WhisperFullParams (whipser-cpp-java 1.0.0 API)

java.lang.Object
- com.sun.jna.Structure
- - com.litongjava.whipser.cpp.java.params.WhisperFullParams

```
public class WhisperFullParams
extends com.sun.jna.Structure
```
Parameters for the whisper_full() function. If you change the order or add new parameters, make sure to update the default values in whisper.cpp: whisper_full_default_params()

嵌套类概要
- 从类继承的嵌套类/接口 com.sun.jna.Structure
  com.sun.jna.Structure.ByReference, com.sun.jna.Structure.ByValue, com.sun.jna.Structure.FieldOrder, com.sun.jna.Structure.StructField

字段概要

字段
限定符和类型	字段和说明
`int`	`audio_ctx` Overwrite the audio context size (0 = use default).
`BeamSearchParams`	`beam_search` Beam search decoding parameters.
`CBool`	`detect_language` Flag to indicate whether to detect language automatically.
`int`	`duration_ms` Audio duration to process in milliseconds.
`com.sun.jna.Pointer`	`encoder_begin_callback` Callback each time before the encoder starts.
`com.sun.jna.Pointer`	`encoder_begin_callback_user_data` User data for the encoder_begin_callback.
`float`	`entropy_thold` Entropy threshold (similar to OpenAI's "compression_ratio_threshold").
`GreedyParams`	`greedy` Greedy decoding parameters.
`String`	`initial_prompt` Tokens to provide to the whisper decoder as an initial prompt.
`String`	`language` Language for auto-detection.
`float`	`length_penalty` Length penalty.
`com.sun.jna.Pointer`	`logits_filter_callback` Callback by each decoder to filter obtained logits.
`com.sun.jna.Pointer`	`logits_filter_callback_user_data` User data for the logits_filter_callback.
`float`	`logprob_thold` Log probability threshold.
`float`	`max_initial_ts` Maximum initial timestamp.
`int`	`max_len` Maximum segment length in characters.
`int`	`max_tokens` Maximum tokens per segment (0, default = no limit)
`int`	`n_max_text_ctx` Maximum tokens to use from past text as a prompt for the decoder.
`int`	`n_threads` Number of threads.
`com.sun.jna.Pointer`	`new_segment_callback` Callback for every newly generated text segment.
`com.sun.jna.Pointer`	`new_segment_callback_user_data` User data for the new_segment_callback.
`CBool`	`no_context` Flag to indicate whether to use past transcription (if any) as an initial prompt for the decoder.
`float`	`no_speech_thold` No speech threshold.
`int`	`offset_ms` Start offset in milliseconds.
`CBool`	`print_progress` Flag to print progress information.
`CBool`	`print_realtime` Flag to print results from within whisper.cpp (avoid it, use callback instead).
`CBool`	`print_special` Flag to print special tokens (e.g., <SOT>, <EOT>, <BEG>, etc.).
`CBool`	`print_timestamps` Flag to print timestamps for each text segment when printing realtime.
`com.sun.jna.Pointer`	`progress_callback` Callback on each progress update.
`com.sun.jna.Pointer`	`progress_callback_user_data` User data for the progress_callback.
`int`	`prompt_n_tokens` Number of prompt tokens.
`com.sun.jna.Pointer`	`prompt_tokens` Prompt tokens.
`CBool`	`single_segment` Flag to force single segment output (useful for streaming).
`CBool`	`speed_up` Flag to speed up the audio by 2x using Phase Vocoder.
`CBool`	`split_on_word` Flag to split on word rather than on token (when used with max_len).
`int`	`strategy` Sampling strategy for whisper_full() function.
`CBool`	`suppress_blank` Flag to suppress blank tokens.
`CBool`	`suppress_non_speech_tokens` Flag to suppress non-speech tokens.
`CBool`	`tdrz_enable` Enable tinydiarize (default = false)
`float`	`temperature` Initial decoding temperature.
`float`	`temperature_inc` Temperature increment.
`float`	`thold_pt` [EXPERIMENTAL] Timestamp token probability threshold (~0.01).
`float`	`thold_ptsum` [EXPERIMENTAL] Timestamp token sum probability threshold (~0.01).
`CBool`	`token_timestamps` [EXPERIMENTAL] Flag to enable token-level timestamps.
`CBool`	`translate` Translate flag.

