配置Speech-to-Text-WaveNet

https://github.com/buriburisuri/speech-to-text-wavenet

1. 为了不和之前环境冲突，我们使用python virtualenv安装tensorflow

pip install  virtualenv

mkdir tensorflow

virtualenvtensorflow --no-site-packages


cd tensorflow

source bin/active

2. 安装tensorflow

pip install --upgrade tensorflow-gpu

3. 安装依赖库

sudo apt-get install libsndfile-dev sox

pip install sugartensor

pip install pandas

pip install librosa

pip install scikits.audiolab

4. 测试程序

python recognize.py --file asset/data/LibriSpeech/test-clean/1089/134686/1089-134686-0000.flac