Struct MtmdAudioRequest 

pub struct MtmdAudioRequest {
    pub seq_id: i32,
    pub prompt: String,
    pub lang: Option<String>,
    pub top_k: i32,
    pub top_p: f32,
    pub seed: u32,
    pub out_type: MtmdAudioOutType,
}

What to synthesize, and how.

Fields

seq_id: i32

Sequence id to generate under.

prompt: String

Text to speak.

lang: Option<String>

BCP-47-ish language hint, if the pipeline takes one.

top_k: i32

Top-k for the backbone sampler.

top_p: f32

Top-p for the backbone sampler.

seed: u32

Seed; u32::MAX means random.

out_type: MtmdAudioOutType

Container for MtmdAudioGen::output.

Implementations

impl MtmdAudioRequest

pub fn new(prompt: impl Into<String>) -> Self

A request to speak prompt with upstream’s defaults.

Trait Implementations

impl Clone for MtmdAudioRequest

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MtmdAudioRequest

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

Formats the value using the given formatter.