MusicFlamingoOptions

Options & Configuration · AiDotNet.Audio.Multimodal

Configuration options for the Music Flamingo model.

Inheritance: ModelOptions → MusicFlamingoOptions

For Beginners

Music Flamingo is like giving a language AI the ability to understand music. You can play it a song and ask “What genre is this?” or “What instruments are playing?” and it will answer in natural language, combining its music listening ability with language understanding.

How It Works

Music Flamingo (2024) adapts the Flamingo architecture specifically for music understanding. It uses a frozen music encoder (e.g., MERT or Jukebox features) with perceiver cross-attention to enable a pre-trained LLM to reason about music: answering questions about genre, instruments, mood, structure, and musical theory.

Constructors

Constructor Summary
MusicFlamingoOptions()

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 MaxAudioDurationSeconds { get; set; } Gets or sets the maximum audio duration in seconds.
int LLMHiddenDim { get; set; } Gets or sets the LLM hidden dimension.
int MaxResponseTokens { get; set; } Gets or sets the maximum response tokens.
int MusicEncoderDim { get; set; } Gets or sets the music encoder dimension.
int NumPerceiverLayers { get; set; } Gets or sets the number of perceiver layers.
int NumPerceiverTokens { get; set; } Gets or sets the number of perceiver latent tokens.
int SampleRate { get; set; } Gets or sets the audio sample rate in Hz.
string ModelPath { get; set; } Gets or sets the path to the ONNX model file.
string Variant { get; set; } Gets or sets the model variant.