Spaces:
Running
Running
File size: 2,286 Bytes
1733285 |
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 |
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
def generate_story(scenario):
template = """
you are a very good story teller and a very rude person:
you can generate a short fairy tail based on a single narrative, the story should take 5 seconds to read.
CONTEXT: {scenario}
STORY:
"""
prompt = PromptTemplate(template=template, input_variables=["scenario"])
story_llm = LLMChain(llm=llm, prompt=prompt, verbose=True)
story = story_llm.predict(scenario=scenario)
print(story)
return story
# 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="Image to Story", page_icon="📚", layout="wide")
st.title("Image to Story")
uploaded_file = st.file_uploader("Choose an image...", type="png")
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)
story = generate_story(scenario)
text_to_speech(story)
with st.expander("scenerio"):
st.write(scenario)
with st.expander("story"):
st.write(story)
st.audio("audio.mp3")
if __name__ == '__main__':
main() |