Download app.py from sarawork/Digitize-Historical-Records-Using-AI: direct link, hf CLI and curl.
- Browser
- Download file 1 kB
-
https://huggingface.co/spaces/sarawork/Digitize-Historical-Records-Using-AI/resolve/main/app.py
- Command line
-
hf download hf://spaces/sarawork/Digitize-Historical-Records-Using-AI/app.py
-
curl -L -o app.py https://huggingface.co/spaces/sarawork/Digitize-Historical-Records-Using-AI/resolve/main/app.py
1 kB
| import gradio as gr | |
| from transformers import TrOCRProcessor, VisionEncoderDecoderModel | |
| from PIL import Image | |
| processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-printed") | |
| model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-printed") | |
| def digitize_image(image): | |
| if image is None: | |
| return "Please upload a valid image." | |
| image = image.resize((768, 768)) # Optional: improve resolution | |
| pixel_values = processor(images=image, return_tensors="pt").pixel_values | |
| generated_ids = model.generate(pixel_values) | |
| raw_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] | |
| return f"๐ OCR Result:\n{raw_text}" | |
| demo = gr.Interface( | |
| fn=digitize_image, | |
| inputs=gr.Image(type="pil", label="Upload Document"), | |
| outputs=gr.Textbox(label="Digitized Text"), | |
| title="๐ Digitize Historical Records (Improved)", | |
| description="Extract printed or handwritten text from historical documents using TrOCR." | |
| ) | |
| demo.launch() | |