File size: 3,097 Bytes
5350da8 8738846 5d9279e 8738846 |
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 |
import os
import streamlit as st
import requests
from transformers import pipeline
from typing import Dict
from together import Together
# Image-to-text
def img2txt(url: str) -> str:
print("Initializing captioning model...")
captioning_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
print("Generating text from the image...")
text = captioning_model(url, max_new_tokens=20)[0]["generated_text"]
print(text)
return text
# Text-to-story generation with LLM model
def txt2story(prompt: str, top_k: int, top_p: float, temperature: float) -> str:
# Load the Together API client
client = Together(api_key=os.environ.get("TOGETHER_API_KEY"))
# Modify the prompt based on user inputs and ensure a 250-word limit
story_prompt = f"Write a short story of no more than 250 words based on the following prompt: {prompt}"
# Call the LLM model
stream = client.chat.completions.create(
model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
messages=[
{"role": "system", "content": '''As an experienced short story writer, write a meaningful story influenced by the provided prompt.
Ensure the story does not exceed 250 words.'''},
{"role": "user", "content": story_prompt}
],
top_k=top_k,
top_p=top_p,
temperature=temperature,
stream=True
)
# Concatenate story chunks
story = ''
for chunk in stream:
story += chunk.choices[0].delta.content
return story
# Text-to-speech
def txt2speech(text: str) -> None:
print("Initializing MeloTTS text-to-speech conversion...")
pipe = pipeline("text-to-speech", model="myshell-ai/MeloTTS-English")
# Generate audio from the text
audio = pipe(text)
# Save the audio output to a file
with open("audio_story.wav", "wb") as file:
file.write(audio["wav"])
# Get user preferences for the story
def get_user_preferences() -> Dict[str, str]:
preferences = {}
preferences['continent'] = st.selectbox("Continent", ["North America", "Europe", "Asia", "Africa", "Australia"])
preferences['genre'] = st.selectbox("Genre", ["Science Fiction", "Fantasy", "Mystery", "Romance"])
preferences['setting'] = st.selectbox("Setting", ["Future", "Medieval times", "Modern day", "Alternate reality"])
preferences['plot'] = st.selectbox("Plot", ["Hero's journey", "Solving a mystery", "Love story", "Survival"])
preferences['tone'] = st.selectbox("Tone", ["Serious", "Light-hearted", "Humorous", "Dark"])
preferences['theme'] = st.selectbox("Theme", ["Self-discovery", "Redemption", "Love", "Justice"])
preferences['conflict'] = st.selectbox("Conflict Type", ["Person vs. Society", "Internal struggle", "Person vs. Nature", "Person vs. Person"])
preferences['twist'] = st.selectbox("Mystery/Twist", ["Plot twist", "Hidden identity", "Unexpected ally/enemy", "Time paradox"])
preferences['ending'] = st.selectbox("Ending", ["Happy", "Bittersweet", "Open-ended", "Tragic"])
return preferences
|