| 程序包 | 说明 |
|---|---|
| com.litongjava.whipser.cpp.java |
| 限定符和类型 | 方法和说明 |
|---|---|
WhisperFullParams |
WhisperCpp.getFullDefaultParams(WhisperSamplingStrategy strategy)
Provides default params which can be used with `whisper_full()` etc.
|
| 限定符和类型 | 方法和说明 |
|---|---|
String |
WhisperCpp.fullTranscribe(WhisperFullParams whisperParams,
float[] audioData)
Run the entire model: PCM -> log mel spectrogram -> encoder -> decoder -> text.
|
List<WhisperSegment> |
WhisperCpp.fullTranscribeWithTime(WhisperFullParams whisperParams,
float[] audioData) |
int |
WhisperCppJnaLibrary.whisper_full_parallel(com.sun.jna.Pointer ctx,
WhisperFullParams params,
float[] samples,
int n_samples,
int n_processors) |
int |
WhisperCppJnaLibrary.whisper_full_with_state(com.sun.jna.Pointer ctx,
com.sun.jna.Pointer state,
WhisperFullParams params,
float[] samples,
int n_samples) |
int |
WhisperCppJnaLibrary.whisper_full(com.sun.jna.Pointer ctx,
WhisperFullParams params,
float[] samples,
int n_samples)
Run the entire model: PCM -> log mel spectrogram -> encoder -> decoder -> text
Not thread safe for same context
Uses the specified decoding strategy to obtain the text.
|
Copyright © 2023. All rights reserved.