Update app.py

app.py

@@ -2,6 +2,7 @@ import streamlit as st
 import re
 import string
 from transformers import pipeline
+from datasets import load_dataset
 
 def img2text(url):
     image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base", use_fast=True)
@@ -50,7 +51,12 @@ def text2story(text):
     
     return final_story
 
-
+def text2audio(story_text):
+    audio_generator = pipeline("text-to-speech", "microsoft/speecht5_tts")
+    embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+    speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
+    audio_output = audio_generator(story_text, forward_params={"speaker_embeddings": speaker_embedding})
+    return audio_output
 
 def main():
     st.set_page_config(page_title="Once Upon A Time - Storytelling Application", page_icon="📖")
@@ -73,7 +79,9 @@ def main():
         story = text2story(scenario)
         st.write(story)
 
-
+        st.text('Your story is going to be told...🎧')
+        audio_data = text2audio(story)
+        st.audio(audio_data['audio'], format="audio/wav", start_time=0, sample_rate=audio_data['sampling_rate'])
 
 if __name__ == "__main__":
     main()