https://github.com/m-romanenko/tv-script-generation

Generating new Simpsons scripts with an RNN
https://github.com/m-romanenko/tv-script-generation

lstm python rnn tensorflow

Last synced: 27 days ago
JSON representation

Generating new Simpsons scripts with an RNN

• Host: GitHub
• URL: https://github.com/m-romanenko/tv-script-generation
• Owner: m-romanenko
• Created: 2018-11-01T13:13:29.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2019-01-13T09:21:53.000Z (almost 6 years ago)
• Last Synced: 2024-05-17T10:55:36.901Z (6 months ago)
• Topics: lstm, python, rnn, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 191 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Generating new Simpsons scripts with an RNN

### Udacity Deep Learning Nanodegree project

Training a recurrent neural network with LSTM cells on a dataset of Simpsons scripts to generate scripts for new episodes (that almost make sense). 

* [Jupyter notebook with code](./dlnd_tv_script_generation.ipynb)

### References:

* [The Simpsons](https://en.wikipedia.org/wiki/The_Simpsons)

* [Original dataset](https://www.kaggle.com/wcukierski/the-simpsons-by-the-data)

* [RNNs/LSTMs](http://people.idsia.ch/~juergen/rnn.html)