app.py

import gradio as gr
import pytesseract
import cv2
import os

def process(files, lang: str = 'eng') -> str:
    results = []
    for file in files:
        try:
            img = cv2.imread(file)
            gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
            _, threshold_img = cv2.threshold(gray, 127, 255, cv2.THRESH_TOZERO)
            result = pytesseract.image_to_string(threshold_img, lang=lang)
            results.append(result)
        except Exception as e:
            results.append(f"Error processing {file}: {str(e)}")
        finally:
            os.remove(file)
    return "\n\n".join(results)

# Get available languages for pytesseract
langs = pytesseract.get_languages()

# Define the Gradio interface using gr.Files to allow multiple file uploads
interface = gr.Interface(
    fn=process,
    inputs=[
        gr.Files(label="Upload Images", file_count="multiple", type="filepath"),
        gr.Dropdown(label="Select Language", choices=langs, type="value")
    ],
    outputs="text",
    css="footer {visibility: hidden}",
    title="Optical Character Recognition | Batch Image To Text",
    article="""
    <p style='text-align: center;'>

    </p>
    """
)

# Launch the interface
interface.launch(show_api=False)