Spaces:
Running
Running
| import gradio as gr | |
| import pytesseract | |
| from pdf2image import convert_from_path | |
| from PIL import Image | |
| import os | |
| # Function to perform OCR | |
| def ocr(input_file, lang='fas'): # 'fas': Persian language (Farsi) | |
| extracted_text = "" | |
| # Check if the input file is a PDF or an image | |
| if isinstance(input_file, str) and input_file.endswith('.pdf'): # Check if the file is a PDF | |
| # Convert PDF to images | |
| images = convert_from_path(input_file) | |
| # Loop through each image and perform OCR | |
| for page_number, image in enumerate(images): | |
| text = pytesseract.image_to_string(image, lang=lang) | |
| extracted_text += text | |
| elif isinstance(input_file, Image.Image): # If the input is an image | |
| text = pytesseract.image_to_string(input_file, lang=lang) | |
| extracted_text = text | |
| return extracted_text | |
| def gradio_interface(): | |
| # Define Gradio inputs and outputs | |
| input_type = gr.Radio(["PDF", "Image"], label="Choose Input Type", value="PDF") | |
| file_input = gr.File(label="Upload PDF/Image") | |
| language_input = gr.Dropdown( | |
| label="Select OCR Language", | |
| choices=[ | |
| ("English", "eng"), | |
| ("Mandarin Chinese", "chi_sim"), | |
| ("Hindi", "hin"), | |
| ("Spanish", "spa"), | |
| ("French", "fra"), | |
| ("Standard Arabic", "ara"), | |
| ("Bengali", "ben"), | |
| ("Portuguese", "por"), | |
| ("Russian", "rus"), | |
| ("Urdu", "urd"), | |
| ("Persian (Farsi)", "fas") | |
| ], | |
| value="fas" # Default to Persian | |
| ) | |
| output_text = gr.Textbox(label="Extracted Text", interactive=False) | |
| # Function to process the inputs and return the outputs | |
| def process(input_type, file, lang): | |
| if input_type == "PDF": | |
| extracted_text = ocr(file.name, lang) | |
| else: | |
| image = Image.open(file.name) | |
| extracted_text = ocr(image, lang) | |
| return extracted_text | |
| # Create and launch Gradio interface | |
| gr.Interface( | |
| fn=process, | |
| inputs=[input_type, file_input, language_input], | |
| outputs=[output_text], | |
| title="OCR (PDF/Image)", | |
| description="Upload a PDF or Image, select the OCR language, and extract the text." | |
| ).launch() | |
| # Call the function to create the interface | |
| gradio_interface() | |