Struct SpeechAct 

#[non_exhaustive]
pub struct SpeechAct {
    pub sentence_index: usize,
    pub label: String,
    pub confidence: f32,
    pub scores: Vec<f32>,
}

One sentence-level classification result.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

sentence_index: usize

Index into NlpResult::sentences.

label: String

Class label (e.g. "STATEMENT", "QUESTION", "GREETING").

Equals the label of the argmax of scores.

confidence: f32

Provider-reported confidence in [0.0, 1.0].

Equals scores[argmax] — the probability of the winning label.

scores: Vec<f32>

Full per-class softmax over the model’s dialog-act vocabulary.

Parallel to NlpLabelMaps::cls: scores[i] is the probability of the class named cls[i], and the values sum to ~1.0. Empty when the model does not expose a distribution. Lets consumers do thresholded multi-label gating instead of relying on the top-1 label.

Trait Implementations

impl Clone for SpeechAct

fn clone(&self) -> SpeechAct

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SpeechAct

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for SpeechAct

fn default() -> SpeechAct

Returns the “default value” for a type.