TrainingValidator

class montreal_forced_aligner.validation.TrainingValidator(**kwargs)

Bases: TrainableAligner, ValidationMixin

Validator class for checking whether a corpus and a dictionary will work together for training

See also

TrainableAligner

For training configuration

ValidationMixin

For validation parameters

Variables:

training_configs (dict[str, MonophoneTrainer])

classmethod parse_parameters(config_path=None, args=None, unknown_args=None)

Parse parameters for validation from a config path or command-line arguments

Parameters:

• config_path (Path) – Config path

• args (dict[str, Any]) – Parsed arguments

• unknown_args (list[str]) – Optional list of arguments that were not parsed

Returns:

Configuration parameters

Return type:

dict[str, Any]

setup()

Set up the corpus and validator

Raises:

KaldiProcessingError – If there were any errors in running Kaldi binaries

validate(output_directory=None)

Performs validation of the corpus

Parameters:

output_directory (Path, optional) – Optional directory to save output files in

property working_directory

Working directory