从类继承的字段 com.sun.jna.Structure
ALIGN_DEFAULT, ALIGN_GNUC, ALIGN_MSVC, ALIGN_NONE, CALCULATE_SIZE

构造器概要

构造器
构造器和说明

WhisperFullParams(com.sun.jna.Pointer p)

构造器
构造器和说明
`WhisperFullParams(com.sun.jna.Pointer p)`

方法概要

所有方法实例方法具体方法
限定符和类型	方法和说明
`void`	`detectLanguage(boolean enable)` Flag to indicate whether to detect language automatically.
`void`	`enableContext(boolean enable)` Flag to indicate whether to use past transcription (if any) as an initial prompt for the decoder.
`protected List<String>`	`getFieldOrder()`
`void`	`printProgress(boolean enable)` Flag to print progress information.
`void`	`printRealtime(boolean enable)` Flag to print results from within whisper.cpp (avoid it, use callback instead).
`void`	`printSpecial(boolean enable)` Flag to print special tokens (e.g., <SOT>, <EOT>, <BEG>, etc.).
`void`	`printTimestamps(boolean enable)` Flag to print timestamps for each text segment when printing realtime.
`void`	`setBeamSize(int beamSize)`
`void`	`setBeamSizeAndPatience(int beamSize, float patience)`
`void`	`setBestOf(int bestOf)`
`void`	`setEncoderBeginCallbackeginCallbackCallback(WhisperEncoderBeginCallback callback)`
`void`	`setLogitsFilterCallback(WhisperLogitsFilterCallback callback)`
`void`	`setNewSegmentCallback(WhisperNewSegmentCallback callback)`
`void`	`setProgressCallback(WhisperProgressCallback callback)`
`void`	`setPromptTokens(int[] tokens)`
`void`	`singleSegment(boolean single)` Flag to force single segment output (useful for streaming).
`void`	`speedUp(boolean enable)` Flag to speed up the audio by 2x using Phase Vocoder.
`void`	`splitOnWord(boolean enable)` Flag to split on word rather than on token (when used with max_len).
`void`	`suppressBlanks(boolean enable)`
`void`	`suppressNonSpeechTokens(boolean enable)` Flag to suppress non-speech tokens.
`void`	`tdrzEnable(boolean enable)` Enable tinydiarize (default = false)
`void`	`tokenTimestamps(boolean enable)` [EXPERIMENTAL] Flag to enable token-level timestamps.
`void`	`transcribeMode()` The compliment of translateMode()
`void`	`translateMode()` The compliment of transcribeMode()

从类继承的方法 com.sun.jna.Structure
allocateMemory, allocateMemory, autoAllocate, autoRead, autoRead, autoWrite, autoWrite, cacheTypeInfo, calculateSize, clear, createFieldsOrder, createFieldsOrder, createFieldsOrder, createFieldsOrder, dataEquals, dataEquals, ensureAllocated, equals, fieldOffset, getAutoRead, getAutoWrite, getFieldList, getFields, getNativeAlignment, getNativeSize, getNativeSize, getPointer, getStringEncoding, getStructAlignment, hashCode, newInstance, newInstance, read, readField, readField, setAlignType, setAutoRead, setAutoSynch, setAutoWrite, setStringEncoding, size, sortFields, toArray, toArray, toString, toString, useMemory, useMemory, write, writeField, writeField, writeField

从类继承的方法 java.lang.Object
clone, finalize, getClass, notify, notifyAll, wait, wait, wait

