Machine learning project using federated learning for text generation

🌸 A Haiku generator using Project Gutenberg and AI 🗻

A tool for extracting chapters from Gutenberg Project Italian raw text e-books. RegEx are used to match chapter headings and extract the text between them.

This repo contains a scrapper for the Gutenberg's project website which contains 56,019 books free to read and download. In this repo also, you can find text file containing all the book data until April 2018 containing only the 'id', 'title' and 'authors' for every book in the dataset.

language modeling, bigram, trigram, mixture of language models, perplexity, Gutenberg project