app.py

import streamlit as st
from transformers import pipeline

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

# text2story
def text2story(text):
    story_generator = pipeline("text-generation", model="distilgpt2")  # Corrected pipeline initialization
    story_text = story_generator(text, max_length=150, num_return_sequences=1)  # Pass parameters here
    return story_text[0]["generated_text"]  # Extract generated text

# text2audio
def text2audio(story_text):
    tts_model = pipeline("text-to-speech", model="facebook/mms-tts-eng")  # Initialize pipeline
    audio_data = tts_model(story_text)  # Generate audio
    return audio_data  # Return generated audio
     

#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)
    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 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)