Update app.py

app.py

@@ -1,8 +1,6 @@
 import streamlit as st
 from transformers import pipeline
-from io import BytesIO
 from PIL import Image
-import torch
 
 # Load pipelines
 image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
@@ -24,7 +22,8 @@ if uploaded_image:
     
     # Convert text to speech
     speech_output = text_to_speech(text_output)
-    audio_bytes = BytesIO(speech_output['audio'])
-    
     st.write("### Listen to Speech Output:")
-    st.audio(audio_bytes, format="audio/wav")
+    st.audio(speech_output['audio'], 
+             format="audio/wav", 
+             start_time=0, 
+             sample_rate = speech_output['sample_rate'])