aligner.multiprocessing.tree_stats(directory, align_directory, split_directory, ci_phones, num_jobs, fmllr=False)[source]

Multiprocessing function that computes stats for decision tree training

See for more details on the Kaldi binary this runs.


directory : str

Directory of training (triphone, speaker-adapted triphone training directories)

align_directory : str

Directory of previous alignment

split_directory : str

Directory of training data split into the number of jobs

ci_phones : str

Colon-separated list of context-independent phones

num_jobs : int

The number of processes to use in calculation

fmllr : bool, optional

Whether the current training session is using fMLLR (speaker-adaptation), defaults to False