Comments (3)
4 gigabytes might be overkill, that would probably overtrain the model before even one epoch, unless your audio data is somehow extremely large file-size,
~400 minutes of audio, estimating from the amount of files, that's a lot considering you'd normally use 10-60 minutes, i've rarely seen people use more than 30 minutes too.
for the pitch extraction, I'll make it continue then, but you'll have to delete the folders if you want to switch pitch extraction method
from audio-webui.
I found what it was. The logs in the status box were crashing the browser. I stopped outputting "processing" and "extracting pitch" then it successfully completed.
As for over training, I think it came out that way. This audio is only 3 videos of someone streaming. Previous model was one and I think that came out better. Seems 1000 steps is sort of a sweet spot. The previous estimator used too few, about 10 epochs was good. Current one I need to re-run at about 4-5 vs the 1 it recommends.
Ironically, sometimes the over trained models do better on certain samples. This is just talking so singing might be a different story.
2.0 is a good loss here? I'm used to LLMs where 1.5-1.0 was the zone before it got too much of the material. I never found any best practices so I'm winging it and trying things.
from audio-webui.
yeah, i'm still trying to find the sweet spot for the amount of training, it can still depend a lot on the audio.
the exact number in the loss is not important, just the loss relative to the previous losses is important, if it becomes unstable, you're overtraining, and need to take a previous checkpoint
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.