Spaces:
Sleeping
Sleeping
File size: 2,640 Bytes
90bef38 5b9e396 90bef38 e1ee436 90bef38 e1ee436 90bef38 5b9e396 90bef38 1e8cc2c 90bef38 1e8cc2c 90bef38 44b14a6 5b9e396 90bef38 5b9e396 90bef38 1e8cc2c 90bef38 5b9e396 90bef38 5b9e396 90bef38 5b9e396 90bef38 |
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 |
import streamlit as st
from transformers import pipeline
from PIL import Image
import io
from gtts import gTTS
import time
# Set page title
st.set_page_config(page_title="Kids Story Generator")
# Title and introduction
st.title("Kids Story Generator")
st.write("Upload a picture and let's create a magical story!")
# Initialize models
@st.cache_resource
def load_models():
image_to_text = pipeline("image-to-text", model="microsoft/git-base-coco")
story_generator = pipeline("text-generation", model="gpt2")
return image_to_text, story_generator
image_to_text, story_generator = load_models()
# Function to generate caption from image
def generate_caption(image):
caption = image_to_text(image)[0]['generated_text']
return caption
# Function to generate story from caption (less than 100 words)
def generate_story(caption):
prompt = f"Once upon a time, {caption} "
# Set max_length to control story length (approximately 100 words)
# Typical English word is ~5 characters, so ~500 characters ≈ 100 words
story = story_generator(prompt, max_length=100, do_sample=True)[0]['generated_text']
# Ensure story doesn't exceed 100 words
words = story.split()
if len(words) > 100:
words = words[:100]
story = " ".join(words)
# Add period to the end if needed
if not story.endswith(('.', '!', '?')):
story += '.'
return story
# Function to convert text to speech
def text_to_speech(text):
tts = gTTS(text=text, lang='en', slow=False)
audio_file = "story_audio.mp3"
tts.save(audio_file)
return audio_file
# File uploader
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
if uploaded_file is not None:
# Display the uploaded image
image = Image.open(uploaded_file)
st.image(image, caption='Uploaded Image', use_container_width=True)
# Generate button
if st.button("Generate Story"):
with st.spinner("Generating your story..."):
# Generate caption
caption = generate_caption(image)
st.write("Image caption:", caption)
# Generate story
story = generate_story(caption)
word_count = len(story.split())
st.write(f"### Your Story ({word_count} words)")
st.write(story)
# Generate audio
audio_file = text_to_speech(story)
# Display audio
st.write("### Listen to your story")
st.audio(audio_file)
st.markdown("---")
st.write("Created for ISOM5240 Assignment") |