Struct WordErrorRate 

pub struct WordErrorRate { /* private fields */ }

The word error rate (WER) metric, similar to the CER, is defined as the edit distance (e.g. Levenshtein distance) between the predicted and reference word sequences, divided by the total number of words in the reference. Here, the “units” within the sequences are words.

Implementations

impl WordErrorRate

pub fn new() -> WordErrorRate

Creates the metric.

pub fn with_pad_token(self, index: usize) -> WordErrorRate

Sets the pad token.

Trait Implementations

impl Clone for WordErrorRate

fn clone(&self) -> WordErrorRate

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Default for WordErrorRate

fn default() -> WordErrorRate

Returns the “default value” for a type.

impl Metric for WordErrorRate

type Input = WerInput

The input type of the metric.

fn update( &mut self, input: &WerInput, _metadata: &MetricMetadata, ) -> Result<SerializedEntry, TensorReadError>

Update the metric state and returns the current metric entry.

fn compute(&mut self) -> Result<SerializedEntry, TensorReadError>

Compute the final metric value.

fn name(&self) -> Arc<String>

The parameterized name of the metric.

fn clear(&mut self)

Clear the metric state.

fn attributes(&self) -> MetricAttributes

Attributes of the metric.

fn description(&self) -> Option<String>

A short description of the metric.

impl Numeric for WordErrorRate

fn value(&self) -> Option<NumericEntry>

Returns the numeric value of the metric, or None if this metric has no meaningful value yet (e.g. it only accumulates state per batch and computes its value once all state has been accumulated).

fn running_value(&self) -> Option<NumericEntry>

Returns the current aggregated value of the metric over the global step, or None if this metric has no meaningful value yet (e.g. it only accumulates state per batch and computes its value once all state has been accumulated).

fn final_value(&self) -> NumericEntry

Returns the final, authoritative value of the metric for the epoch. Only meaningful after Metric::compute has been called.