create app.py

app.py

@@ -0,0 +1,56 @@
+import re
+import gradio
+import torch
+
+from PIL import Image
+from transformers import DonutProcessor, VisionEncoderDecoderModel
+
+processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
+model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+model.to(device)
+
+def process_document(image):
+
+    # prepare encoder inputs
+    pixel_values = processor(image, return_tensors="pt").pixel_values
+    
+    # prepare decoder inputs
+    task_prompt = "<s_cord-v2>"
+    decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
+          
+    # generate answer
+    outputs = model.generate(
+        pixel_values.to(device),
+        decoder_input_ids=decoder_input_ids.to(device),
+        max_length=model.decoder.config.max_position_embeddings,
+        early_stopping=True,
+        pad_token_id=processor.tokenizer.pad_token_id,
+        eos_token_id=processor.tokenizer.eos_token_id,
+        use_cache=True,
+        num_beams=1,
+        bad_words_ids=[[processor.tokenizer.unk_token_id]],
+        return_dict_in_generate=True,
+    )
+    
+    # postprocess
+    sequence = processor.batch_decode(outputs.sequences)[0]
+    sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
+    sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
+    
+    return processor.token2json(sequence)
+
+demo = gradio.Interface(
+    fn=process_document,
+    inputs="image",
+    outputs="json",
+    title="Document Parsing Demo",
+    description=None,
+    article=None,
+    enable_queue=True,
+    examples=None,
+    cache_examples=False)
+
+demo.launch()