TrainSpeakerLmArguments#

class montreal_forced_aligner.language_modeling.multiprocessing.TrainSpeakerLmArguments(job_name, session, log_path, model_path, tree_path, lexicon_compilers, order, method, target_num_ngrams, hclg_options)[source]#

Bases: MfaArguments

Arguments for TrainSpeakerLmFunction

Parameters:

  • job_name (int) – Integer ID of the job

  • session (sqlalchemy.orm.scoped_session or str) – SqlAlchemy scoped session or string for database connections

  • log_path (Path) – Path to save logging information during the run

  • model_path (Path) – Path to model

  • order (int) – Ngram order of the language models

  • method (str) – Ngram smoothing method

  • target_num_ngrams (int) – Target number of ngrams

  • hclg_options (dict[str, Any]) – HCLG creation options