speechbrain.utils¶

Package containing various tools (accuracy, checkpoints …)

`speechbrain.utils.Accuracy`	Calculate accuracy.
`speechbrain.utils.DER`	Calculates Diarization Error Rate (DER) which is the sum of Missed Speaker (MS), False Alarm (FA), and Speaker Error Rate (SER) using md-eval-22.pl from NIST RT Evaluation.
`speechbrain.utils.bleu`
`speechbrain.utils.callchains`	Chaining together callables, if some require relative lengths
`speechbrain.utils.checkpoints`	This module implements a checkpoint saver and loader.
`speechbrain.utils.data_pipeline`	A pipeline for data transformations.
`speechbrain.utils.data_utils`	This library gathers utilities for data io operation.
`speechbrain.utils.depgraph`	A dependency graph for finding evaluation order.
`speechbrain.utils.distributed`	Guard for running certain operations on main process only
`speechbrain.utils.edit_distance`	Edit distance and WER computation.
`speechbrain.utils.epoch_loop`	Implements a checkpointable epoch counter (loop).
`speechbrain.utils.logger`	Managing the logger, utilities
`speechbrain.utils.metric_stats`	The `metric_stats` module provides an abstract class for storing statistics produced over the course of an experiment and summarizing them.
`speechbrain.utils.parameter_transfer`	Convenience functions for the simplest parameter transfer cases.
`speechbrain.utils.superpowers`	Superpowers which should be rarely used.
`speechbrain.utils.torch_audio_backend`
`speechbrain.utils.train_logger`	Loggers for experiment monitoring.

Summary¶