Update app.py

app.py

@@ -11,9 +11,8 @@ def img2text(url):
 
 # text2story
 def text2story(text):
-    messages = [{"role": "user", "content": text}]
     text_generation_model = pipeline("text-generation", model="microsoft/Phi-4-mini-instruct", trust_remote_code=True)
-    story_text = text_generation_model(messages)[0]["generated_text"]
+    story_text = text_generation_model(text)[0]["generated_text"]
     return story_text
 
 # text2audio
@@ -21,8 +20,8 @@ def text2audio(story_text):
     text_to_speech_model = pipeline("text-to-speech", model="suno/bark-small")
     audio_data = text_to_speech_model(story_text)
     return {
-        'audio': audio_data['audio'],
-        'sampling_rate': audio_data['sampling_rate']
+        'audio': audio_data["audio"],
+        'sampling_rate': audio_data["sampling_rate"]
     }
 
 #main part
@@ -41,24 +40,23 @@ if uploaded_file is not None:
     st.image(uploaded_file, caption="Uploaded Image",
              use_column_width=True)
 
-    #Stage 1: Image to Text
+    # Stage 1: Image to Text
     st.text('Processing img2text...')
     scenario = img2text(uploaded_file.name)
     st.write(scenario)
 
-    #Stage 2: Text to Story
+    # Stage 2: Text to Story
     st.text('Generating a story...')
     story = text2story(scenario)
     st.write(story)
 
-    #Stage 3: Story to Audio data
+    # Stage 3: Story to Audio data
     st.text('Generating audio data...')
-    audio_data =text2audio(story)
+    audio_data = text2audio(story)
 
     # 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")
+                 format="audio/wav",
+                 start_time=0,
+                 sample_rate=audio_data['sampling_rate'])