Skip to main content

Vocoder

aprender::speech::tts

Trait Vocoder 

Source 
pub trait Vocoder {
    // Required methods
    fn vocalize(&self, mel: &[Vec<f32>]) -> Result<Vec<f32>, SpeechError>;
    fn sample_rate(&self) -> u32;
    fn n_mels(&self) -> usize;
}
Expand description

Trait for neural vocoder (mel to audio).

Required Methods§

Source

fn vocalize(&self, mel: &[Vec<f32>]) -> Result<Vec<f32>, SpeechError>

Convert mel spectrogram to audio.

§Arguments
  • mel - Mel spectrogram (n_mels x frames)
§Returns

Audio samples.

§Errors

Returns error if conversion fails.

Source

fn sample_rate(&self) -> u32

Get output sample rate

Source

fn n_mels(&self) -> usize

Get expected number of mel channels

Dyn Compatibility§

This trait is dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementors§