Benjamin Kröger

Anarci is already able to do wolfguy labeling. By including the Scheme boarders abnumber can handle the annotation as well.

Pass the device in load_model to Neural aligner

1

The `load_model` method currently doesn't pass the device to the DeepBLAST model, forcing it to always run in `cuda` / `gpu` model. With the current implementation it is not possible...

Could you change the device specifications to one consistent name, either `cuda` cuda or `gpu`, although I would suggest using `cuda` since this works with pytorch as well.