python對音頻文件進行重採樣

一、ffmpeg

pip install python-ffmpeg

簡單代碼:

import ffmpeg

ffmpeg.input('input.mp3').output('output.mp3', ar=16000).run()

二、librosa庫

import librosa
# to install librosa package
# > conda install -c conda-forge librosa 

filename = 'ClapSound.wav'
newFilename = 'ClapSound_8k.wav'

y, sr = librosa.load(filename, sr=48000)
y_8k = librosa.resample(y,sr,8000)

librosa.output.write_wav(newFilename, y_8k, 8000)

參考：
https://blog.csdn.net/u010070526/article/details/85218613
https://www.v2ex.com/t/561239
https://www.cnblogs.com/xingshansi/p/6799994.html