Init

.gitattributes

@@ -2,27 +2,20 @@
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt 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
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz 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
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl 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
-*.safetensors 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
@@ -30,5 +23,7 @@ saved_model/**/* 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
-*.zst 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

.gitignore

@@ -0,0 +1,3 @@
+env
+__pycache__
+*.png

README.md

@@ -1,10 +1,10 @@
 ---
-title: Cord V2
-emoji: 😻
-colorFrom: yellow
-colorTo: red
+title: Donut Base Finetuned Cord V2
+emoji: 🍩
+colorFrom: blue
+colorTo: gray
 sdk: gradio
-sdk_version: 3.27.0
+sdk_version: 3.0.26
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,46 @@
+"""
+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.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(server_name="0.0.0.0")

requirements-lock.txt

@@ -0,0 +1,104 @@
+aiofiles==23.1.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+altair==4.2.2
+anyio==3.6.2
+async-timeout==4.0.2
+attrs==23.1.0
+certifi==2022.12.7
+charset-normalizer==3.1.0
+click==8.1.3
+cmake==3.26.3
+contourpy==1.0.7
+cycler==0.11.0
+datasets==2.11.0
+dill==0.3.6
+donut-python==1.0.9
+entrypoints==0.4
+fastapi==0.95.1
+ffmpy==0.3.0
+filelock==3.11.0
+fonttools==4.39.3
+frozenlist==1.3.3
+fsspec==2023.4.0
+gradio==3.27.0
+gradio_client==0.1.3
+h11==0.14.0
+httpcore==0.17.0
+httpx==0.24.0
+huggingface-hub==0.13.4
+idna==3.4
+Jinja2==3.1.2
+joblib==1.2.0
+jsonschema==4.17.3
+kiwisolver==1.4.4
+lightning-utilities==0.8.0
+linkify-it-py==2.0.0
+lit==16.0.1
+markdown-it-py==2.2.0
+MarkupSafe==2.1.2
+matplotlib==3.7.1
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.4
+multiprocess==0.70.14
+munch==2.5.0
+networkx==3.1
+nltk==3.8.1
+numpy==1.24.2
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cufft-cu11==10.9.0.58
+nvidia-curand-cu11==10.2.10.91
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-nccl-cu11==2.14.3
+nvidia-nvtx-cu11==11.7.91
+orjson==3.8.10
+packaging==23.1
+pandas==2.0.0
+Pillow==9.5.0
+pyarrow==11.0.0
+pydantic==1.10.7
+pydub==0.25.1
+pyparsing==3.0.9
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytorch-lightning==2.0.1.post0
+pytz==2023.3
+PyYAML==6.0
+regex==2023.3.23
+requests==2.28.2
+responses==0.18.0
+ruamel.yaml==0.17.21
+ruamel.yaml.clib==0.2.7
+sconf==0.2.5
+semantic-version==2.10.0
+sentencepiece==0.1.98
+six==1.16.0
+sniffio==1.3.0
+starlette==0.26.1
+sympy==1.11.1
+timm==0.6.13
+tokenizers==0.13.3
+toolz==0.12.0
+torch==2.0.0
+torchmetrics==0.11.4
+torchvision==0.15.1
+tqdm==4.65.0
+transformers==4.24.0
+triton==2.0.0
+typing_extensions==4.5.0
+tzdata==2023.3
+uc-micro-py==1.0.1
+urllib3==1.26.15
+uvicorn==0.21.1
+websockets==11.0.2
+xxhash==3.2.0
+yarl==1.8.2
+zss==1.2.0

requirements.txt

@@ -0,0 +1,4 @@
+torch
+donut-python
+gradio
+transformers==4.24.0