Image-To-Story / app.py
AMRitecs
First commit
5b14a6a
# Original code
# https://www.youtube.com/watch?app=desktop&v=_j7JEDWuqLE&ab_channel=AIJason
# OpenAI break
# https://github.com/langchain-ai/langchain/issues/12949
import os
import requests
from transformers import pipeline
#from langchain import PromptTemplate, LLMChain, OpenAI
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain
from langchain.llms import OpenAI
import streamlit as st
#from huggingface_hub import HfApi
HUGGING_FACE_API_TOKEN = st.secrets["HUGGING_FACE_API_TOKEN"]
#api = HfApi()
#if api.is_authenticated():
# print('HF server')
# HUGGING_FACE_API_TOKEN = os.environ("HUGGING_FACE_API_TOKEN")
#else:
# print('Local machine')
# HUGGING_FACE_API_TOKEN = st.secrets("HUGGING_FACE_API_TOKEN")
# img2text
def img2text(url):
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
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 20 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
# text to speech
def text2speech(message):
API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
headers = {"Authorization": f"Bearer {HUGGING_FACE_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="img 2 audio story", page_icon="A")
st.header("Turn img into audio story")
uploaded_file = st.file_uploader("Chose 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 = img2text(uploaded_file.name)
story = generate_story(scenario)
text2speech(story)
with st.expander("scenario"):
st.write(scenario)
with st.expander("story"):
st.write(story)
st.audio("audio.flac")
if __name__ == '__main__':
main()
# Debug
#scenario = img2text("photo.jpg")
#story = generate_story(scenario)
#text2speech(story)