs="json",
+    title=f"Donut 🍩 demonstration for `cord-v2` task",
+    description="""This model is trained with 800 Indonesian receipt images of CORD dataset. <br>
+Demonstrations for other types of documents/tasks are available at https://github.com/clovaai/donut <br>
+More CORD receipt images are available at https://huggingface.co/datasets/naver-clova-ix/cord-v2
+More details are available at:
+- Paper: https://arxiv.org/abs/2111.15664
+- GitHub: https://github.com/clovaai/donut""",
+    examples=[["receipt1.png"], ["receipt2.png"]],
+    cache_examples=False,
+)
+
+demo.launch()"""