资源分类
》 资源 》算法》tensorflow-wavenet

tensorflow-wavenet

2019-12-18 | |  56 |   0 |   0

Speech-to-Text-WaveNet : End-to-end sentence level Chinese speech recognition using DeepMind's WaveNet

A tensorflow implementation for Chinese speech recognition based on DeepMind's WaveNet: A Generative Model for Raw Audio. (Hereafter the Paper)

Version

Current Version : 0.0.1

Dependencies

  1. python == 3.5

  2. tensorflow == 1.0.0

  3. librosa == 0.5.0

Dataset

清华30小时中文数据集

Directories

  1. cache: save data featrue and word dictionary

  2. data: wav files and related labels

  3. model: save the models

Network model

  1. Data random shuffle per epoch

  2. Xavier initialization

  3. Adam optimization algorithms

  4. Batch Normalization

Train the network

python3 train.py

Test the network

python3 test.py

Other resources

  1. TensorFlow练习15: 中文语音识别

  2. ibab's WaveNet(speech synthesis) tensorflow implementationt

  3. buriburisuri's WaveNet(English speech recognition) tensorflow and sugartensor implementationt


上一篇：keras-wavenet

下一篇：keras-yolo3

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...