Adding PaddleOCR

app.py

@@ -3,6 +3,9 @@ import gradio as gr
 from docling.document_converter import DocumentConverter, PdfFormatOption
 from docling.datamodel.pipeline_options import PdfPipelineOptions
 from docling.datamodel.base_models import InputFormat
+from paddleocr import PPStructureV3
+from pdf2image import convert_from_path
+import numpy as np
 
 pipeline_options = PdfPipelineOptions(enable_remote_services=True)
 converter = DocumentConverter(
@@ -20,9 +23,26 @@ def get_docling_ocr(pdf_path, page_num):
     markdown_text_docling = result.document.export_to_markdown()
     return markdown_text_docling
 
+def get_paddle_ocr(page_image):
+    pipeline = PPStructureV3()
+    output = pipeline.predict(input=np.array(page_image))
+
+    markdown_list = []
+
+    for res in output:
+        md_info = res.markdown
+        markdown_list.append(md_info)
+
+    markdown_text_paddleOCR = pipeline.concatenate_markdown_pages(markdown_list)
+    return markdown_text_paddleOCR
+
 def inference(pdf_path, page_num):
     docling_ocr = get_docling_ocr(pdf_path, page_num)
-    return docling_ocr
+    # Extract the first page as an image
+    images = convert_from_path(pdf_path, first_page=page_num, last_page=page_num)
+    page_image = images[0]
+    paddle_ocr = get_paddle_ocr(page_image)
+    return docling_ocr, paddle_ocr
 
 title = "OCR Arena"
 description = "A simple Gradio interface to extract text from PDFs and compare OCR models"
@@ -46,10 +66,11 @@ with gr.Blocks(theme=gr.themes.Glass()) as demo:
                         clear_btn = gr.ClearButton(components=[pdf, page_num])
                         submit_btn = gr.Button("Submit", variant='primary')
 
-                    submit_btn.click(inference, inputs=[pdf, page_num], outputs=docling_ocr_out)
+                    submit_btn.click(inference, inputs=[pdf, page_num], outputs=[docling_ocr_out, paddle_ocr_out])
 
         with gr.Column():
             docling_ocr_out = gr.Textbox(label="Docling OCR Output", type="text")
+            paddle_ocr_out = gr.Textbox(label="Paddle OCR Output", type="text")
 
     examples_obj = gr.Examples(examples=examples, inputs=[pdf])
 

requirements.txt

@@ -1,58 +1,103 @@
 aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.13
+aiosignal==1.3.2
 annotated-types==0.7.0
 anyio==4.9.0
+astor==0.8.1
 attrs==25.3.0
 beautifulsoup4==4.13.4
+cachetools==6.1.0
 certifi==2025.6.15
+chardet==5.2.0
 charset-normalizer==3.4.2
 click==8.2.1
 colorama==0.4.6
+colorlog==6.9.0
+cssselect==1.3.0
+cssutils==2.11.1
+dataclasses-json==0.6.7
+decorator==5.2.1
 dill==0.4.0
+distro==1.9.0
 docling==2.39.0
 docling-core==2.39.0
 docling-ibm-models==3.6.0
 docling-parse==4.1.0
 easyocr==1.7.2
+einops==0.8.1
 et_xmlfile==2.0.0
 fastapi==0.115.14
 ffmpy==0.6.0
 filelock==3.18.0
 filetype==1.2.0
+frozenlist==1.7.0
 fsspec==2025.5.1
+ftfy==6.3.1
+GPUtil==1.4.0
 gradio==5.35.0
 gradio_client==1.10.4
+greenlet==3.2.3
 groovy==0.1.2
 h11==0.16.0
 httpcore==1.0.9
 httpx==0.28.1
+httpx-sse==0.4.1
 huggingface-hub==0.33.1
 idna==3.10
 imageio==2.37.0
+imagesize==1.4.1
 Jinja2==3.1.6
+jiter==0.10.0
+joblib==1.5.1
 jsonlines==3.1.0
+jsonpatch==1.33
+jsonpointer==3.0.0
 jsonref==1.1.0
 jsonschema==4.24.0
 jsonschema-specifications==2025.4.1
+langchain==0.3.26
+langchain-community==0.3.26
+langchain-core==0.3.66
+langchain-openai==0.3.27
+langchain-text-splitters==0.3.8
+langsmith==0.4.4
 latex2mathml==3.78.0
 lazy_loader==0.4
 lxml==5.4.0
 markdown-it-py==3.0.0
 marko==2.1.4
 MarkupSafe==3.0.2
+marshmallow==3.26.1
 mdurl==0.1.2
+more-itertools==10.7.0
 mpire==2.10.2
 mpmath==1.3.0
+multidict==6.6.0
 multiprocess==0.70.18
-networkx==3.4.2
+mypy_extensions==1.1.0
+networkx==3.5
 ninja==1.11.1.4
 numpy==2.2.6
+openai==1.93.0
+opencv-contrib-python==4.10.0.84
 opencv-python-headless==4.11.0.86
 openpyxl==3.1.5
+opt-einsum==3.3.0
 orjson==3.10.18
-packaging==25.0
+packaging==24.2
+paddleocr==3.0.3
+paddlepaddle==3.0.0
+paddlex==3.0.3
 pandas==2.3.0
+pdf2image==1.17.0
 pillow==11.2.1
 pluggy==1.6.0
+premailer==3.10.0
+prettytable==3.16.0
+propcache==0.3.2
+protobuf==6.31.1
+py-cpuinfo==9.0.0
 pyclipper==1.3.0.post6
 pydantic==2.11.7
 pydantic-settings==2.10.1
@@ -73,13 +118,17 @@ PyYAML==6.0.2
 referencing==0.36.2
 regex==2024.11.6
 requests==2.32.4
+requests-toolbelt==1.0.0
 rich==14.0.0
 rpds-py==0.25.1
 rtree==1.4.0
+ruamel.yaml==0.18.14
+ruamel.yaml.clib==0.2.12
 ruff==0.12.1
 safehttpx==0.1.6
 safetensors==0.5.3
 scikit-image==0.25.2
+scikit-learn==1.7.0
 scipy==1.15.3
 semantic-version==2.10.0
 semchunk==2.2.2
@@ -89,10 +138,14 @@ shellingham==1.5.4
 six==1.17.0
 sniffio==1.3.1
 soupsieve==2.7
+SQLAlchemy==2.0.41
 starlette==0.46.2
 sympy==1.14.0
 tabulate==0.9.0
+tenacity==9.1.2
+threadpoolctl==3.6.0
 tifffile==2025.5.10
+tiktoken==0.9.0
 tokenizers==0.21.2
 tomlkit==0.13.3
 torch==2.7.1
@@ -100,10 +153,15 @@ torchvision==0.22.1
 tqdm==4.67.1
 transformers==4.53.0
 typer==0.16.0
+typing-inspect==0.9.0
 typing-inspection==0.4.1
 typing_extensions==4.14.0
 tzdata==2025.2
+ujson==5.10.0
 urllib3==2.5.0
 uvicorn==0.34.3
+wcwidth==0.2.13
 websockets==15.0.1
 xlsxwriter==3.2.5
+yarl==1.20.1
+zstandard==0.23.0