项目作者: alexcaselli

项目描述 :
Give a large book from Project Gutenberg (e.g., The Count of Monte Cristo). Train a network to predict network trained to predict the next textual character given a sequence of characters. Such network can be used to generate text by sampling a character
高级语言: Python
项目地址: git://github.com/alexcaselli/Text-Generation-Using-RNN.git
创建时间: 2020-07-19T19:21:40Z
项目社区:https://github.com/alexcaselli/Text-Generation-Using-RNN

开源协议:Apache License 2.0

下载


RNN Text Generation using TensorFlow

Give a large book from Project Gutenberg (e.g., The Count of Monte Cristo). Train a network to predic the next textual character given a sequence of characters. Such network can be used to generate text by sampling a character given the first one.

This project uses TensorFlow and LSTM cells to train a recurrent model able to generate sentences in plain English.

The same model can be used to learn from your Json exported Telegram conversations given a preprocessing function available in this repository which cast the Json formatted chat to the plain txt version giving some funny results.