Comments (7)
-Python ver 3.10.5 already reinstall
from ai-waifu.
Thank you for opening the issue and contributing to this project!
I've implemented error handling. Now, before this error message will be a short explanation and device list.
To fix this:
- Check the list of devices that print's before an error message
- Find the first device that starts with
CABLE Input
. For me, it'sCABLE Input (VB-Audio Virtual C, MME (0 in, 2 out)
- Copy ID of this device (it's printed before device name)
- Paste it as value of
output_device
in main.py insideinitialize
method
If your CABLE Input device has ID 3, update it in initialize
method:
waifu.initialize(user_input_service='whisper',
stt_duration = None,
mic_index = None,
chatbot_service='openai',
chatbot_model = None,
chatbot_temperature = None,
personality_file = None,
tts_service='elevenlabs',
output_device=3,
tts_voice='Rebecca - wide emotional range',
tts_model = None
)
I'm planning to add GUI in the future, so then I'll make a better way to solve it! Thanks for bringing this to my attention!
from ai-waifu.
I am happy to say that it worked, my value was 7, now this is supposed to work with VTubeStudio right? is there any special action I need to take to do that? since currently it's just audio.
from ai-waifu.
Right and does it just record until you say something? I feel like that would fill up storage real quick if it even records silence.
I'm just worried about wasting my tokens.
from ai-waifu.
I'm glad to hear that it fixed your issue!
To make Waifu work, you'll need to set a few settings in VTube Studio. You need to select CABLE Output
as microphone, select preview option, and setup Mouth Open
setting. You can find more detailed explanation in README file, under 6th list item in "Installation" part, there's Settings:
you can click on to reveal screenshots with explanation.
Additionally, you can go through most of parameters and check the "Auto-breath" box to add idle movent for 2D avatar.
As for audio recording, that's a really important point that I've missed. Thanks for pointing this out! I'm afraid it really does record silence. Unfortunately, I'll be busy for the next few days on my work. If there's free time to spare I'll look into this issue. But it's more likely that I'll be able to fix it only on Monday
from ai-waifu.
I followed the instructions yet it is still unable to lipsync, also take your time with the audio recording issue most people have a keybind which records your audio, but i am more interested in simply chatting and it automatically picks up on it.
from ai-waifu.
Also another potential issue I found is that while you're using V-CABLE for the output, you cannot hear anything else from your computer other than the AI, no music, no videos. I'm just bringing it into your attention if you weren't aware and I was wondering if there was a possible fix for it.
EDIT: I just used a diff output other than V-CABLE to hear everything.
from ai-waifu.
Related Issues (8)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ai-waifu.