What's new
By:
Filters
LiteRECORDS

Register a free account today to become a member! Once signed in, you'll be able to participate on this site by adding your own topics and posts, as well as connect with other members through your own private inbox!

  • Guest, before your account can be reviewed you must click the activation link sent to your email account. Please ensure you check your junk folders.
    If you do not see the link after 24 hours please open a support ticket.

Powerful New Vocal Remover AI - Instructions

Anjok

Anjok

Superstar DJ
Ultimate Vocal Remover

***All Installation Instructions Can Be Found on My GitHub Repository***
To see this hidden content, you must like this content.
===============================================
Everyone seems to keep missing this so I'm adding the quote here for the time being.
djtayz said:
I'm personally not able to run the newest models that Anjok released with the most recent GUI, another version of Colab is in development though (not by me).

I will see if I can fix things, meanwhile, I'm open to any kind of requests for Colab, will try my best to implement them or think of workarounds.
Click to expand...

Google Colab Method

If you encounter issues during the installation of the regular vocal remover or the GUI, you can use this method. It doesn't require any special or powerful hardware, as all of the processes are done in the cloud. 1 track gets processed for around 1 minute.

STEPS:

Delete everything from the old Colab project, including the folder in your Google Drive, before updating!


1. Download this archive and upload the folder "vocal-remover" to your Google Drive.
https://mega.nz/file/Mbx3TLIZ#o6yEif1etlOT7KkEpgoSX7JUalzztrXNO2OrQzjxh9M

2. Go to https://colab.research.google.com/ and click on "Upload".

3. Download this file and upload it to Google Colab.
https://mega.nz/file/dD5lgDaB#msNAKlWeV4-DrTW7Z8nezSl05F1Tb6RO4gIn8TTPRho

4. When you open the project, you'll see a couple of steps that I've numbered to be easy to follow. Just click each one and wait until it gets finished.

On the fifth step, where you're choosing which track to process, make sure you've typed its name exactly as it is + the file type (WAV/FLAC/MP3 etc.)


5. Your instrumental & acapella tracks should be found inside the "vocal-remover" folder.
Optional: If you wish for cleaner results, you can run your instrumental (that you just made) through the stacked model. It's the very last step.​

Video tutorial for Colab by @NewAgeRipper: (if it doesn't play, click the Pop-out icon on the top right side)

[GD]1k3tfRBnAXuyl0pbHfH8q1xKdt01-uiTn[/GD]
 

Attachments

  • UVRGUI.jpg
    UVRGUI.jpg
    53.2 KB · Views: 100
Last edited by a moderator:
Wow, that's comprehensive.
Count me excited as well. I'm very curious to see what can be done by assembling a bunch of different models. Maybe one model will convert a track exceptionally well, except for one part of the song ... but a different model will do that one part much better, but doesn't do the rest of the song as well. Then the results of the two conversions (or more) can be spliced together to create the best possible results.
 
ChrisCall said:
Wow, that's comprehensive.
Count me excited as well. I'm very curious to see what can be done by assembling a bunch of different models. Maybe one model will convert a track exceptionally well, except for one part of the song ... but a different model will do that one part much better, but doesn't do the rest of the song as well. Then the results of the two conversions (or more) can be spliced together to create the best possible results.
Click to expand...

I hope it gets there! My hope is that many here will train individualized models that can process many different kinds of tracks. If we crowdsource models and share them here, I can build a GUI interface with a drop-down menu to process songs on the genre-specific models.
 
Anjok said:
I hope it gets there! My hope is that many here will train individualized models that can process many different kinds of tracks. If we crowdsource models and share them here, I can build a GUI interface with a drop-down menu to process songs on the genre-specific models.
Click to expand...

That would be brilliant.
 
Do you think you could create a short video tutorial from start to finish?
I admit I'm not much of a coder and I got stuck when installing soundstretch =8
 
djtayz said:
Do you think you could create a short video tutorial from start to finish?
I admit I'm not much of a coder and I got stuck when installing soundstretch =8
Click to expand...

