import gradio as gr
from transformers import pipeline

# Initialize the image-to-text pipeline
extractor = pipeline("image-to-text", model="microsoft/git-base-textcaps")

def extract_text(image):
    result = extractor(image)
    return result[0]['generated_text']

# Create the Gradio interface
iface = gr.Interface(
    fn=extract_text,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="Image Text Extractor",
    description="Upload an image to extract text using Hugging Face's image-to-text model."
)

# Launch the app
iface.launch()