Spaces:
Runtime error
Runtime error
File size: 2,150 Bytes
eb2392a cab4a8f eb2392a |
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 |
from transformers import pipeline
from langchain import PromptTemplate, LLMChain, OpenAI
import requests
import os
from dotenv import load_dotenv
import streamlit as st
load_dotenv(find_dotenv())
HUGGINGPHASE_API_TOKEN = os.getenv("HUGGINGPHASE_API_TOKEN")
# Image2Text
def img2text(url):
image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
text = img2text(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 simple narrative, the story should be more than 20 words;
CONTEXT:{scenario},
STORY:
"""
prompt = PromptTemplate(template=template, input_variable=["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 {HUGGINGPHASE_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='🤖')
st.header("Turn img into an audio story")
uploaded_file = st.file_uploader("Choose an image...", type="jpg")
if uploaded_file is not None:
print(uploaded_file)
with open(uploaded_file.name, "wb") as file:
file.write(uploaded_file.getvalue())
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()
|