You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The github release links to 2 versions for each steams model (2/4/5) : Xstems and Xstems-finetune.
What's the difference between the 2 kind of models, and how/why would you use one over the other ?
The text was updated successfully, but these errors were encountered:
The Xstems-finetune contains extra optimizer parameters that makes it possible to continue training on your own data (fine-tune the model with your own data). Other than that, they are the same as the Xstems models.
If you just want to perform separation, the Xstems-finetune models are useless as the extra optimizer parameters won't be used (and the model files are quite bigger).
The github release links to 2 versions for each steams model (2/4/5) : Xstems and Xstems-finetune.
What's the difference between the 2 kind of models, and how/why would you use one over the other ?
The text was updated successfully, but these errors were encountered: