Generate TV script from Seinfeld dataset (This Project is part from Udacity's deep learning nanodegree).
In this project, we will generate our own Seinfeld TV scripts using RNNs. we will be using part of the Seinfeld dataset of scripts from 9 seasons. The Neural Network we will build will generate a new ,"fake" TV script, based on patterns it recognizes in this training data.
-
Clone the repository and navigate to the downloaded folder.
git clone https://github.com/noureldinalaa/TV_Script_Generator.git cd TV_Script_Generator
-
The data is already provided in this repo in this path ./data/Seinfeld_Scripts.txt .
-
Install packages like pytorch and torch vision and some pip packages in requirements text file :
conda install pytorch torchvision -c pytorch pip install -r requirements.txt
-
Open a terminal window and navigate to the project folder. Open the notebook and follow the instructions.
jupyter notebook dlnd_tv_script_generation.ipynb
Try to increase the accuracy more .