File size: 2,200 Bytes
9e375c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
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())
HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")

#module1: image to text
def imgtotxt(url):
    img_to_txt = pipeline("image-to-text",model="Salesforce/blip-image-captioning-base")
    text = img_to_txt(url)[0]["generated_text"]
    print(text)
    return text


#module2: llm
def generate_story(scenario):
    template = """
    You are a story teller;
    You can generate a short story based on a simple narrative, the story should be no more than 50 words;

    CONTEXT: {scenario}
    STORY:
    """

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

    story_llm = LLMChain(llm=OpenAI(model_name="gpt-3.5-turbo", temperature=1), prompt=prompt, verbose=True)
    story = story_llm.predict(scenario=scenario)

    print(story)
    return story


#module3: text to speech
def texttospeech(message):
    API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
    headers = {"Authorization": f"Bearer {HUGGINGFACEHUB_API_TOKEN}"}
    payloads = {
        "inputs": message
    }

    response = requests.post(API_URL, headers=headers, json=payloads)
    with open('audio.flac', 'wb') as file:
        file.write(response.content)

def main():
    st.set_page_config(page_title="Image to Audio Story", page_icon="🗣️")
    st.header("Turn Image into Audio Story")
    uploaded_file = st.file_uploader("Choose an Image...", type="jpg")

    if uploaded_file is not None:
        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)
        scenario = imgtotxt(uploaded_file.name)
        story= generate_story(scenario)
        texttospeech(story)

        with st.expander("Scenario"):
            st.write(scenario)
        with st.expander("Story"):
            st.write(story)

        st.audio("audio.flac")

if __name__ == '__main__':
    main()