app.py

# import part
import streamlit as st
from transformers import pipeline


# function part
# img2text
def img2text(img):
    image_to_text_model = pipeline("image-to-text", 
                                   model="Salesforce/blip-image-captioning-base")
    text = image_to_text_model(img)[0]["generated_text"]
    return text

# text2story
def text2story(text):
    story_text = ""   # to be completed
    return story_text

# text2audio
def text2audio(story_text):
    audio_data = ""     # to be completed
    return audio_data


# main part

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


if uploaded_file is not None:
    print(uploaded_file)
    st.image(uploaded_file, caption="Uploaded Image",
             use_column_width=True)  
    

    #Stage 1: Image to Text
    st.text('Processing img2text...')
    scenario = img2text(uploaded_file.name)
    st.write(scenario)


    #Stage 2: Text to Story
    st.text('Generating a story...')
    #story = text2story(scenario)
    #st.write(story)

    #Stage 3: Story to Audio data
    #st.text('Generating audio data...')
    #audio_data =text2audio(story)

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