Update app.py

app.py

@@ -1,26 +1,23 @@
-import gradio as gr
-import argparse
-import torch
-from PIL import Image
-from donut import DonutModel
-def demo_process(input_img):
-    global model, task_prompt, task_name
-    input_img = Image.fromarray(input_img)
-    output = model.inference(image=input_img, prompt=task_prompt)["predictions"][0]
-    return output
-parser = argparse.ArgumentParser()
-parser.add_argument("--task", type=str, default="Booking")
-parser.add_argument("--pretrained_path", type=str, default="result/train_booking/20241112_150925")
-args, left_argv = parser.parse_known_args()
-task_name = args.task
-task_prompt = f"<s_{task_name}>"
-model = DonutModel.from_pretrained("./result/train_booking/20241112_150925")
-if torch.cuda.is_available():
-    model.half()
-    device = torch.device("cuda")
-    model.to(device)
-else:
-    model.encoder.to(torch.bfloat16)
-model.eval()
-demo = gr.Interface(fn=demo_process,inputs="image",outputs="json", title=f"Donut 🍩 demonstration for `{task_name}` task",)
-demo.launch(debug=True)
+import gradio as gr
+import argparse
+import torch
+from PIL import Image
+from donut import DonutModel
+def demo_process(input_img):
+    global model, task_prompt, task_name
+    input_img = Image.fromarray(input_img)
+    output = model.inference(image=input_img, prompt=task_prompt)["predictions"][0]
+    return output
+parser = argparse.ArgumentParser()
+parser.add_argument("--task", type=str, default="SGSInvoice")
+parser.add_argument("--pretrained_path", type=str, default="uartimcs/donut-invoice-extract")
+args, left_argv = parser.parse_known_args()
+task_name = args.task
+task_prompt = f"<s_{task_name}>"
+
+
+
+model = DonutModel.from_pretrained("uartimcs/donut-invoice-extract")
+model.eval()
+demo = gr.Interface(fn=demo_process,inputs="image",outputs="json", title=f"Donut 🍩 demonstration for `{task_name}` task",)
+demo.launch()