Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from transformers import BlipProcessor, BlipForConditionalGeneration
-from pydub import AudioSegment
-from pydub.playback import play
+from gtts import gTTS
+import pygame
 
 model_id = "dblasko/blip-dalle3-img2prompt"
 model = BlipForConditionalGeneration.from_pretrained(model_id)
@@ -21,10 +21,11 @@ def generate_caption(image):
 
     return generated_caption, audio_path
 
-
 def play_audio(audio_path):
-    sound = AudioSegment.from_file(audio_path)
-    play(sound)
+    pygame.mixer.init()
+    pygame.mixer.music.load(audio_path)
+    pygame.mixer.music.play()
+    pygame.event.wait()
 
 # Create a Gradio interface with an image input, a textbox output, a button, and an audio player
 demo = gr.Interface(
@@ -37,4 +38,3 @@ demo = gr.Interface(
     ]
 )
 demo.launch()
-