Update app.py

app.py

@@ -21,7 +21,7 @@ def text2story(text):
         {"role": "user", "content": f"write me a story of {text}. Story need to be at least 100 words and less than 200 words"}
     ]
     # Initialize the pipeline with max_length to ensure sufficient length
-    pipe = pipeline("text-generation", model="Qwen/Qwen2.5-1.5B-Instruct", max_length=280, min_length=130)
+    pipe = pipeline("text-generation", model="Qwen/Qwen2.5-1.5B-Instruct", max_length=260, min_length=130)
     # Generate the story
     story = pipe(messages)
     # Extract the generated text
@@ -31,8 +31,8 @@ def text2story(text):
 # text2audio
 def text2audio(story_text):
   # Initialize the pipeline
-        #pipe = pipeline("text-to-speech", model="facebook/mms-tts-eng")
-        pipe = pipeline("text-to-speech", model="espnet/kan-bayashi_ljspeech_fastspeech2", device=0)
+        pipe = pipeline("text-to-speech", model="facebook/mms-tts-eng")
+        
         # Generate audio
         audio_output = pipe(story_text)
         
@@ -56,11 +56,8 @@ def text2audio(story_text):
         output_file = "story_output.wav"
         sf.write(output_file, audio_data, sampling_rate)
         
-        print(f"Audio saved as {output_file}")
-        
         return output_file
 
-
 # Main part
 st.set_page_config(page_title="Your Image to Audio Story",
                    page_icon="🦜")
@@ -88,6 +85,5 @@ if uploaded_file is not None:
         audio_data = text2audio(story)
         st.audio("story_output.wav")
 
-
 # Footer
 st.write("Powered by Hugging Face Transformers and Streamlit")