reduce verbosity of nemo and print output

app.py

@@ -40,13 +40,15 @@ model = nemo_asr.models.EncDecCTCModelBPE.restore_from(
 
 
 def transcribe(audio_file):
-    transcription_file = model.transcribe([audio_file])[0]
-    return transcription_file
+    transcription = model.transcribe([audio_file], verbose=False)[0]
+    print(f"{audio_file}: {transcription}")
+    return transcription
 
 
 def get_duration_ms(audio_file):
     duration = mediainfo(audio_file)["duration"]  # a string in seconds
     duration_ms = int(float(duration) * 1000)
+    print(f"{audio_file}: {duration_ms} ms")
     return duration_ms