Module speaker 

Who is speaking, as a vector: the contract every speaker-embedding engine implements.

An engine turns a window of 16 kHz samples into a unit-norm embedding. Two embeddings of one voice point the same way, so their cosine says whether two stretches of speech came from the same person. What to do with that number is policy, kept out of every engine: Diarizer groups voices and claims enrolled names, SegmentReader applies it to the segments a transcription session emits, and PyannoteVoices reads who spoke when from the audio itself, beside the transcriber.

Structs

Chunk

Model outputs for one chunk, reusable across clustering threshold sweeps.

Diarizer

An embedding engine with enrolled profiles and anonymous voice clusters.

EnrolledNon-target_family=wasm

A finished enrollment: the profile to store, and the score worth showing the person who just recorded it.

EnrollmentNon-target_family=wasm

Samples gathered so far, and the engine that measures them.

Grouping

Clustering thresholds, adjustable without rerunning model inference.

Heardsilero and non-target_family=wasm

One finalized segment, as the labeler judged it.

Merged

A voice that turned out to be one already heard.

Profile

One enrolled voice.

ProfileStoreNon-target_family=wasm

The directory of enrolled voices.

PyannoteVoices

Revision

What an observation changed about names already written.

SegmentLabelersilero and non-target_family=wasm

SegmentReadersilero and non-target_family=wasm

Walks the finalized segments of one recording: cuts each segment’s audio out of the window, labels it, and frees what no reader needs any more.

SpeakerName

An enrolled person’s name, which is also their filename. Holding one is proof it cannot escape the speakers directory.

Spoken

One stretch of the recording, and whose voice was in it.

Standing

One voice as it stands right now, for a caller watching a session settle.

StoredProfilesNon-target_family=wasm

Voiceprint

What one local voice sounded like, embedded through its own frame mask.

Enums

EnrollmentErrorNon-target_family=wasm

HeardUpdatesilero and non-target_family=wasm

Label

An enrolled person, or a voice nobody enrolled, numbered in the order it was first heard.

ProfileErrorNon-target_family=wasm

ReplaceNon-target_family=wasm

Whether storing a profile may overwrite one already there.

Role

What an enrolled voice is allowed to be. Only an owner’s voice answers “was that you?”, so a guest can be recognized by name without turning on dictation meant for the person who set the machine up.

SpeakerError

SpeakerNameError

Verdictsilero and non-target_family=wasm

Constants

CLUSTER_THRESHOLD

Similarity threshold for anonymous clusters; short audio windows need a lower gate.

ENROLLED_THRESHOLD

Minimum similarity for claiming an enrolled name.

MIN_SAMPLESNon-target_family=wasm

Below two samples there is nothing to average and no disagreement to measure.

OWN_VOICE_THRESHOLDsilero and non-target_family=wasm

Owner-match threshold below the naming gate to allow short turns. Calibrated on one voice and one synthetic alternative.

Traits

Embedder

Turns audio into a comparable voice vector.

Engine

How an engine is constructed from its own configuration. NAME names the engine in stored profiles and errors; Config carries whatever it needs to load.

Voices

A running account of who is speaking in a recording.

Functions

attribute_spans

Asks a track who owned each paragraph, skipping the ones nobody timed.

centroidNon-target_family=wasm

Normalizes the elementwise mean of unit-length embeddings. Returns None when the mean has no direction.

consistencyNon-target_family=wasm

Mean pairwise cosine similarity of unit-length embeddings.

normalized

Scales a vector to unit length, so cosines are plain dot products. None when the vector has no direction to keep.

settle

Fills missing labels from neighboring speakers. Utterance openings prefer the following label; other gaps prefer the preceding one. All-None input stays unchanged.

validate_model_fileNon-target_family=wasm

crate::backend::validate_model_file, failing as a SpeakerError.