app.py

import os
import requests
import streamlit as st

from dotenv import find_dotenv, load_dotenv
from transformers import pipeline

from langchain import PromptTemplate, LLMChain
from langchain.llms import GooglePalm

load_dotenv(find_dotenv())

#llm = GooglePalm(temperature=0.9, google_api_key=os.getenv("GOOGLE_API_KEY"))

# Iamge to Text
def image_to_text(url):
    #load a transformer
    image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

    text = image_to_text(url)[0]['generated_text']

    print (text)
    return text

# llm
#
# text to speech

def text_to_speech(message):
    API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
    headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_TOKEN')}"}
    payload = {"inputs": message}

    response = requests.post(API_URL, headers=headers, json=payload)
    print(response.content)
    with open('audio.mp3', 'wb') as audio_file:
        audio_file.write(response.content)

def main():
    st.set_page_config(page_title="描述圖片", page_icon="📚", layout="wide")

    st.title("描述圖片")
    uploaded_file = st.file_uploader("Choose an image...", type=["jpg","png","jpeg"])

    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 = image_to_text(uploaded_file.name)
        

        with st.expander("按下觀看圖片描述"):
            st.write(scenario)
        

if __name__ == '__main__':
    main()