Testing_v2 / app.py
scmlewis's picture
Update app.py
1d39cce verified
import streamlit as st
from transformers import pipeline
from PIL import Image
# Creates a brief description of a picture using a smart model
def generate_caption(image):
with st.spinner("🔍 Looking at your picture..."):
# Loads the BLIP model to examine and describe the picture
image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
caption = image_to_text(image)[0]["generated_text"]
return caption
# Builds a story from the picture’s description
def generate_story(caption):
with st.spinner("✍️ Writing a fun story..."):
# Uses a story model to craft a tale from the description
pipe = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
story = pipe(caption)[0]['generated_text']
return story
# Turns the story into spoken audio
def generate_audio(story):
with st.spinner("🎙️ Turning story into audio..."):
# Uses a speech model to read the story aloud
pipe = pipeline("text-to-speech", model="facebook/mms-tts-eng")
audio = pipe(story)
return audio
# Streamlit UI: Makes a simple interface for kids to enjoy stories
# Displays a fun title
st.title("Picture to Story Fun! 🌈")
# Describes the app for young users
st.write("Hi, kids! Share a picture to get a fun story! Great for ages 3-10.")
# Allows picture uploads
uploaded_file = st.file_uploader("Pick a picture!", type=["png", "jpg", "jpeg"])
if uploaded_file is not None:
# Shows the uploaded picture
image = Image.open(uploaded_file)
st.image(image, caption="Your Picture!", use_container_width=True)
# Gets the picture’s description
image_caption = generate_caption(image)
st.subheader("Picture Description:")
st.write(image_caption)
# Creates a story
story_telling = generate_story(image_caption)
st.subheader("Your Story:")
st.write(story_telling)
# Generates audio
audio = generate_audio(story_telling)
if st.button("Hear Story!"):
st.audio(audio['audio'],
format="audio/wav",
start_time=0,
sample_rate=audio['sampling_rate'])