TriphoneTrainer

class aligner.trainers.TriphoneTrainer(default_feature_config)[source]

Configuration class for triphone training

Attributes:
num_iterations : int

Number of training iterations to perform, defaults to 40

transition_scale : float

Scaling of transition costs in alignment, defaults to 1.0

acoustic_scale : float

Scaling of acoustic costs in alignment, defaults to 0.1

self_loop_scale : float

Scaling of self loop costs in alignment, defaults to 0.1

beam : int

Default beam width for alignment, defaults = 10

retry_beam : int

Beam width to fall back on if no alignment is produced, defaults to 40

max_gaussians : int

Total number of gaussians, defaults to 1000

boost_silence : float

Factor by which to boost silence likelihoods in alignment, defaults to 1.0

realignment_iterations : list

List of iterations to perform alignment

power : float

Exponent for number of gaussians according to occurrence counts, defaults to 0.25

num_leaves : int

Number of states in the decision tree, defaults to 1000

max_gaussians : int

Number of gaussians in the decision tree, defaults to 10000

cluster_threshold : int

For build-tree control final bottom-up clustering of leaves, defaults to 100

Attributes

align_directory
align_log_directory
feature_file_base_name
final_gaussian_iteration
gaussian_increment
log_directory
meta
phone_type
train_directory
train_type

Methods

align(subset[, call_back])
compute_calculated_properties()
export_textgrids() Export a TextGrid file for every sound file in the dataset
get_unaligned_utterances()
init_training(identifier, …)
parse_log_directory(directory, iteration, …) Parse error files and relate relevant information about unaligned files
save(path) Output an acoustic model and dictionary to the specified path
train([call_back])
update(data)