With nkululeko you usually compute acoustic features with some software, but you can also simply import them from a text file.

You simply use the import as feature extraction type, and specify the file locations (can of course be only one) like this:

[FEATS]
type = ['import']
import_file = ['tests/results/exp_emodb_praat/store/emodb_praat_test.csv', 'tests/results/exp_emodb_praat/store/emodb_praat_train.csv']

The import file(s) must be in CSV (comma separated values) format and contain either a file index (a column with file names) or an audformat segmented index.

The index must match with the one from your data, else you will get the error:

Imported features for data set XXX not found!

You can combine with other features, e.g.

[FEATS]
type = ['import', 'os']

and select features, just like with any other feature sets.