app.py

from dotenv import find_dotenv, load_dotenv
from transformers import pipeline
from langchain import PromptTemplate, LLMChain, OpenAI
import requests
import os
import streamlit as st

load_dotenv(find_dotenv())
HF_API_KEY=os.getenv("HF_API_KEY")

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

    print(text)
    return text


#  Describe it using LLM
def generate_description(caption):
    template = """
    You are a story teller;
    You can generate a short story based on a simple narrative, the story should be no more than 30 words;
    CONTEXT: {caption}
    STORY;
    """

    prompt = PromptTemplate(template=template, input_variables=["caption"])

    desc_llm = LLMChain(llm=OpenAI(model_name="gpt-4", temperature=1), prompt=prompt, verbose=True)
    description = desc_llm.predict(caption=caption).replace('"', '')

    print(description)
    return description



# text to speech
def text2speech(message):
    API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
    headers = {"Authorization": f"Bearer {HF_API_KEY}"}
    payload = {
        "inputs": message
    }
    
    response = requests.post(API_URL, headers=headers, json=payload)
    with open('audio.flac', 'wb') as file:
        file.write(response.content)


def main():
    st.set_page_config(page_title="image-to-caption-to-summary", page_icon="😊")
    st.header("Image to caption to summary")
    uploaded_file = st.file_uploader("Choose an image", type=['png', 'jpg'])

    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)

        st.text('Processing img2text...')
        caption = img2text(uploaded_file.name)
        with st.expander("caption"):
            st.write(caption)

        st.text('Generating description of given image...')
        description = generate_description(caption)
        with st.expander("Description"):
            st.write(story)
        
        st.text('Processing text2speech...')
        text2speech(story)
        st.audio("audio.flac")

if __name__ == '__main__':
    main()