get_average_posteriors

aligner.multiprocessing.get_average_posteriors(i, nnet_dir, prev_egs_dir, config, num_jobs)[source]

Multiprocessing function that gets average posterior for purposes of computing priors (for nnet)

See:

for more details on the Kaldi binary this runs.

Also see https://github.com/kaldi-asr/kaldi/blob/master/egs/wsj/s5/steps/nnet2/train_pnorm_multisplice2.sh for the original bash script that this function was based on.

Parameters:
i : int

Number of the current iteration

nnet_dir : str

Directory of nnet training

prev_egs_dir : str

Directory for training examples from the last iteration

config : NnetBasicConfig

Configuration object for training

num_jobs : int

The number of processes to use in calculation