- 字段详细资料
  - strategy
```
public int strategy
```
    Sampling strategy for whisper_full() function.
  - n_threads
```
public int n_threads
```
    Number of threads. (default = 4)
  - n_max_text_ctx
```
public int n_max_text_ctx
```
    Maximum tokens to use from past text as a prompt for the decoder. (default = 16384)
  - offset_ms
```
public int offset_ms
```
    Start offset in milliseconds. (default = 0)
  - duration_ms
```
public int duration_ms
```
    Audio duration to process in milliseconds. (default = 0)
  - translate
```
public CBool translate
```
    Translate flag. (default = false)
  - no_context
```
public CBool no_context
```
    Flag to indicate whether to use past transcription (if any) as an initial prompt for the decoder. (default = true)
  - single_segment
```
public CBool single_segment
```
    Flag to force single segment output (useful for streaming). (default = false)
  - print_special
```
public CBool print_special
```
    Flag to print special tokens (e.g., <SOT>, <EOT>, <BEG>, etc.). (default = false)
  - print_progress
```
public CBool print_progress
```
    Flag to print progress information. (default = true)
  - print_realtime
```
public CBool print_realtime
```
    Flag to print results from within whisper.cpp (avoid it, use callback instead). (default = true)
  - print_timestamps
```
public CBool print_timestamps
```
    Flag to print timestamps for each text segment when printing realtime. (default = true)
  - token_timestamps
```
public CBool token_timestamps
```
    [EXPERIMENTAL] Flag to enable token-level timestamps. (default = false)
  - thold_pt
```
public float thold_pt
```
    [EXPERIMENTAL] Timestamp token probability threshold (~0.01). (default = 0.01)
  - thold_ptsum
```
public float thold_ptsum
```
    [EXPERIMENTAL] Timestamp token sum probability threshold (~0.01).
  - max_len
```
public int max_len
```
    Maximum segment length in characters. (default = 0)
  - split_on_word
```
public CBool split_on_word
```
    Flag to split on word rather than on token (when used with max_len). (default = false)
  - max_tokens
```
public int max_tokens
```
    Maximum tokens per segment (0, default = no limit)
  - speed_up
```
public CBool speed_up
```
    Flag to speed up the audio by 2x using Phase Vocoder. (default = false)
  - audio_ctx
```
public int audio_ctx
```
    Overwrite the audio context size (0 = use default).
  - tdrz_enable
```
public CBool tdrz_enable
```
    Enable tinydiarize (default = false)
  - initial_prompt
```
public String initial_prompt
```
    Tokens to provide to the whisper decoder as an initial prompt. These are prepended to any existing text context from a previous call.
  - prompt_tokens
```
public com.sun.jna.Pointer prompt_tokens
```
    Prompt tokens. (int*)
  - prompt_n_tokens
```
public int prompt_n_tokens
```
    Number of prompt tokens.
  - language
```
public String language
```
    Language for auto-detection. For auto-detection, set to `null`, `""`, or "auto".
  - detect_language
```
public CBool detect_language
```
    Flag to indicate whether to detect language automatically.
  - suppress_blank
```
public CBool suppress_blank
```
    Flag to suppress blank tokens.
  - suppress_non_speech_tokens
```
public CBool suppress_non_speech_tokens
```
    Flag to suppress non-speech tokens.
  - temperature
```
public float temperature
```
    Initial decoding temperature.
  - max_initial_ts
```
public float max_initial_ts
```
    Maximum initial timestamp.
  - length_penalty
```
public float length_penalty
```
    Length penalty.
  - temperature_inc
```
public float temperature_inc
```
    Temperature increment.
  - entropy_thold
```
public float entropy_thold
```
    Entropy threshold (similar to OpenAI's "compression_ratio_threshold").
  - logprob_thold
```
public float logprob_thold
```
    Log probability threshold.
  - no_speech_thold
```
public float no_speech_thold
```
    No speech threshold.
  - greedy
```
public GreedyParams greedy
```
    Greedy decoding parameters.
  - beam_search
```
public BeamSearchParams beam_search
```
    Beam search decoding parameters.
  - new_segment_callback
```
public com.sun.jna.Pointer new_segment_callback
