Python 音频指纹和识别 Python Dejavu
Dejavu 是一个 Python 库，用于音频指纹和识别的算法。Dejavu 听一次音频后就会记录该音频的指纹信息，然后可通过麦克风对输入的音频进行识别是否同一首歌。
Python Dejavu依赖情况如下:
pyaudio for grabbing audio from microphone
ffmpeg for converting audio files to .wav format
pydub, a Python ffmpeg wrapper
numpy for taking the FFT of audio signals
scipy, used in peak finding algorithms
matplotlib, used for spectrograms and plotting
MySQLdb for interfacing with MySQL databases
相关推荐
alanlonglong 2020-11-05
nongfusanquan0 2020-10-28
tuonioooo 2020-10-27
莫明天涯 2020-09-03
xiaoxiaodedu 2020-01-05
CNETNews 2020-01-03
ivabrother 2019-12-26
yunna0 2019-11-19
李子无为的杂货铺 2019-11-10
drilistbox 2019-06-14
benny0 2019-06-11
海水梦悠悠 2019-03-22
dairen0 2019-04-29
82296535 2017-02-08
88266533 2016-09-05
81236630 2016-08-29
89384498 2016-06-11
muyangzhe 2016-01-25