Comments (4)
Index files are optional, they do not affect training. They contain basically all features from your training data. I believe a similarity search is used on them in order to fit accents and speech patterns better.
Nothing has changed with training, index is not used during training at all. Not sure why you're seeing differences.
from audio-webui.
The huge amount of epochs now? It used to be like 2 or 3.. I ran it for about 20 or 30 before to see what "more" would do and it would flatline and sound more electronic. Now it doesn't crack but it's taking quite a while.. more like any other model. Even in my huge 45 sized batches.
I need to try the models with and without the index to check the difference. Perhaps that is indeed the secret sauce. Definitely will re-extract my downloaded ones and pull out those index files if that's the case.
I notice one of the created indexes is never copied or used and other people's models came with both.
I'm not trying to be a huge pain, but RVC info seems rather limited and the repo is in I think Chinese.
from audio-webui.
that might have been something else, not the index though.
i'm trying to figure out as much as i can about RVC.
from audio-webui.
Yes, docs on audio models and training in general aren't great. A lot of trying things blind and hoping for the best.
from audio-webui.
Related Issues (20)
- [BUG REPORT] Failed to listen on network address HOT 2
- [BUG REPORT] HOT 1
- [BUG REPORT] HOT 3
- getting a error thing HOT 3
- [BUG REPORT]
- Installation failed on Windows [BUG REPORT] HOT 3
- [FEATURE REQUEST] Image2SFX HOT 1
- SOS: Python Packages vs. GPU Performance insights?
- [QUESTION] Enable to run py command! HOT 6
- [BUG REPORT] ImportError: cannot import name 'set_documentation_group' from 'gradio_client.documentation' HOT 7
- [BUG REPORT] Forever loading, without any output (Similar to issue #199?) HOT 3
- [BUG REPORT] Unresponsive UI, Missing TensorboardX library, wrong torchvision version installed. HOT 4
- [BUG REPORT] HOT 1
- [FEATURE REQUEST] MusicGen-Remixer & MusicGen-Chord
- [BUG REPORT]
- During my installation process, I keep encountering persistent torch version conflict warnings. What exactly is happening here? I am using the install.bat script on a Windows operating system. HOT 3
- [BUG REPORT] cant install pytorch on windows HOT 2
- [BUG REPORT] cant download or cant strip audio HOT 1
- [QUESTION] reaching out for a contact, and to share some details about bark re: the tokens it uses HOT 1
- [FEATURE REQUEST] (Offering to help) - Unified model management HOT 7
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 audio-webui.