Update app.py

app.py

@@ -1,21 +1,19 @@
 import gradio as gr
 from transformers import pipeline
-import soundfile as sf
-import numpy as np
 
-# Speech-to-text model
+# Speech → Text
 stt = pipeline(
     "automatic-speech-recognition",
     model="openai/whisper-base"
 )
 
-# Language model
+# LLM
 llm = pipeline(
-    "text2text-generation",
-    model="google/flan-t5-base"
+    "text-generation",
+    model="distilgpt2"
 )
 
-# Text-to-speech model
+# Text → Speech
 tts = pipeline(
     "text-to-speech",
     model="facebook/fastspeech2-en-ljspeech"
@@ -24,16 +22,16 @@ tts = pipeline(
 
 def voice_assistant(audio):
 
-    # Convert speech → text
+    # speech to text
     speech_text = stt(audio)["text"]
 
-    # Generate AI response
+    # AI response
     response = llm(
         speech_text,
         max_new_tokens=80
     )[0]["generated_text"]
 
-    # Convert text → speech
+    # text to speech
     speech_output = tts(response)
 
     audio_array = speech_output["audio"]