SourceSeparationOptions

Options & Configuration ยท AiDotNet.Audio.SourceSeparation

Options for music source separation.

Inheritance: ModelOptions โ†’ SourceSeparationOptions

For Beginners

These options configure the SourceSeparation model. Default values follow the original paper settings.

Constructors

Constructor Summary
SourceSeparationOptions() Initializes a new instance with default values.
SourceSeparationOptions(SourceSeparationOptions other) Initializes a new instance by copying from another instance.

Properties

Property Summary
OnnxModelOptions OnnxOptions { get; set; } ONNX model options.
int DemucsBaseChannels { get; set; } Channel count of the first Demucs encoder level; it doubles at each level.
int DemucsDepth { get; set; } Number of encoder levels in the native waveform-Demucs stack (mirrored in the decoder).
int DemucsKernelSize { get; set; } Convolution kernel size in the Demucs encoder and decoder.
int DemucsPadding { get; set; } Convolution padding in the Demucs encoder and decoder.
int DemucsStride { get; set; } Convolution stride in the Demucs encoder and decoder.
int FftSize { get; set; } FFT size.
int HopLength { get; set; } Hop length between frames.
int HpssKernelSize { get; set; } HPSS kernel size for spectral separation.
int SampleRate { get; set; } Audio sample rate.
int StemCount { get; set; } Number of stems to separate (2, 4, or 5).
string ModelPath { get; set; } Path to ONNX model file (optional).