TokenizerValidator

class montreal_forced_aligner.tokenization.tokenizer.TokenizerValidator(utterances_to_tokenize=None, **kwargs)

Bases: CorpusTokenizer

compute_validation_errors(gold_values, hypothesis_values)

Computes validation errors

Parameters:

• gold_values (dict[str, set[str]]) – Gold pronunciations

• hypothesis_values (dict[str, list[str]]) – Hypothesis pronunciations

property data_directory

Data directory

property data_source_identifier

Dummy “validation” data source

property evaluation_csv_path

Path to working directory’s CSV file

setup()

Set up the pronunciation generator

tokenize_utterances()

Tokenize utterances

Returns:

Mappings of keys to their tokenized utterances

Return type:

dict[str, list[str]]