Update app.py
Browse files
app.py
CHANGED
|
@@ -1,73 +1,65 @@
|
|
| 1 |
-
# app.py
|
| 2 |
-
|
| 3 |
import streamlit as st
|
| 4 |
from transformers import pipeline
|
| 5 |
from PIL import Image
|
| 6 |
import numpy as np
|
| 7 |
import io
|
| 8 |
|
| 9 |
-
# Stage 1
|
| 10 |
@st.cache_resource
|
| 11 |
-
def
|
| 12 |
return pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
|
| 13 |
|
| 14 |
-
def
|
| 15 |
-
|
| 16 |
-
result =
|
| 17 |
return result[0]['generated_text']
|
| 18 |
|
| 19 |
-
# Stage 2
|
| 20 |
@st.cache_resource
|
| 21 |
def load_story_generator():
|
| 22 |
-
return pipeline("
|
| 23 |
|
| 24 |
def text2story(description):
|
| 25 |
story_gen = load_story_generator()
|
| 26 |
-
prompt = f"{description}
|
| 27 |
-
|
| 28 |
-
return
|
| 29 |
|
| 30 |
-
# Stage 3
|
| 31 |
@st.cache_resource
|
| 32 |
def load_tts():
|
| 33 |
-
return pipeline("text-to-
|
| 34 |
|
| 35 |
def story_to_audio(story_text):
|
| 36 |
tts = load_tts()
|
| 37 |
-
|
| 38 |
-
|
|
|
|
|
|
|
| 39 |
|
| 40 |
-
#
|
| 41 |
def main():
|
| 42 |
-
st.set_page_config(page_title="Kids Story
|
| 43 |
-
|
| 44 |
-
st.title("🎨 Kids Story Maker")
|
| 45 |
-
st.markdown("Upload a picture, and we will turn it into a story and voice!")
|
| 46 |
|
| 47 |
-
|
| 48 |
|
| 49 |
-
if
|
| 50 |
-
image = Image.open(
|
| 51 |
-
st.image(image, caption="
|
| 52 |
|
| 53 |
-
#
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
description = generate_image_caption(image)
|
| 57 |
-
st.success(f"Caption: {description}")
|
| 58 |
|
| 59 |
-
#
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
story = text2story(description)
|
| 63 |
-
st.success("Generated Story:")
|
| 64 |
st.write(story)
|
| 65 |
|
| 66 |
-
#
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
audio, sample_rate = story_to_audio(story)
|
| 70 |
-
st.audio(audio, sample_rate=sample_rate, format="audio/wav")
|
| 71 |
|
| 72 |
if __name__ == "__main__":
|
| 73 |
main()
|
|
|
|
|
|
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
from transformers import pipeline
|
| 3 |
from PIL import Image
|
| 4 |
import numpy as np
|
| 5 |
import io
|
| 6 |
|
| 7 |
+
# Stage 1: Image to Text (Captioning)
|
| 8 |
@st.cache_resource
|
| 9 |
+
def load_image_caption_model():
|
| 10 |
return pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
|
| 11 |
|
| 12 |
+
def generate_caption(image):
|
| 13 |
+
caption_model = load_image_caption_model()
|
| 14 |
+
result = caption_model(image)
|
| 15 |
return result[0]['generated_text']
|
| 16 |
|
| 17 |
+
# Stage 2: Text to Story (Children-friendly)
|
| 18 |
@st.cache_resource
|
| 19 |
def load_story_generator():
|
| 20 |
+
return pipeline("text-generation", model="zuu-nlp/zuu-tiny-story-generator", max_length=200)
|
| 21 |
|
| 22 |
def text2story(description):
|
| 23 |
story_gen = load_story_generator()
|
| 24 |
+
prompt = f"Write a creative and simple story for kids aged 3 to 10 about: {description}"
|
| 25 |
+
story = story_gen(prompt)[0]['generated_text']
|
| 26 |
+
return story
|
| 27 |
|
| 28 |
+
# Stage 3: Story to Speech (Lightweight & Compatible)
|
| 29 |
@st.cache_resource
|
| 30 |
def load_tts():
|
| 31 |
+
return pipeline("text-to-speech", model="espnet/kan-bayashi_ljspeech_vits", framework="espnet")
|
| 32 |
|
| 33 |
def story_to_audio(story_text):
|
| 34 |
tts = load_tts()
|
| 35 |
+
output = tts(story_text)
|
| 36 |
+
audio = output["audio"]
|
| 37 |
+
sample_rate = output["sampling_rate"]
|
| 38 |
+
return audio, sample_rate
|
| 39 |
|
| 40 |
+
# Streamlit App UI
|
| 41 |
def main():
|
| 42 |
+
st.set_page_config(page_title="Kids Story Creator", layout="centered")
|
| 43 |
+
st.title("🧒 Kids Story Creator 📖")
|
|
|
|
|
|
|
| 44 |
|
| 45 |
+
uploaded_image = st.file_uploader("Upload an image (jpg/jpeg/png):", type=["jpg", "jpeg", "png"])
|
| 46 |
|
| 47 |
+
if uploaded_image is not None:
|
| 48 |
+
image = Image.open(uploaded_image).convert("RGB")
|
| 49 |
+
st.image(image, caption="Uploaded Image", use_column_width=True)
|
| 50 |
|
| 51 |
+
st.markdown("### Step 1: Generating Description...")
|
| 52 |
+
caption = generate_caption(image)
|
| 53 |
+
st.success(f"Caption: {caption}")
|
|
|
|
|
|
|
| 54 |
|
| 55 |
+
st.markdown("### Step 2: Generating Story from Caption...")
|
| 56 |
+
story = text2story(caption)
|
| 57 |
+
st.success("Here's your story:")
|
|
|
|
|
|
|
| 58 |
st.write(story)
|
| 59 |
|
| 60 |
+
st.markdown("### Step 3: Converting Story to Audio...")
|
| 61 |
+
audio, sample_rate = story_to_audio(story)
|
| 62 |
+
st.audio(audio, format="audio/wav", sample_rate=sample_rate)
|
|
|
|
|
|
|
| 63 |
|
| 64 |
if __name__ == "__main__":
|
| 65 |
main()
|