Configure Speech-to-text-wavenet

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

1. In order not to conflict with the previous environment, we use the Python virtualenv to install TensorFlow

Pip Install Virtualenv

mkdir TensorFlow

Virtualenv TensorFlow--no-site-packages

CD TensorFlow

SOURCE Bin/active

2. Install TensorFlow

Pip Install--upgrade Tensorflow-gpu

3. Install dependent libraries

sudo apt-get install Libsndfile-dev sox

Pip Install Sugartensor

Pip Install Pandas

Pip Install Librosa

Pip Install Scikits.audiolab

4. Test procedure

Python recognize.py--file Asset/data/librispeech/test-clean/1089/134686/1089-134686-0000.flac