Update app.py

app.py

@@ -2,6 +2,10 @@ import gradio as gr
 from transformers import pipeline
 import edge_tts
 import numpy as np
+import asyncio
+
+# Print Gradio version for debugging
+print(f"Gradio version: {gr.__version__}")
 
 # Load speech-to-text model (Whisper small for Farsi)
 stt = pipeline("automatic-speech-recognition", model="openai/whisper-small")
@@ -21,7 +25,7 @@ async def tts(text, voice="fa-IR-FaridNeural"):
     return sample_rate, audio_array
 
 # Main function: Audio-to-audio pipeline
-def audio_to_audio(audio_input):
+async def audio_to_audio(audio_input):
     sample_rate_in, data_in = audio_input
     audio = {"array": data_in, "sampling_rate": sample_rate_in}
     
@@ -32,7 +36,7 @@ def audio_to_audio(audio_input):
     response = chatbot(text, max_length=50, num_return_sequences=1)[0]["generated_text"]
     
     # Step 3: Convert text to speech
-    sample_rate_out, data_out = tts(response)
+    sample_rate_out, data_out = await tts(response)
     
     return (sample_rate_out, data_out)