arusl / nwp-en-bsd

This repo contains a Jupyter notebook for training an English next word prediction model based on a conversational dataset.

Next Word Prediction Model

This notebook shows how to train an English next word prediction model using LSTM (w/ Keras and NLTK).

Required files

To run the notebook (next_word_prediction_en_bsd.ipynb) in Google Colab, you need to download the followings and adjust the paths inside the notebook:

• training file (train.json) from this repo.

Load a trained model

If you want, you can skip the training step and load the trained model below to make predictions.

• trained model (next_word_model.h5)

Notes

Detailed explanations can be found inside the notebook.