gpt-omni commited on
Commit
10cc30a
1 Parent(s): b7df447
Files changed (1) hide show
  1. app.py +23 -8
app.py CHANGED
@@ -332,14 +332,29 @@ def process_audio(audio):
332
  else:
333
  return OUT_RATE, audio_data.astype(np.int16)
334
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
335
 
336
  if __name__ == '__main__':
337
- demo = gr.Interface(
338
- process_audio,
339
- inputs=gr.Audio(type="filepath", label="Microphone"),
340
- outputs=[gr.Audio(label="Response", streaming=streaming_output, autoplay=True)],
341
- title="Chat Mini-Omni Demo",
342
- live=True,
343
- )
344
- demo.queue()
345
  demo.launch()
 
332
  else:
333
  return OUT_RATE, audio_data.astype(np.int16)
334
 
335
+
336
+ # Create the Gradio interface
337
+ with gr.Blocks() as demo:
338
+ # Input component: allows users to record or upload audio
339
+ audio_input = gr.Audio(source="microphone", type="filepath", label="Record or Upload Audio")
340
+
341
+ # Output component: audio output that will automatically play
342
+ audio_output = gr.Audio(label="Processed Audio", streaming=streaming_output, autoplay=True)
343
+
344
+ # Button to trigger processing after recording/uploading
345
+ submit_btn = gr.Button("Submit")
346
+
347
+ # Functionality: When the button is clicked, process the audio and output it
348
+ submit_btn.click(fn=process_audio, inputs=audio_input, outputs=audio_output)
349
+
350
 
351
  if __name__ == '__main__':
352
+ # demo = gr.Interface(
353
+ # process_audio,
354
+ # inputs=gr.Audio(type="filepath", label="Microphone"),
355
+ # outputs=[gr.Audio(label="Response", streaming=streaming_output, autoplay=True)],
356
+ # title="Chat Mini-Omni Demo",
357
+ # live=True,
358
+ # )
359
+ # demo.queue()
360
  demo.launch()