MadmomBeatTrackerOptions
Options & Configuration ยท AiDotNet.Audio.MusicAnalysis
Configuration options for the Madmom-style neural beat tracker.
Inheritance: ModelOptions โ MadmomBeatTrackerOptions
For Beginners
This model listens to music and finds exactly where each beat falls, like a musician tapping their foot in time. It can tell you the tempo (beats per minute) and mark every beat position, which is essential for music synchronization, DJ software, and automatic remixing.
How It Works
The Madmom beat tracking system (Bock et al., 2016) uses a recurrent neural network to detect beat positions and downbeat positions in audio. It combines spectrogram features with bidirectional RNNs and a dynamic Bayesian network for beat tracking, achieving state-of-the-art results on multiple beat tracking benchmarks.
Constructors
| Constructor | Summary |
|---|---|
MadmomBeatTrackerOptions() |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
Gets or sets the ONNX runtime options. |
double DropoutRate { get; set; } |
Gets or sets the dropout rate. |
double LearningRate { get; set; } |
Gets or sets the learning rate. |
double MaxGradientNorm { get; set; } |
Gets or sets the gradient-clipping norm used when no optimizer is injected. |
double MinBeatInterval { get; set; } |
Gets or sets the minimum inter-beat interval in seconds. |
double PeakThreshold { get; set; } |
Gets or sets the peak picking threshold for beat detection. |
int FftSize { get; set; } |
Gets or sets the FFT window size. |
int HopLength { get; set; } |
Gets or sets the hop length between frames. |
int NumBands { get; set; } |
Gets or sets the number of spectrogram bands. |
int NumRnnLayers { get; set; } |
Gets or sets the number of RNN layers. |
int RnnHiddenSize { get; set; } |
Gets or sets the RNN hidden size. |
int SampleRate { get; set; } |
Gets or sets the expected audio sample rate in Hz. |
string ModelPath { get; set; } |
Gets or sets the path to the ONNX model file. |