SarvamASROptions
Options & Configuration ยท AiDotNet.SpeechRecognition.ProprietaryAPI
Options for the Sarvam speech-to-text stand-in, a Conformer encoder with a CTC layer over Indic-script characters.
Inheritance: ModelOptions โ SarvamASROptions
For Beginners
These options set the size of the encoder and decoder, the feature front end and the training augmentation.
How It Works
See SarvamASR for which defaults the vendor or paper discloses and which the stand-in infers.
Constructors
| Constructor | Summary |
|---|---|
SarvamASROptions() |
Initializes a new instance with default values. |
SarvamASROptions(SarvamASROptions 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 standing in for the relative sinusoidal encoding. |
double TimeMaskRatio { get; set; } |
Largest time mask as a fraction of the utterance (pS = 0.05). |
int ConvKernel { get; set; } |
Depthwise convolution kernel (31). |
int EncoderDim { get; set; } |
Conformer width (512). |
int FeedForwardMultiplier { get; set; } |
Expansion of each half-step feed-forward module (Gulati et al. |
int FrequencyMaskWidth { get; set; } |
Largest frequency mask, in mel bins (F = 27). |
int FrequencyMasks { get; set; } |
SpecAugment frequency masks (Park et al. |
int MaxAudioLengthSeconds { get; set; } |
Longest audio a transcription covers, in seconds; longer input is truncated. |
int NumAttentionHeads { get; set; } |
Attention heads per block (8). |
int NumEncoderLayers { get; set; } |
Conformer blocks (18). |
int NumMels { get; set; } |
Log-mel bins (80 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 (10). |
int VocabSize { get; set; } |
Output vocabulary size: token 0 is the blank and every other token is its Unicode code point, through the end of the Malayalam block (U+0D7F). |
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 their Unicode code points. |