Enum Model 

#[non_exhaustive]
pub enum Model {
    WaveNet(WaveNet),
    Lstm(Lstm),
}

A runnable NAM model of any supported architecture.

Build with Model::from_nam; then call Model::process_buffer on the audio thread. #[non_exhaustive] so future architectures don’t break downstream matches.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

WaveNet(WaveNet)

A WaveNet model.

Lstm(Lstm)

An LSTM model.

Implementations

impl Model

pub fn from_nam(model: &NamModel) -> Result<Self, Error>

Build the runtime matching model.architecture. All allocation happens here.

pub fn process_buffer(&mut self, io: &mut [f32])

Process a buffer of mono samples in place. Allocation-free.

pub fn process_sample(&mut self, x: f32) -> f32

Process a single mono sample. Allocation-free.

pub fn sample_rate(&self) -> f64

The model’s sample rate.

pub fn reset(&mut self)

Reset all internal state to the model’s initial conditions.

Trait Implementations

impl Debug for Model

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

Formats the value using the given formatter.