CanaryFlashOptions

Options & Configuration · AiDotNet.SpeechRecognition.NeMo

Options for Canary-1B-Flash.

Inheritance: ModelOptions → CanaryFlashOptions

For Beginners

These options set the size of the Conformer encoder, the feature front end and the training augmentation.

How It Works

The defaults: a Fast Conformer encoder of 32 blocks, width 1024, 8 heads, kernel 9, and a 4-layer Transformer decoder.

Constructors

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

Properties

Property Summary
OnnxModelOptions OnnxOptions { get; set; } ONNX runtime options.
double RopeTheta { get; set; } Rotary base of the attention’s relative position encoding, standing in for the paper’s relative sinusoidal encoding (section 2.1).
double TimeMaskRatio { get; set; } Largest time mask as a fraction of the utterance (section 3.1: pS = 0.05).
int ConvKernel { get; set; } Depthwise convolution kernel (Fast Conformer, section 3.1: 9).
int DecoderFeedForwardDim { get; set; } Feed-forward units of each decoder layer (4096).
int EncoderDim { get; set; } Conformer width.
int FeedForwardMultiplier { get; set; } Expansion of each half-step feed-forward module (section 2.3: 4).
int FrequencyMaskWidth { get; set; } Largest frequency mask, in mel bins (section 3.1: F = 27).
int FrequencyMasks { get; set; } SpecAugment frequency masks (section 3.1: 2).
int MaxAudioLengthSeconds { get; set; } Longest audio a transcription covers, in seconds; longer input is truncated.
int MaxTextLength { get; set; } Most tokens a transcription decodes.
int NumAttentionHeads { get; set; } Attention heads per block.
int NumDecoderLayers { get; set; } Transformer decoder layers.
int NumEncoderLayers { get; set; } Conformer blocks.
int NumMels { get; set; } Log-mel bins (Canary: 128-dimensional features every 10 ms over 25 ms windows).
int SampleRate { get; set; } Audio sample rate in Hz.
int SubsamplingChannels { get; set; } Channels of the 8x depthwise-separable subsampling (section 3.1: 256).
int TimeMasks { get; set; } SpecAugment time masks (section 3.1: 10).
int VocabSize { get; set; } Output vocabulary size, blank (token 0) included (Canary: four 1024-token language tokenizers and 32 special tokens).
string Language { get; set; } Language reported for transcriptions.
string ModelPath { get; set; } Path to an exported ONNX model, when one is used.
string[] Vocabulary { get; set; } The text of each token; tokens past the list decode as Unicode code points, and tokens in angle brackets decode to nothing.