app.py

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

def main():
    st.title("AI-Powered Audio Assistant")

    # 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:
        # Get predictions
        processed_image, text, audio = get_predictions(uploaded_image)

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

        # Play generated audio
        st.audio(audio, format="audio/wav")

if __name__ == "__main__":
    main()