SelfConditionedCTCOptions
Options & Configuration ยท AiDotNet.SpeechRecognition.CTCVariants
Options for Self-conditioned CTC.
Inheritance: ModelOptions โ SelfConditionedCTCOptions
For Beginners
These options set the size of the Transformer encoder, the feature front end and the training augmentation.
How It Works
The defaults: a 18-layer Transformer encoder, width 256, 4 heads, 2048 feed-forward units and a CTC layer.
Constructors
| Constructor | Summary |
|---|---|
SelfConditionedCTCOptions() |
Initializes a new instance with default values. |
SelfConditionedCTCOptions(SelfConditionedCTCOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
ONNX runtime options. |
double IntermediateCtcWeight { get; set; } |
Weight w of the mean intermediate CTC loss in (1 - w) L_CTC + w L_inter. |
double TimeMaskRatio { get; set; } |
Largest time mask as a fraction of the utterance (section 3.1: pS = 0.05). |
int EncoderDim { get; set; } |
Conformer width. |
int FeedForwardMultiplier { get; set; } |
Expansion of each feed-forward network: 2048 units at width 256. |
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 NumAttentionHeads { get; set; } |
Attention heads per block. |
int NumEncoderLayers { get; set; } |
Conformer blocks. |
int NumMels { get; set; } |
Log-mel bins (section 3.1: 80-channel filterbanks over 25 ms windows with a 10 ms stride). |
int SampleRate { get; set; } |
Audio sample rate in Hz. |
int TimeMasks { get; set; } |
SpecAugment time masks (section 3.1: 10). |
int VocabSize { get; set; } |
Output vocabulary size, blank (token 0) included. |
int[] IntermediateCtcLayers { get; set; } |
Encoder layers (1-based) whose outputs get an intermediate CTC loss through the shared CTC layer. |
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. |