Class Audio2Vowels
Definition
- Assembly:
- Tizen.AIAvatar.dll
The Audio2Vowels class is responsible for predicting vowels from audio data using a pre-trained TensorFlow model.
public class Audio2Vowels- Inheritance
-
objectAudio2Vowels
Constructors
View SourceAudio2Vowels(string)
Initializes a new instance of the Audio2Vowels class with the specified TensorFlow model file path.
Declaration
public Audio2Vowels(string tensorflowFilePath)Parameters
| Type | Name | Description |
|---|---|---|
| string | tensorflowFilePath | The path to the pre-trained TensorFlow model file. |
Methods
View SourceGetSampleRate()
Gets the current sample rate of the audio data.
Declaration
public int GetSampleRate()Returns
| Type | Description |
|---|---|
| int | The current sample rate. |
PredictVowels(byte[])
Predicts the vowels present in the given audio data.
Declaration
public string[] PredictVowels(byte[] audioData)Parameters
| Type | Name | Description |
|---|---|---|
| byte[] | audioData | The audio data to analyze. |
Returns
| Type | Description |
|---|---|
| string[] | An array of predicted vowels. |
SetSampleRate(int)
Sets the sample rate of the audio data.
Declaration
public void SetSampleRate(int rate)Parameters
| Type | Name | Description |
|---|---|---|
| int | rate | The sample rate to set. |