pplev / mitsuha Goto Github PK

This project forked from 1nereality/mitsuha

0.0 0.0 0.0 323 KB

Multilingual Inexpensive Therapeutic Sophisticated Ultra-responsive Holographic Agent. In simple terms, an AI you can talk to and it'll talk back with a body using VTube Studio.

License: GNU General Public License v3.0

Python 99.45% Batchfile 0.55%

mitsuha's Introduction

OneReality

Bridging the real and virtual worlds

Demo video with 3D printed hologram box · Report Bug · Request Feature

Table of Contents

About The Project
- Built With
Getting Started
- Prerequisites
- Installation
Roadmap
License
Acknowledgments

About The Project

Click on image for demo video

A virtual waifu / assistant that you can speak to through your mic and it'll speak back to you! Has many features such as:

You can speak to her with a mic
It can speak back to you
Has short-term memory and long-term memory
Can open apps
Smarter than you
Fluent in English, Japanese, Korean, and Chinese
Can control your smart home like Alexa if you set up Tuya (more info in Prerequisites)

More features I'm planning to add soon in the Roadmap. Also, here's a summary of how it works for those of you who want to know:

First, the Python package SpeechRecognition recognizes what you say into your mic, then that speech is written into an audio (.wav) file, which is sent to OpenAI's Whisper speech-to-text transcription AI, and the transcribed result is printed in the terminal and written in a conversation.jsonl which the vector database hyperdb uses cosine similarity on to find 2 of the closest matches to what you said in the conversation.jsonl and appends that to the prompt to give Megumin context, the response is then passed through multiple NLE RTE and other checks to see if you want to open an app or do something with your smarthome, the prompt is then sent to llama.cpp, and the response from Megumin is printed to the terminal and appended to conversation.jsonl, and finally, the response is spoken by VITS TTS.

(back to top)

Built With

(back to top)

Getting Started

Video tutorial Here's how you can set it up on Windows (probably similar steps on Mac and Linux but I haven't tested them).

Prerequisites

Install Python 3.10.11 and set it as an environment variable in PATH
Install GIT
Install CUDA 11.7 if you have an Nvidia GPU
Install Visual Studio Community 2022 and select Desktop Development with C++ in the install options
Install VTube Studio on Steam
Download Megumin's VTube Studio Model
Extract the downloaded zip so it's only one folder deep (you should be able to open the folder and have all the files there, not one folder containing everything)
Open VTube Studio > Settings icon > Open Data Folder and move the folder there > Person icon > c001_f_costume_kouma
Install VB Cable Audio Driver, but don't set it as your audio devices just yet
Open Control Panel > Sound and Hardware > Sound > Recording > find CABLE Output > right-click > Properties > Listen > Check Listen to this device > For Playback through this device, select your headphones or speakers
(Optional) Create a Tuya cloud project if you want to control your smart devices with the AI, for example, you can say 'Hey Megumin, can you turn on my LEDs' it's a bit complicated though and I'll probably make a video on it later because it's hard to explain through text, but here's a guide that should help you out: https://developer.tuya.com/en/docs/iot/device-control-practice?id=Kat1jdeul4uf8

Automatic Installation

Open cmd in whatever folder you want the project to be in, and run git clone --recurse-submodules https://github.com/DogeLord081/OneReality.git
Open the folder and run python setup.py and follow the instructions
Edit the variables in .env if you must
Run OneReality.bat and while it's running, open the start menu and type Sound Mixer Options and open it. You might have to wait and make Megumin say something first, but you should see Python in the App Volume list
Change the output to CABLE Input (VB-Audio Virtual Cable)
Open VTube Studio > Settings icon > Scroll to Microphone Settings > Select Microphone > CABLE Output (VB-Audio Virtual Cable) > Person with settings icon > Scroll to Mouth Smile > Copy these settings > Scroll to Mouth Open > Copy these settings
Open Sound Mixer Options again and change the input for VTube Studio to CABLE Output (VB-Audio Virtual Cable)
May need to restart computer if lip sync doesn't work
You're good to go! If you run into any issues, let me know on Discord and I can help you. Once again, it's https://discord.gg/PN48PZEXJS
When you want to stop, say goodbye, bye, or see you somewhere in your sentence because that automatically ends the program, otherwise you can just ctrl + c or close the window