It has been a while since the last dev log, huh? I haven't been sleeping on the project though. Let's run through all the updates/changes. First things first: A frontend/control panel. At first, this was just an excuse to install and learn Figma, since
Just a couple days ago, I 100%ed DDLC+. It's prompted some self-reflection, and I thought I'd write down some things I like. When I was younger, this wouldn't have even occurred to me to write about. But idk, as I think about it,
There is a problem with AI. I don't mean any of the technical, ethical, or political problems, I'm specifically talking about the problem we have of accurately informing the public about how AI works. Of course, I'm sure I'm not the first
Rule 1: Don't let anything stop you from doing the thing you want to learn. All other Rules are subservient to Rule 1. If any other rule stops you from following Rule 1, ignore them. I'm writing this for myself. So, if you disagree, just create
Today I wasted some more time on the discord audio thing then gave up and moved on. However, I did work on integrating vtube control and twitch integration. I modified the tts library to output text into my virutal audio cable, which feeds into vtube studio and the microphone volume
Today I tried to integrate the current system into a discord bot. The only thing I learned was that I hate working with receiving data from discord voice channels. Literally all I've done today is painfully digging through pycord's source code and documentation trying to first
Posting this devlog the next morning because I was up till 2 am gamin. Anyway, today I actually just went ahead and wrote all of the python code like I outlined in dev log 3 I think. Since I had such a clear plan it wasn't too hard.
Day 4! Today's Goal: Give the LLM some character! I was busy with other stuff today so not as much progress. First thing I did was to read up on Samantha and try copying her system prompt over into the web-ui to prove that this can work effectively.
Another day another dev log! Happy new Year. Today I worked on putting together a proof of concept system for a end to end audio in, audio out system. I decided to not use the STT and TTS extensions because they are not designed to stream audio in or out.
Today's goals: Experiment with and get TTS and STT working. So first I just installed the "builtin" coqui-TTS extension, and found that it worked, but not super well. I then found erew123/alltalk_TTS, which is a fork of the coqui-TTS extension with more features. The
Edit (5/6/2024): The GitHub repository is public here: kimjammer/Neuro, see what it's become now! Today begins my journey to recreate Neuro sama until I get bored. I will try to record what I've learned each day in a dev log like this. Idk
Just in case it's necessary in the future, thought I'd throw this in here. All expressed opinions and thoughts are limited in scope to when they were written. Their continued existence on this site or other publication is done for archival purposes only and do not