파이썬 오디오 인식 - pydub, audiogrep

오디오/음성를 인식해서 text로 바꿔주는 기능은 open source로도 많이 있습니다. 오래된 기술인데 사실 어떤 application에 쓰일수 있느냐가 key인데 재밌는 application이 많이 있는데도 아직까지 많이 퍼지지 않은것이 궁금해서 이것저것 보고 있습니다.

Pydub 

Pydub lets you do stuff to audio in a way that isn't stupid.

Manipulate audio with a simple and easy high level interface 

http://pydub.com

Installing pydub is easy, but don't forget to install ffmpeg/avlib (the next section in this doc)

pip install pydub

-OR-

git clone https://github.com/jiaaro/pydub.git

Dependencies

You can open and save WAV files with pure python. For opening and saving non-wav files – like mp3 – you'll need ffmpeg or libav.

Linux (using aptitude):

# libav
apt-get install libav-tools libavcodec-extra-53

####    OR    #####

# ffmpeg
apt-get install ffmpeg libavcodec-extra-53

https://github.com/jiaaro/pydub

--------------------

Audiogrep

Audiogrep transcribes audio files and then creates "audio supercuts" based on search phrases. It usesCMU Pocketsphinx for speech-to-text and pydub to stitch things together.

pip install audiogrep

How to use it

First, transcribe the audio (you'll only need to do this once per audio track, but it can take some time)

# transcribes all mp3s in the selected folder
audiogrep --input path/to/*.mp3 --transcribe

이 명령어만 쓰고 ouput된 text에 따로 grep하는게 좋을것 같습니다.

# returns all phrases with the word 'word' in them
audiogrep --input path/to/*.mp3 --search 'word'

https://github.com/antiboredom/audiogrep

--------------------

sudo apt-get install python-pip

1. pip is a package management system used to install and manage software packages written in Python. Many packages can be found in the Python Package Index (PyPI).