Comments (12)
A way to fine-tune from our models would be to add a new embedding(s) for your new artist(s), and initialise them from the aritst_id = 0 ie "unknown" artist embedding.
from jukebox.
We've updated the instructions on how to finetune from 1b_lyrics or train from scratch. Hope it helps!
from jukebox.
The easiest approach would be to train your own top-level prior on a new dataset.
In theory, if you have enough VRAM/GPUs, you could finetune from our pretrained top-level priors, but it is going to be a lot of work possibly involving a fair bit of code change/model surgery. 1B top-level training fits on a single GPU with gradient checkpointing (enabled with --c_res=1
), but 5B will require something like GPipe. One caveat though is that you will most likely be able to fit a per-gpu batch size of 1 example, so finetuning could also take some time depending on your setup.
from jukebox.
@heewooj Thank you so much! I'll try training a top-level prior. How much data is recommended? And would a free Colab GPU be sufficient for this or is this something that would require spending some money to train?
from jukebox.
^ 👍 also, this function has to be implemented if you'd like to enable --labels=True
. But, if there's only one that you'd like to finetune from, you can actually just consider 0 (originally unknown) to be the artist/genre of your choice.
from jukebox.
@prafullasd @heewooj I'll read more on this and give it a shot. Thanks guys!
from jukebox.
@heewooj Wonderful! You guys are amazing.
from jukebox.
related - #40
from jukebox.
Thanks a lot for all this support!
Just a question on how much data is needed both for fine-tuning and training from scratch.
Roughly: How many new songs should there be per artist/genre to achieve nice results?
from jukebox.
Good morning friends! Please help us to review about this code we are using to train prior level 2.
The checkpoint tar file does not grow size more than 12.92 Mb size.
During training Does EMA bpd value must decay to 0.99 average? It started over 7 value.
Thank you in advance for your help
from jukebox.
For Prior Level 2 training?
What is the recommended dataset time duration we should use?
What are the amount of training steps we must train?
It is needed remove voices to audio dataset with Spleeter?
What are the best charts of Tensorboard we must take care during our training process?
from jukebox.
Good morning friends! Please help us to review about this code we are using to train prior level 2.
The checkpoint tar file does not grow size more than 12.92 Mb size.
During training Does EMA bpd value must decay to 0.99 average? It started over 7 value.
Thank you in advance for your help
Tar file we know now that is around 1GB size for prior training with lyrics and non-lyrics.
from jukebox.
Related Issues (20)
- Installation Error,Packages not found HOT 7
- Fine-tuning the prior
- Hudba
- Error
- Just ignore
- Error right at the start of Colab HOT 1
- Changing output permissions
- stuck repeating the last few lines over and over and over and over again
- #0penA1 - #Fu11A1
- Encountering Errors with OpenAI Jukebox in Google Colab HOT 3
- Enhancement feature
- "Installation Error: jukebox package not found on conda channels (Windows 64-bit, Python 3.9.18)" "Unable to Install Jukebox from Conda (conda 23.11.0, Python 3.9.18)" HOT 1
- Syntax error on Colab
- My trackq HOT 1
- Rt
- Te amo
- AROA HOT 1
- Size mismatch
- Ya par tal
- Does anyone use the jukebox on their mac M2?
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 jukebox.