A Haiku generator using Keras to develop an agent to predict text in a loose-haiku fashion.

YosAI utilizes Long Short Term Memory (LSTM) via a Recurrent Neural Network (RNN) and Natural Language Processing (NLP) to generate insightful haikus based off a robust dataset.

The model uses character encoding and sequence prediction via vectors in batches to train in each epoch/generation.

The model can be trained with any text document, learning how many syllables and lines based off the dataset.