Spaces:
Sleeping
Sleeping
File size: 2,669 Bytes
82e3a35 |
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 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
from dotenv import find_dotenv, load_dotenv # get the API keys
from transformers import pipeline # download huggingface model to our machine
from langchain_core.prompts import PromptTemplate
from langchain_community.chat_models import ChatOpenAI
from langchain.chains import LLMChain
import requests
import os
import streamlit as st
load_dotenv(find_dotenv())
HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
# img2text
def img2text(url):
image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
text = image_to_text(url)[0]["generated_text"]
print(text)
return text
# llm
def generate_story(scenario):
# template to generate a story
template = """
You are a story teller;
You can generate a short story based on a single narrative, the story should be no more than 20 words;
CONTEXT: {scenario}
STORY:
"""
prompt = PromptTemplate(template=template, input_variables=["scenario"])
# llm chain
story_llm = LLMChain(llm=ChatOpenAI(
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 {HUGGINGFACEHUB_API_TOKEN}"}
payloads = {"inputs": message}
response = requests.post(API_URL, headers=headers, json=payloads)
with open("audio.wav", 'wb') as file: # for me .wav worked instead of .flac
file.write(response.content)
# scenario = img2text("photo.jpg")
# story = generate_story(scenario)
# text2speech(story)
# main function for UI layer
def main():
st.set_page_config(page_title="Image 2 Audio Story", page_icon="🩵")
st.header("Turn image into a short audio story")
uploaded_file = st.file_uploader("Choose an image...", type="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_container_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.wav")
if __name__ == '__main__':
main() |