Struct AudioSpectrogramConfig

pub struct AudioSpectrogramConfig {
    pub num_mel_bins: usize,
    pub hop_length: usize,
    pub window_size: usize,
}

Configuration for generating audio spectrograms.

This struct contains the parameters needed to compute mel-scale spectrograms from audio waveforms, which are used in audio tokenization.

Fields

• num_mel_bins - Number of mel-frequency bins (typically 80 or 128)
• hop_length - Length of overlapping windows for STFT (typically 160)
• window_size - Window size for Fourier transform (typically 400)

Fields

num_mel_bins: usize

hop_length: usize

window_size: usize

Implementations

impl AudioSpectrogramConfig

pub fn new( num_mel_bins: usize, hop_length: usize, window_size: usize, ) -> Result<Self>

Creates a new AudioSpectrogramConfig with validation.

Arguments

• num_mel_bins - Number of mel-frequency bins (must be > 0)
• hop_length - Length of overlapping windows for STFT (must be > 0)
• window_size - Window size for Fourier transform (must be > 0)

Returns

A new AudioSpectrogramConfig instance.

Errors

Returns an error if any parameter is zero or invalid.

Examples

use tekken::audio::AudioSpectrogramConfig;

let config = AudioSpectrogramConfig::new(80, 160, 400)?;

Trait Implementations

impl Clone for AudioSpectrogramConfig

fn clone(&self) -> AudioSpectrogramConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AudioSpectrogramConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for AudioSpectrogramConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for AudioSpectrogramConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.