Update app.py

app.py

@@ -1,5 +1,6 @@
 import streamlit as st
 import re
+import string
 from transformers import pipeline
 
 def img2text(url):
@@ -17,6 +18,13 @@ def text2story(text):
     if story_text.startswith(". "):
         story_text = story_text[2:]
     
+    # Capitalize the first alphabetic character if it's lowercase
+    for i, char in enumerate(story_text):
+        if char.isalpha():
+            if char.islower():
+                story_text = story_text[:i] + char.upper() + story_text[i+1:]
+            break
+    
     # Split into sentences
     sentences = re.split(r'(?<=[.!?])\s+', story_text.strip())
     
@@ -43,7 +51,7 @@ def text2story(text):
     return final_story
 
 def text2audio(story_text):
-    audio_generator = pipeline("text-to-speech", model="espnet/kan-bayashi_ljspeech_vits")
+    audio_generator = pipeline("text-to-speech", model="microsoft/speecht5_tts")
     audio_output = audio_generator(story_text)
     return audio_output