GenreClassifierOptions
Options & Configuration · AiDotNet.Audio.Classification
Options for genre classification after Tzanetakis and Cook 2002: 23 ms analysis windows, 1 s texture windows, 65536-sample beat histogram windows, and a three-component Gaussian mixture per genre.
Inheritance: ModelOptions → GenreClassifierOptions
For Beginners
These options configure the GenreClassifier model. Default values follow the paper (sections III and IV).
Constructors
| Constructor | Summary |
|---|---|
GenreClassifierOptions() |
Initializes a new instance with default values. |
GenreClassifierOptions(GenreClassifierOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
ONNX model options. |
int BeatHop { get; set; } |
Hop between beat histogram windows. |
int BeatWindow { get; set; } |
Samples per beat histogram window. |
int EmIterations { get; set; } |
EM (and K-means initialization) iterations of a fit. |
int FftSize { get; set; } |
Analysis window (and FFT size) in samples. |
int HopLength { get; set; } |
Hop between analysis windows. |
int MixtureComponents { get; set; } |
Gaussians in each genre’s mixture. |
int SampleRate { get; set; } |
Audio sample rate. |
int TextureWindowFrames { get; set; } |
Analysis windows per texture window. |
int TopK { get; set; } |
Number of top predictions to return. |
string ModelPath { get; set; } |
Path to ONNX model file (optional). |
string[] CustomGenres { get; set; } |
Custom genre labels (optional). |