All Projects → stardut → Text-Generate-RNN

stardut / Text-Generate-RNN

Licence: Apache-2.0 license
中国古诗生成(文本生成)

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Text-Generate-RNN

Char Rnn Chinese
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. Based on code of https://github.com/karpathy/char-rnn. Support Chinese and other things.
Stars: ✭ 192 (+81.13%)
Mutual labels:  rnn, chinese
Gpt2 Chinese
Chinese version of GPT2 training code, using BERT tokenizer.
Stars: ✭ 4,592 (+4232.08%)
Mutual labels:  text-generation, chinese
Char rnn lm zh
language model in Chinese,基于Pytorch官方文档实现
Stars: ✭ 57 (-46.23%)
Mutual labels:  rnn, chinese
Text Classification Cnn Rnn
CNN-RNN中文文本分类,基于TensorFlow
Stars: ✭ 3,613 (+3308.49%)
Mutual labels:  rnn, chinese
Chinese Poetry
The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人,21050首词。
Stars: ✭ 34,881 (+32806.6%)
Mutual labels:  poetry, chinese
Gpt2 Ml
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
Stars: ✭ 1,066 (+905.66%)
Mutual labels:  text-generation, chinese
Doc Han Att
Hierarchical Attention Networks for Chinese Sentiment Classification
Stars: ✭ 206 (+94.34%)
Mutual labels:  rnn, chinese
neural-namer
Fantasy name generator in TensorFlow
Stars: ✭ 65 (-38.68%)
Mutual labels:  rnn, char-rnn
Tensorflow poems
中文古诗自动作诗机器人,屌炸天,基于tensorflow1.10 api,正在积极维护升级中,快star,保持更新!
Stars: ✭ 3,429 (+3134.91%)
Mutual labels:  poetry, rnn
Gpt2 Newstitle
Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。
Stars: ✭ 235 (+121.7%)
Mutual labels:  text-generation, chinese
name2gender
Extrapolate gender from first names using Naïve-Bayes and PyTorch Char-RNN
Stars: ✭ 24 (-77.36%)
Mutual labels:  rnn, char-rnn
weapp-poem
诗词墨客 - 最全中华古诗词小程序
Stars: ✭ 409 (+285.85%)
Mutual labels:  poetry, chinese
pinyin4js
A opensource javascript library for converting chinese to pinyin。welcome Star : P
Stars: ✭ 153 (+44.34%)
Mutual labels:  chinese
cnn-rnn-classifier
A practical example on how to combine both a CNN and a RNN to classify images.
Stars: ✭ 47 (-55.66%)
Mutual labels:  rnn
gpt-neo-fine-tuning-example
Fine-Tune EleutherAI GPT-Neo And GPT-J-6B To Generate Netflix Movie Descriptions Using Hugginface And DeepSpeed
Stars: ✭ 157 (+48.11%)
Mutual labels:  text-generation
FCH-TTS
A fast Text-to-Speech (TTS) model. Work well for English, Mandarin/Chinese, Japanese, Korean, Russian and Tibetan (so far). 快速语音合成模型,适用于英语、普通话/中文、日语、韩语、俄语和藏语(当前已测试)。
Stars: ✭ 154 (+45.28%)
Mutual labels:  chinese
TV4Dialog
No description or website provided.
Stars: ✭ 33 (-68.87%)
Mutual labels:  chinese
Solar-Rad-Forecasting
In these notebooks the entire research and implementation process carried out for the construction of various machine learning models based on neural networks that are capable of predicting levels of solar radiation is captured given a set of historical data taken by meteorological stations.
Stars: ✭ 24 (-77.36%)
Mutual labels:  rnn
chinese-diceware
Diceware word lists in Chinese
Stars: ✭ 27 (-74.53%)
Mutual labels:  chinese
fandom-publics
The Chinese edition of The Internet and New Social Formation in China (粉丝公众), authored by Weiyu Zhang, translated by the CNPolitics translation team.
Stars: ✭ 62 (-41.51%)
Mutual labels:  chinese

Poetry and novel generate

Using RNN, LSTM automatically generates Chinese poetry texts.


USE

requirements

sample poetry

python sample.py
整首诗生成效果:

《擣练绯》 
噀景抱松草,清风吹颈人。皇军学夸便,和望忆皇恩。砌遍春来老,浮烟菊气长。

《瀑布交山寺肄暕院破田子游诗章二首 二》
何处花林接,伊川实遥早。李朝自二宗,设小都稍醒。乱舞何颓口,垂纶戏耳轻。武者复在宥,见使岂敢尊。

《与溧阳》 
往年南北别,守坐带蝉鸣。上迹报书叶,激然人未归。若逢南岳坑,红换夜嘉仙。

《得韦昭侍御》 
杜鹃筵豁头,忽认巴南天。阴有云斋趣,遥深愁梦梦。髫来住未得,谁屈骏鸟飞。羽檄紫人接,栖景不遑离。遽白李四子,牀余风上船。去名无真州,无复无戡情。柳色自清日,冰毫华素长。所,空木涩。乔楼块盈象,访道想斾浓。白石贫天分,深宫鹤子清。惟应意非时,有事感儒师。
藏头诗生成效果:

To do
根据上句诗完成下句诗:

To do

train

   python train.py

Poetry

Data:https://github.com/chinese-poetry/chinese-poetry

  • 5.5万首唐诗
  • 26万首宋诗
  • 2.1万首宋词
  • 唐宋两朝近1.4万古诗人
  • 两宋时期1.5K词人

reference:

If this has some help for you, star is a good reward ^-^

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].