Struct Sv2TtsSpeakerEncoder 

pub struct Sv2TtsSpeakerEncoder { /* private fields */ }

SV2TTS-based speaker encoder.

Reference: Jia et al., 2018 - Transfer Learning from Speaker Verification to TTS.

Note

This is a stub - requires model weights.

Implementations

impl Sv2TtsSpeakerEncoder

pub fn new(embedding_dim: usize) -> Sv2TtsSpeakerEncoder

Create new SV2TTS speaker encoder

pub fn default_config() -> Sv2TtsSpeakerEncoder

Create with default dimension (256)

Trait Implementations

impl Debug for Sv2TtsSpeakerEncoder

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

Formats the value using the given formatter.

impl SpeakerEncoder for Sv2TtsSpeakerEncoder

fn encode(&self, audio: &[f32]) -> Result<SpeakerEmbedding, VoiceError>

Encode speaker from audio to embedding.

fn embedding_dim(&self) -> usize

Get embedding dimension