Qwen2AudioOptions

Options & Configuration · AiDotNet.Audio.Multimodal

Configuration options for the Qwen2-Audio multimodal audio-language model.

Inheritance: ModelOptions → Qwen2AudioOptions

For Beginners

Qwen2-Audio is like having a conversation partner who can hear. You play it audio and ask questions like “What sounds do you hear?” or “Describe this music.” It uses a powerful language model (similar to ChatGPT) combined with an audio understanding system to provide intelligent responses about any audio input.

How It Works

Qwen2-Audio (Chu et al., 2024, Alibaba) is a large audio-language model that can process audio and text inputs to generate text responses. It uses a Whisper-style audio encoder with a Qwen2 language model backbone, connected by a perceiver-style adapter. It supports audio captioning, question answering, sound event detection, and audio reasoning.

Constructors

Constructor Summary
Qwen2AudioOptions()

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.
double Temperature { get; set; } Gets or sets the sampling temperature.
double TopP { get; set; } Gets or sets the top-p (nucleus) sampling parameter.
int AdapterDim { get; set; } Gets or sets the perceiver adapter output dimension.
int AudioEncoderDim { get; set; } Gets or sets the audio encoder dimension (Whisper-style).
int LMHiddenDim { get; set; } Gets or sets the language model hidden dimension.
int MaxResponseTokens { get; set; } Gets or sets the maximum response length in tokens.
int NumAudioEncoderHeads { get; set; } Gets or sets the number of audio encoder attention heads.
int NumAudioEncoderLayers { get; set; } Gets or sets the number of audio encoder layers.
int NumLMHeads { get; set; } Gets or sets the number of language model attention heads.
int NumLMLayers { get; set; } Gets or sets the number of language model layers.
int NumLatentTokens { get; set; } Gets or sets the number of perceiver latent tokens.
int NumMels { get; set; } Gets or sets the number of mel spectrogram channels.
int SampleRate { get; set; } Gets or sets the audio sample rate in Hz.
int VocabSize { get; set; } Gets or sets the LM vocabulary size.
string ModelPath { get; set; } Gets or sets the path to the ONNX model file.