Update app.py

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import os
 from pyannote.audio import Pipeline
 from pyannote.core import Segment
 from pyannote.audio import Audio
@@ -12,24 +13,10 @@ pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization-3.1",use_auth_
 def respond(audio_input):
     # Save the audio input to a file
     audio_file = audio_input
-    audio_input.save(audio_file)
-
     # Perform diarization on the whole file
     diarization = pipeline(audio_file)
 
-    # Example: Extract and process a specific segment
-    excerpt = Segment(start=2.0, end=5.0)
-    waveform, sample_rate = Audio().crop(audio_file, excerpt)
-
-    # Further processing (placeholder for actual implementation)
-    text_response = f"Processed segment from {excerpt.start} to {excerpt.end} seconds."
-    output_path = "response.wav"  # Placeholder path
-
-    # Generate an audio file as the response (placeholder for TTS implementation)
-    audio = AudioSegment.from_wav(output_path)
-    duration = len(audio) / 1000
-
-    return text_response, output_path
+    return text_response
 
 input_audio = gr.Audio(
     sources=["microphone"],
@@ -44,7 +31,7 @@ input_audio = gr.Audio(
 gr.Interface(
     fn=respond,
     inputs=input_audio,
-    outputs=["text", "audio"],
+    outputs="text",
     title="Tommy Vercetti Chatbot",
     description="Chat with Tommy Vercetti from GTA Vice City. Get responses in both text and voice!"
 ).launch(debug=True)