Import original code from Daniel Travaglia

README.md

@@ -1,14 +1,12 @@
 ---
-title: Donut Finetuned Sogc Trademarks 1883 2001
-emoji: 📉
-colorFrom: gray
-colorTo: yellow
+title: Donut fine-tuned - Swiss trademarks
+emoji: 📚
+colorFrom: purple
+colorTo: indigo
 sdk: gradio
-sdk_version: 5.34.0
+sdk_version: 3.29.0
 app_file: app.py
-pinned: false
-license: mit
-short_description: ' Donut fine-tuned - Swiss trademarks'
+pinned: true
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,57 @@
+import re
+import gradio as gr
+
+import torch
+from transformers import DonutProcessor, VisionEncoderDecoderModel
+
+# updated
+processor = DonutProcessor.from_pretrained("Travad98/donut-finetuned-sogc-trademarks-1883-2001")
+model = VisionEncoderDecoderModel.from_pretrained("Travad98/donut-finetuned-sogc-trademarks-1883-2001")
+
+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)
+
+description = "Gradio-based demo for Donut, an instance of VisionEncoderDecoderModel fine-tuned on the sogc-trademark-1883-2001 dataset. To use it, simply upload your image and click 'submit', or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2111.15664' target='_blank'>Donut: OCR-free Document Understanding Transformer</a> | <a href='https://github.com/clovaai/donut' target='_blank'>Github Repo</a></p>"
+
+demo = gr.Interface(
+    fn=process_document,
+    inputs="image",
+    outputs="json",
+    title="Donut 🍩 for 🇨🇭 trademark registration events",
+    description=description,
+    article=article,
+    enable_queue=True,
+    examples=[["example-1.jpg"], ["example-2.jpg"], ["example-3.jpg"], ["example-4.jpg"], ["example-5.jpg"]],
+    cache_examples=False)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+torch
+git+https://github.com/huggingface/transformers.git
+sentencepiece