Struct FastSpeech2Synthesizer 

pub struct FastSpeech2Synthesizer { /* private fields */ }

FastSpeech2-style TTS synthesizer.

Non-autoregressive, parallel synthesis for fast inference.

Note

This is a stub - requires model weights.

Implementations

impl FastSpeech2Synthesizer

pub fn new(config: TtsConfig) -> Self

Create new FastSpeech2 synthesizer

pub fn default_config() -> Self

Create with default configuration

pub fn add_speaker(&mut self, speaker: String)

Add a speaker

Trait Implementations

impl Debug for FastSpeech2Synthesizer

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

Formats the value using the given formatter.

impl SpeechSynthesizer for FastSpeech2Synthesizer

fn synthesize( &self, request: &SynthesisRequest, ) -> SpeechResult<SynthesisResult>

Synthesize speech from text.

fn config(&self) -> &TtsConfig

Get the configuration

fn available_speakers(&self) -> Vec<String>

Get available speakers (for multi-speaker models)

fn supports_language(&self, language: &str) -> bool

Check if model supports a language