Update app.py

app.py

@@ -6,43 +6,35 @@ import tempfile
 import os
 
 
-# Function to generate image caption
-def generate_image_caption(image_path):
+# Generate caption from image
+def image_to_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']
+    imgtocaption = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+    caption = imgtocaption(image_path)
+    return caption[0]['generated_text']
 
-# Function to generate story from text
-def text2story(text):
-    """Generates a story from input text"""
-    pipe = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
-    story_text = pipe(text, max_length=200)[0]['generated_text']
-    return story_text
+# Generate story from caption
+def caption_to_story(text):
+    captiontostory = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
+    story = captiontostory(text, max_length=150, min_length=50)
+    return story[0]['generated_text']
 
-# Function to convert text to speech
-def text_to_speech(text):
-    """Converts text to speech audio"""
-    try:
-        # Initialize text-to-audio pipeline
-        tts_pipe = pipeline("text-to-audio", model="facebook/mms-tts-eng")
+# Convert story to speech
+def story_to_audio(text):
+    tts_pipe = pipeline("text-to-audio", model="facebook/mms-tts-eng")
+    audio_output = tts_pipe(text[:1000]) 
+    return audio_output['audio'], audio_output['sampling_rate']
         
-        # Generate audio (returns dict with 'audio' array and 'sampling_rate')
-        audio_output = tts_pipe(text[:1000])  # Limit text length
-        
-        # Return the audio array and sampling rate
-        return audio_output['audio'], audio_output['sampling_rate']
-    except Exception as e:
-        st.error(f"Speech generation failed: {str(e)}")
-        return None, None
+# 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 application
 def main():
-    st.title("Image to Story with Speech")
-    st.write("Upload an image to generate a caption, story, and audio narration")
-
-    uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
-
     if uploaded_image is not None:
         try:
             # Process image
@@ -57,19 +49,19 @@ def main():
 
             # Generate caption
             with st.spinner("Generating caption..."):
-                caption = generate_image_caption(image_path)
+                caption = image_to_caption(image_path)
                 st.subheader("Generated Caption")
                 st.write(caption)
 
             # Generate story
             with st.spinner("Generating story..."):
-                story = text2story(caption)
+                story = caption_to_story(caption)
                 st.subheader("Generated Story")
                 st.write(story)
 
             # Generate speech
             with st.spinner("Generating audio..."):
-                audio_array, sample_rate = text_to_speech(story)
+                audio_array, sample_rate = story_to_audio(story)
                 if audio_array is not None:
                     st.subheader("Audio Narration")
                     st.audio(audio_array, sample_rate=sample_rate)