Update app.py

app.py

@@ -4,12 +4,11 @@ import time
 
 asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_en_conformer_transducer_xlarge")
 
-def transcribe(audio1, audio2):
+def transcribe(audio1):
     mic_audio_transcription = asr_model.transcribe([audio1])[0][0] if audio1 else ""
-    file_audio_transcription = asr_model.transcribe([audio2])[0][0] if audio2 else ""
-    return mic_audio_transcription, file_audio_transcription
+    return mic_audio_transcription
 
 gr.Interface(
     fn=transcribe,
-    inputs=[gr.Audio(source="microphone", type="filepath"), gr.Audio(source="upload", type="filepath")],
-    outputs=["text", "text"]).launch()
+    inputs=[gr.Audio(source="microphone", type="filepath")],
+    outputs=["text"]).launch()