Spaces:
Runtime error
Runtime error
File size: 2,280 Bytes
d3a1278 5e250bb d3a1278 79081f5 0eea78e d3a1278 0eea78e 5e250bb 30fc2e2 5e250bb 0eea78e 2382d71 5e250bb 118351d 79081f5 c0b4d8a 79081f5 2382d71 f4bce7b 48f0586 038de77 48f0586 d25a720 48f0586 41984dc 2382d71 b426c95 2382d71 b426c95 2382d71 |
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 |
import os
from pathlib import Path
import streamlit as st
from transformers import pipeline
from dotenv import load_dotenv
from langchain import PromptTemplate, LLMChain, OpenAI
import requests
if Path(".env").is_file():
load_dotenv(".env")
st.set_page_config(layout="wide")
HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
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 = """
You are a story teller;
You can generate a short story based on a simple narrative, the story should be no momre 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
#textToSpeech
def text2Speech(story) :
API_URL = "https://api-inference.huggingface.co/models/microsoft/speecht5_tts"
headers = {"Authorization": "Bearer {HF_TOKEN}"}
def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
return response.json()
output = query({
"inputs": story,
})
with open('audio.flac','wb') as file:
file.write(output.content)
def main() :
st.set_page_config(page_title="Image to Short Story", page_icon="")
st.header("Turn img into Audio Story")
uploaded_file = st.file.uploader("Choose an image(jpg type)", 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_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() |