Duplicate from naver-clova-ix/donut-base-finetuned-cord-v2

Co-authored-by: Geewook Kim <[email protected]>

.gitattributes

@@ -0,0 +1,29 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+sample_cord_receipt(receipt_00004).png filter=lfs diff=lfs merge=lfs -text
+sample_image_cord_test_receipt_00004.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Donut Base Finetuned Cord V2
+emoji: 🍩
+colorFrom: blue
+colorTo: gray
+sdk: gradio
+sdk_version: 3.0.26
+app_file: app.py
+pinned: false
+duplicated_from: naver-clova-ix/donut-base-finetuned-cord-v2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,47 @@
+"""
+Donut
+Copyright (c) 2022-present NAVER Corp.
+MIT License
+
+https://github.com/clovaai/donut
+"""
+import gradio as gr
+import torch
+from PIL import Image
+
+from donut import DonutModel
+
+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_cord-v2>"
+
+image = Image.open("./sample_image_cord_test_receipt_00004.png")
+image.save("cord_sample_receipt1.png")
+image = Image.open("./sample_image_cord_test_receipt_00012.png")
+image.save("cord_sample_receipt2.png")
+
+pretrained_model = DonutModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
+pretrained_model.encoder.to(torch.bfloat16)
+pretrained_model.eval()
+
+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=[["cord_sample_receipt1.png"], ["cord_sample_receipt2.png"]],
+    cache_examples=False,
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+torch
+donut-python
+gradio