Update app.py

app.py

@@ -1,45 +1,67 @@
 # import part
 import streamlit as st
 from PIL import Image
+from gtts import gTTS
+import io
 import time
 
 from transformers import pipeline
 
-def generate_image_caption(image_path):
-    """Generates a caption for the given image using a pre-trained model."""
-    img2caption = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
-    result = img2caption(image_path)
-    return result[0]['generated_text']
 
-# text2story
-def text2story(text):
-    pipe = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
-    story_text = pipe(text)[0]['generated_text']
-    return story_text
+def image_to_caption(image_path):
+    """Generates a caption for the given image using a pre-trained model."""
+    imgtocaption = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+    caption = imgtocaption(image_path)[0]['generated_text']
+    return caption
 
-# App title
-st.title("Assignment")
+def caption_to_story(text):
+    """Generates a story for the caption using a pre-trained model."""
+    captiontostory = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
+    story = captiontostory(text,max_length=150,min_length=50)[0]['generated_text']
+    return story
 
-# Write some text
-st.write("Image to Story")
+def story_to_audio(text):
+    """Generates an audio for the story."""
+    audio = io.BytesIO()
+    tts = gTTS(text=text, lang='en', slow=False)
+    tts.write_to_fp(audio)
+    audio.seek(0)
+    return audio
 
-# File uploader for image and audio
-uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
-uploaded_audio = st.file_uploader("Upload an audio file", type=["mp3", "wav", "ogg"])
 
-# Display image with spinner
+# Child-Friendly Interface Design
+st.set_page_config(page_title="Magic Story House", page_icon="🧚")
+st.title("🧚 Magic Image Story Generator")
+st.markdown("Upload an image and generate your exclusive fairy tale!")
+
+# File Upload
+uploaded_image = st.file_uploader("Choose a picture", type=["jpg", "jpeg", "png"], key="image_uploader")
+
+# main part
 if uploaded_image is not None:
-    with st.spinner("Loading image..."):
-        time.sleep(1)  # Simulate a delay
-        image = Image.open(uploaded_image)
-        st.image(image, caption="Uploaded Image", use_column_width=True)
-
-# Play audio with spinner
-if uploaded_audio is not None:
-    with st.spinner("Loading audio..."):
-        time.sleep(1)  # Simulate a delay
-        st.audio(uploaded_audio)
-
-# Button interaction
-if st.button("Click Me"):
-    st.write("🎉 You clicked the button!")
+    # Display the uploaded image
+    st.image(uploaded_image, caption='Uploaded Image', use_column_width=True)
+    # Save the uploaded image as a temporary file since the pipeline requires a file path as input
+    import tempfile
+    with tempfile.NamedTemporaryFile(delete=False, suffix='.jpg') as tmp_file:
+        tmp_file.write(uploaded_image.getvalue())
+        tmp_file_path = tmp_file.name
+
+    # Generate an image caption
+    caption = image_to_caption(tmp_file_path)
+    st.write(f"Caption: {caption}")
+
+    # Generate a story based on the caption
+    story = caption_to_story(caption)
+    st.write(f"Story: {story}")
+
+    # Convert the story to audio
+    audio = story_to_audio(story)
+    if audio:
+        st.audio(audio, format='audio/mp3')
+
+    # Delete the temporary file
+    import os
+    os.remove(tmp_file_path)
+
+