项目作者: ugnelis

项目描述 :
RNN CTC by using TensorFlow.
高级语言: Python
项目地址: git://github.com/ugnelis/tensorflow-rnn-ctc.git
创建时间: 2017-08-26T13:27:55Z
项目社区:https://github.com/ugnelis/tensorflow-rnn-ctc

开源协议:MIT License

下载


TensorFlow RNN CTC Build Status

Connectionist Temporal Classification (CTC) by using Recurrent Neural Network (RNN) in TensorFlow.

Requirements

  • Python 2.7+ (for Linux)
  • Python 3.5+ (for Windows)
  • TensorFlow 1.12.1+
  • NumPy 1.5+
  • SciPy 0.12+
  • python_speech_features 0.1+

Installation

I suggest you to use Anaconda. For TensorFlow and python_speech_features use pip:

  1. $ activate anaconda_env_name
  2. (anaconda_env_name)$ pip install python_speech_features
  3. (anaconda_env_name)$ pip install --ignore-installed --upgrade tensorflow # without GPU
  4. (anaconda_env_name)$ pip install --ignore-installed --upgrade tensorflow-gpu # with GPU

Training

Run training by using train.py file.

  1. python train.py

License

This project is licensed under the terms of the MIT license.