https://chtseng.wordpress.com/2016/06/22/%E5%8D%B3%E6%99%82%E5%8F%A3%E8%AD%AF%E6%A9%9F%E5%99%A8%E4%BA%BAdiy%EF%BC%88%E4%B8%80%EF%BC%89/
1. sudo apt-get install flac
2, sudo pip install PocketSphinx -> error
3. sudo apt-get install swig
4, sudo apt-get install libpulse-dev
5. sudo pip install PocketSphinx
切割成20秒的長度...太常會有問題
https://github.com/Uberi/speech_recognition/issues/132
youtube 上面有人分享用python 來產生srt file
https://www.youtube.com/watch?v=hK6dpTLYlY4
use tensorflow to speech to srt
https://www.youtube.com/watch?v=u9FPqkuoEJ8
沒有留言:
張貼留言