drewthomasson Goto Github PK

auto-scalable-speaker-attribution-dataset

This is my attempt at implementing a method for scaling speaker attribution datasets for literature by using GPT

bark

🔊 Power Up The Bark Text-prompted Generative Audio Model

booknlp

BookNLP, a natural language processing pipeline for books

chatgpt_detector

Finding ways to detect if its a person writing or if its chatgpt using samples of their writing as input, makes use of the open api and ML

citation_helper

easy-formatted-quotes-proj-gutenburg-dataset

This is a dataset of txt file versions of project Gutenberg books which are properly formatted with quotes meaning its easy for a program to pull out all of the quotes in them

easy_train_gpt2

A easy way to train a custom GPT2 model with a singel prompt by utilizing ollama

ebook2audiobookstyletts2

This simple program makes use of Calibre to convert a ebook into chapters and styletts2 to turn that into a audiobook with voice cloning capabilities

ebook2audiobookxtts

Generates a audiobook with chapters and ebook metadata using Calibre and Xtts from Coqui tts, and with optional voice cloning, and supports multiple languages

gpt_detector

job-scraping-llm-qna

using gpt4all to qua scraped data from LinkedIn

llm_qna_database_generator

makes a llm with a specific prompt provide a new answer to all the input s to a input and response dataset in csv file format

voxnovel

VoxNovel: generate audiobooks giving each character a different voice actor.

voxnovel-old-

This is an going project of mine that generates audiobooks from a book input, and uses a different actors for each character in the book

voxnovel_old_11_17_2023

VoxNovel: GPT-4 powered audiobooks with unique character voices.

whisper_auto_search

auto searches txt files for relevant keywords