app.py

import streamlit as st
from transformers import pipeline

st.set_page_config(page_title="Image Emotion Classification",
                   page_icon="🦜")
st.header("Turn Your Image to Emotion Audio")
uploaded_file = st.file_uploader("Select an Image...")

if uploaded_file is not None:
    print(uploaded_file)
    bytes_data = uploaded_file.getvalue()
    with open(uploaded_file.name, "wb") as file:
        file.write(bytes_data)
    st.image(uploaded_file, caption="Uploaded Image",
             use_column_width=True)

    #Stage 1: Image to Emotion Text
    pipe1 = pipeline("image-classification", model="ISOM5240gr10/facial_emotion_finetune")
    st.text('Image Emotion Classification Result...')
    scenario = pipe1(uploaded_file.name)
    highest_result = max(scenario, key=lambda x: x['score'])
    st.write(highest_result['label'])

    #Stage 2: Emotion Text to Audio data
    st.text('Generating Audio Data...')
    pipe2 = pipeline("text-to-speech", model="Baghdad99/english_voice_tts")
    audio_data = pipe2(highest_result['label'])

    # Play button
    if st.button("Play Audio"):
        st.audio(audio_data['audio'],
                    format="audio/wav",
                    start_time=0,
                    sample_rate = audio_data['sampling_rate'])