YuEOptions

Options & Configuration · AiDotNet.Audio.Generation

Configuration options for the YuE music generation model.

Inheritance: ModelOptions → YuEOptions

For Beginners

YuE is like having a virtual band that can write and perform an entire song. You give it lyrics and a style (“pop, female vocalist, upbeat”) and it generates a complete song with singing, instruments, and production. Unlike most AI music tools that only make short clips, YuE can create full-length songs.

How It Works

YuE (Yuan et al., 2025) is a full-song music generation model that generates complete songs with vocals and accompaniment from lyrics and genre/style tags. It uses a dual-AR architecture where a lyrics-conditioned language model generates semantic tokens and a second stage produces acoustic tokens, generating songs of several minutes in length.

Constructors

Constructor Summary
YuEOptions()

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 MaxDurationSeconds { get; set; } Gets or sets the maximum generation duration in seconds.
double RepetitionPenalty { get; set; } Gets or sets the repetition penalty factor.
double Temperature { get; set; } Gets or sets the temperature for sampling.
double TopP { get; set; } Gets or sets the top-p (nucleus) sampling parameter.
int AcousticCodebookSize { get; set; } Gets or sets the acoustic codec codebook size.
int AcousticDim { get; set; } Gets or sets the acoustic stage model dimension.
int LyricsVocabSize { get; set; } Gets or sets the lyrics token vocabulary size.
int NumAcousticHeads { get; set; } Gets or sets the number of acoustic stage attention heads.
int NumAcousticLayers { get; set; } Gets or sets the number of acoustic stage transformer layers.
int NumAcousticQuantizers { get; set; } Gets or sets the number of acoustic codec quantizers.
int NumSemanticHeads { get; set; } Gets or sets the number of semantic stage attention heads.
int NumSemanticLayers { get; set; } Gets or sets the number of semantic stage transformer layers.
int NumStyleTags { get; set; } Gets or sets the number of genre/style tag embeddings.
int SampleRate { get; set; } Gets or sets the output audio sample rate in Hz.
int SemanticDim { get; set; } Gets or sets the semantic stage model dimension.
int SemanticVocabSize { get; set; } Gets or sets the semantic token vocabulary size.
int StyleEmbeddingDim { get; set; } Gets or sets the style embedding dimension.
string ModelPath { get; set; } Gets or sets the path to the ONNX model file.