app.py

import streamlit as st
from PIL import Image
from predictions import get_predictions

def main():
    st.set_page_config(page_title="ImageWhisper - AI Powered Audio Assistant", layout="wide")
    st.title("ImageWhisper - AI Powered Audio Assistant")
    st.markdown("---")

    # Sidebar for uploading image
    st.sidebar.title("Upload Image")
    uploaded_image = st.sidebar.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])

    if uploaded_image is not None:
        if st.button("Get Results"):
            # Get predictions
            processed_image, text, audio = get_predictions(uploaded_image)

            # Display processed image with bounding boxes
            st.subheader("Processed Image with Predicted Instances")
            st.image(processed_image, caption="Output image with predicted instances", use_column_width=True)

            # Play generated audio
            st.subheader("Generated Audio")
            st.audio(audio, format="audio/wav", caption="Click to play the generated audio")

            # Show extracted text
            st.subheader("Extracted Text")
            st.write(text)

if __name__ == "__main__":
    main()