TV Script Generation

In this project, you'll generate your own Seinfeld TV scripts using RNNs. You'll be using part of the Seinfeld dataset of scripts from 9 seasons. The Neural Network you'll build will generate a new ,"fake" TV script, based on patterns it recognizes in this training data.

Project Steps

The project consists of the following steps:

1. Get and Explore the Data

2. Implement Preprocessing Functions:

   • Lookup Table
   • Tokenize Punctuation
   • Pre-process all the data and save it
   • Input Batching

3. Build the Neural Network:

   • Model Architecture
   • Defining Forward and Backpropagation

4. Neural Network Training

   • Hyperparameters
   • Training

5. Generate TV Script

Instructions

To complete the project, you need to install the following libraries:

• Numpy
• Pytorch

You can find the data here. The helper.py and problem_unittests.py are helpful files used to finish the project.