Update app.py

app.py

@@ -1,7 +1,6 @@
 import streamlit as st
 from transformers import pipeline
 from PIL import Image
-import numpy as np
 
 # Stage 1: Image to Caption
 @st.cache_resource
@@ -27,7 +26,7 @@ def text2story(description):
 # Stage 3: Story to Speech
 @st.cache_resource
 def load_tts():
-    return pipeline("text-to-speech", model="espnet/kan-bayashi_ljspeech_vits", framework="espnet")
+    return pipeline("text-to-speech", model="facebook/fastspeech2-en-ljspeech")
 
 def story_to_audio(story_text):
     tts = load_tts()