Struct AudioParameters 

pub struct AudioParameters {
    pub sample_rate: u32,
    pub encoder_filename: String,
    pub decoder_filename: Option<String>,
    pub joiner_filename: Option<String>,
    pub max_audio_seconds: u32,
    pub languages: Vec<String>,
}

Audio model parameters.

Audio ONNX models are typically multi-file bundles (encoder + decoder + optional joiner for RNN-T style models). The filenames map to entries inside the HuggingFace repo. Sample rate is the canonical input rate the model expects; preprocessing resamples to it. languages carries ISO-639 codes for ASR models that advertise specific language coverage.

Fields

sample_rate: u32

Required input sample rate in Hz (typically 16000).

encoder_filename: String

Encoder ONNX filename inside the HF repo bundle.

decoder_filename: Option<String>

Decoder ONNX filename (Whisper-style, RNN-T joiner-decoder split). None for single-encoder models like Moonshine.

joiner_filename: Option<String>

Joiner ONNX filename (RNN-T architectures, e.g., Parakeet TDT).

max_audio_seconds: u32

Maximum audio duration the model can process in one pass.

languages: Vec<String>

Supported languages as ISO-639 codes (e.g., ["en", "de", "fr"]). Empty for monolingual models or where docs don’t specify.

Trait Implementations

impl Clone for AudioParameters

fn clone(&self) -> AudioParameters

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AudioParameters

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for AudioParameters

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for AudioParameters

impl PartialEq for AudioParameters

fn eq(&self, other: &AudioParameters) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for AudioParameters

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for AudioParameters