Skip to main content

UNKNOWN

Project description

# word-level-rnn Word Level RNN for text generation using keras.

This is a project with a goal to make a Word Level Text generation using keras on Theano Framework. The code is based on the sample text generation character level code provided as a sample example at https://github.com/fchollet/keras/blob/master/examples/lstm_text_generation.py

I tried training it on chapters of The Game of Thrones (individually, because of memory constraints), seems coherent, please try and give me feedback.

#Read This: Since the code is done at word level instead of character level, it needs more epochs than the character level text generation counter part, as well as much more memory because it has to be trained on thousands of words, (unlike character level code where it’s only trained on 50-100 different characters (assuming ASCII).

Word level RNN text generation should in theory be more coherent then the Character level text generation at lesser amount of training. Suggestions and criticism are welcome to optimising and improve the code. thanks!

Project details


Release history Release notifications

This version

1.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for WordLevelRNN, version 1.0
Filename, size File type Python version Upload date Hashes
Filename, size WordLevelRNN-1.0.win-amd64.exe (227.5 kB) File type Windows Installer Python version any Upload date Hashes View hashes
Filename, size WordLevelRNN-1.0.zip (2.7 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page