"Option: Vocals will not be separated" isn´t working

[daddelpaddel]

He Guys, after my first issues, which were solved quickly i play a bit here and there to see and understand different settings.
The tool is really great and maybe some input / questions will help to get it better and stable for further versions.

I tried to use "Option: Vocals will not be separated" by using mode --interactive. But after a while program still separate vocals from audio. Output says:
"Separating vocals from audio with demucs with model htdemucs and cpu as worker
Selected model is a bag of 1 models. You will see that many progress bars per track"

Isn´t it working or is it needed when setting Karaoke txt file?

Also some other outputs I,m not sure if they are okay if i need to do something / adjust on scripts

Loading whisper with model large-v2 and cpu as worker
Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.3.3. To apply the upgrade to your files permanently, run python -m pytorch_lightning.utilities.upgrade_checkpoint E:\UltraSinger\.venv\lib\site-packages\whisperx\assets\pytorch_model.bin
Model was trained with pyannote.audio 0.0.1, yours is 3.1.1. Bad things might happen unless you revert pyannote.audio to 0.x.
Model was trained with torch 1.10.0+cu102, yours is 2.0.1+cpu. Bad things might happen unless you revert torch to 1.x.

Pitching with crepe and model full and cpu as worker
2024-12-28 16:10:40.250062: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.

Keep going on, it is really a great tool

[rakuri255]

Thanks mate 😃

The --disable_separation is only for the pipeline. So whisper and crepe will use the full audio instead only the vocals.
It will still output seperate vocal and instumental files.
I think you want --disable_karaoke, which do not output instrumental and vocals files.

For those warnings. I know them. But downgrading these packages would lead to more issues 🤣