Update app.py

app.py

@@ -12,7 +12,7 @@ def img2text(url):
 def text2story(text):
     #story_text = ""   # to be completed
     messages = [
-    {"role": "user", "content": "根据以下关键词生成一个100字的故事："+text },
+    {"role": "user", "content": "Generate a 100-word story based on the following keywords："+text },
     ]
     text_to_story_model= pipeline("text-generation", model="microsoft/Phi-4-mini-instruct", trust_remote_code=True)
     story_text = text_to_story_model(messages)[0]['generated_text']
@@ -20,7 +20,9 @@ def text2story(text):
     
 # text2audio
 def text2audio(story_text):
-    audio_data = ""     # to be completed
+    text_to_video_model = pipeline("text-to-speech", model="facebook/mms-tts-eng")
+    #audio_data = ""     # to be completed
+    audio_data = text_to_video_model(story_text)
     return audio_data
 
 st.set_page_config(page_title="Your Image to Audio Story",
@@ -52,8 +54,8 @@ if uploaded_file is not None:
 
     # Play button
     if st.button("Play Audio"):
-        #st.audio(audio_data['audio'],
-        #            format="audio/wav",
-        #            start_time=0,
-        #            sample_rate = audio_data['sampling_rate'])
-        st.audio("kids_playing_audio.wav")
+        st.audio(audio_data['audio'],
+                    format="audio/wav",
+                    start_time=0,
+                    sample_rate = audio_data['sampling_rate'])
+        #st.audio("kids_playing_audio.wav")