I totally understand. This process can be a bit jarring for some. Once you get started, I'd be happy to answer any question you have! If I have the time, I'll work on a tutorial video.
 
i tried spleeter and would say get the same results from RX 7 Audio Editor.
Done a 2 stem split which only takes 2 minutes and a 4 stem split about 5 mins.
Keeps crashing at a 5 stem split
 
rkeane said:
i tried spleeter and would say get the same results from RX 7 Audio Editor.
Done a 2 stem split which only takes 2 minutes and a 4 stem split about 5 mins.
Keeps crashing at a 5 stem split
Click to expand...

This AI only separates vocals from a mix and that's it, but it does it VERY well. It doesn't isolate drums, bass, or guitars/other instruments from a mix. Best part about that is it's one of the things that makes it so much easier to train.
 
Last edited:
Anjok said:
I need to know more about the error you're seeing. I'm going to put together an "out of the box" version of this for those of you who aren't code savvy. I'll have it together by the weekend
Click to expand...

Every time I try to install PyTorch, even with modified code (the thing you're seeing there) as the requirements.txt file specifies for torch 1.3.0, there's that error... but I don't know why.
Maybe my Python engine is outdated?
 
alexban said:
Every time I try to install PyTorch, even with modified code (the thing you're seeing there) as the requirements.txt file specifies for torch 1.3.0, there's that error... but I don't know why.
Maybe my Python engine is outdated?
Click to expand...

Sorry about that! I didn't realize that was a link to an image. It's possible it might already be installed. Try running the following command from the windows command prompt -

pip install torch==1.3.0 torchvision==0.4.0 -f https://download.pytorch.org/whl/torch_stable.html
 
Last edited:
well installed cmd lines as u said but i reckon it doesnt work on intel.........keep getting error looking for Numba which is related to amd gpu and does not work with intel.........is there a work around do u know
 
rkeane said:
well installed cmd lines as u said but i reckon it doesnt work on intel.........keep getting error looking for Numba which is related to amd gpu and does not work with intel.........is there a work around do u know
Click to expand...

I guess I should have mentioned, you might have trouble running this if your PC is more than 5 years old. I'll need to see the full error message in order to help you troubleshoot.
 
PS C:\Users\Robert\Documents\vocal-remover-2.1.0> python inference.py --absolute.mp3 --gpu 0
C:\Users\Robert\AppData\Local\Programs\Python\Python37\lib\site-packages\librosa\util\decorators.py:9: NumbaDeprecationWarning: An import was requested from a module that has moved location.
Import requested from: 'numba.decorators', please update to use 'numba.core.decorators' or pin to Numba version 0.48.0. This alias will not be present in Numba version 0.50.0.
from numba.decorators import jit as optional_jit
C:\Users\Robert\AppData\Local\Programs\Python\Python37\lib\site-packages\librosa\util\decorators.py:9: NumbaDeprecationWarning: An import was requested from a module that has moved location.
Import of 'jit' requested from: 'numba.decorators', please update to use 'numba.core.decorators' or pin to Numba version 0.48.0. This alias will not be present in Numba version 0.50.0.
from numba.decorators import jit as optional_jit
usage: inference.py [-h] [--gpu GPU] [--model MODEL] --input INPUT [--sr SR]
[--hop_length HOP_LENGTH] [--window_size WINDOW_SIZE]
[--out_mask] [--postprocess]
inference.py: error: the following arguments are required: --input/-i
PS C:\Users\Robert\Documents\vocal-remover-2.1.0

tried it just thru cpu every way
tried every cmd every way as gpu
unless im missing something lol

tried installing numba
PS C:\> pip install numba Requirement already satisfied: numba in c:\users\robert\appdata\local\programs\python\python37\lib\site-packages (0.49.0)
Requirement already satisfied: numpy>=1.15 in c:\users\robert\appdata\local\programs\python\python37\lib\site-packages (from numba) (1.18.3)
Requirement already satisfied: llvmlite<=0.33.0.dev0,>=0.31.0.dev0 in c:\users\robert\appdata\local\programs\python\python37\lib\site-packages (from numba) (0.32.0)
Requirement already satisfied: setuptools in c:\users\robert\appdata\local\programs\python\python37\lib\site-packages (from numba) (41.2.0)
 
Last edited:
You must log in or register to reply here.