Turning it down... then up
Speech recognition works best on clean, audible speech. If your audio files are too quiet or too loud, it can hinder transcription.
In this exercise, you'll see how to make an AudioSegment quieter or louder.
Since the play() function won't play your changes in the DataCamp classroom.
The baseline audio file, volume_adjusted.wav can be heard here.
Questo esercizio fa parte del corso
Spoken Language Processing in Python
Esercizio pratico interattivo
Prova a risolvere questo esercizio completando il codice di esempio.
from pydub import AudioSegment
# Import audio file
volume_adjusted = AudioSegment.from_file(____)
# Lower the volume by 60 dB
quiet_volume_adjusted = ____ - _____