Twewy-discord-chatbot - Build a Discord AI Chatbot that Speaks like Your Favorite Character

Last update: Dec 30, 2022

Overview

Build a Discord AI Chatbot that Speaks like Your Favorite Character!

This is a Discord AI Chatbot that uses the Microsoft DialoGPT conversational model fine-tuned on the game transcript of The World Ends With You (TWEWY). Read my tutorial on freeCodeCamp or watch my video tutorial on YouTube. I've also made a JavaScript version of the tutorial using Discord.js.

I trained the model using the lines of my favorite quirky character, Joshua (left in the image below). He has about 700 lines in total in the entire game.

Here is a demo of the Discord bot in action.

You can also directly chat with the model hosted on Hugging Face's Model Hub.

Structure of this Project

model_train_upload_workflow.ipyb: Notebook to be run in Google Colab to train and upload the model to Hugging Face's Model Hub
discord_bot.py: Script to be imported into a Repl.it Python Discord.py project
discord_bot.js: Script to be imported into a Repl.it JavaScript Discord.js project

Twewy-discord-chatbot - Build a Discord AI Chatbot that Speaks like Your Favorite Character

Related tags

Overview

Build a Discord AI Chatbot that Speaks like Your Favorite Character!

Structure of this Project

Resource Links

Owner

Lynn Zheng

translate using your voice

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

A collection of Classical Chinese natural language processing models, including Classical Chinese related models and resources on the Internet.

Transformers implementation for Fall 2021 Clinic

OpenChat: Opensource chatting framework for generative models

SentAugment is a data augmentation technique for semi-supervised learning in NLP.

This code extends the neural style transfer image processing technique to video by generating smooth transitions between several reference style images

BERT, LDA, and TFIDF based keyword extraction in Python

Based on 125GB of data leaked from Twitch, you can see their monthly revenues from 2019-2021

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

a test times augmentation toolkit based on paddle2.0.

뉴스 도메인 질의응답 시스템 (21-1학기 졸업 프로젝트)

📔️ Generate a text-based journal from a template file.

Auto translate textbox from Japanese to English or Indonesia

Understand Text Summarization and create your own summarizer in python

Code for Findings of ACL 2022 Paper "Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors"

Paddlespeech Streaming ASR GUI

Graph Coloring - Weighted Vertex Coloring Problem

RoNER is a Named Entity Recognition model based on a pre-trained BERT transformer model trained on RONECv2

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.