```
    Callback for every newly generated text segment. WhisperNewSegmentCallback
  - new_segment_callback_user_data
```
public com.sun.jna.Pointer new_segment_callback_user_data
```
    User data for the new_segment_callback.
  - progress_callback
```
public com.sun.jna.Pointer progress_callback
```
    Callback on each progress update. WhisperProgressCallback
  - progress_callback_user_data
```
public com.sun.jna.Pointer progress_callback_user_data
```
    User data for the progress_callback.
  - encoder_begin_callback
```
public com.sun.jna.Pointer encoder_begin_callback
```
    Callback each time before the encoder starts. WhisperEncoderBeginCallback
  - encoder_begin_callback_user_data
```
public com.sun.jna.Pointer encoder_begin_callback_user_data
```
    User data for the encoder_begin_callback.
  - logits_filter_callback
```
public com.sun.jna.Pointer logits_filter_callback
```
    Callback by each decoder to filter obtained logits. WhisperLogitsFilterCallback
  - logits_filter_callback_user_data
```
public com.sun.jna.Pointer logits_filter_callback_user_data
```
    User data for the logits_filter_callback.
- 构造器详细资料
  - WhisperFullParams
```
public WhisperFullParams(com.sun.jna.Pointer p)
```
- 方法详细资料
  - transcribeMode
```
public void transcribeMode()
```
    The compliment of translateMode()
  - translateMode
```
public void translateMode()
```
    The compliment of transcribeMode()
  - enableContext
```
public void enableContext(boolean enable)
```
    Flag to indicate whether to use past transcription (if any) as an initial prompt for the decoder. (default = true)
  - singleSegment
```
public void singleSegment(boolean single)
```
    Flag to force single segment output (useful for streaming). (default = false)
  - printSpecial
```
public void printSpecial(boolean enable)
```
    Flag to print special tokens (e.g., <SOT>, <EOT>, <BEG>, etc.). (default = false)
  - printProgress
```
public void printProgress(boolean enable)
```
    Flag to print progress information. (default = true)
  - printRealtime
```
public void printRealtime(boolean enable)
```
    Flag to print results from within whisper.cpp (avoid it, use callback instead). (default = true)
  - printTimestamps
```
public void printTimestamps(boolean enable)
```
    Flag to print timestamps for each text segment when printing realtime. (default = true)
  - tokenTimestamps
```
public void tokenTimestamps(boolean enable)
```
    [EXPERIMENTAL] Flag to enable token-level timestamps. (default = false)
  - splitOnWord
```
public void splitOnWord(boolean enable)
```
    Flag to split on word rather than on token (when used with max_len). (default = false)
  - speedUp
```
public void speedUp(boolean enable)
```
    Flag to speed up the audio by 2x using Phase Vocoder. (default = false)
  - tdrzEnable
```
public void tdrzEnable(boolean enable)
```
    Enable tinydiarize (default = false)
  - setPromptTokens
```
public void setPromptTokens(int[] tokens)
```
  - detectLanguage
```
public void detectLanguage(boolean enable)
```
    Flag to indicate whether to detect language automatically.
  - suppressBlanks
```
public void suppressBlanks(boolean enable)
```
  - suppressNonSpeechTokens
```
public void suppressNonSpeechTokens(boolean enable)
```
    Flag to suppress non-speech tokens.
  - setBestOf
```
public void setBestOf(int bestOf)
```
  - setBeamSize
```
public void setBeamSize(int beamSize)
```
  - setBeamSizeAndPatience
```
public void setBeamSizeAndPatience(int beamSize,
                                   float patience)
```
  - setNewSegmentCallback
```
public void setNewSegmentCallback(WhisperNewSegmentCallback callback)
```
  - setProgressCallback
```
public void setProgressCallback(WhisperProgressCallback callback)
```
  - setEncoderBeginCallbackeginCallbackCallback
```
public void setEncoderBeginCallbackeginCallbackCallback(WhisperEncoderBeginCallback callback)
```
  - setLogitsFilterCallback
```
public void setLogitsFilterCallback(WhisperLogitsFilterCallback callback)
```
  - getFieldOrder
```
protected List<String> getFieldOrder()
```
    覆盖:
    
    getFieldOrder 在类中 com.sun.jna.Structure

类 WhisperFullParams

嵌套类概要

从类继承的嵌套类/接口 com.sun.jna.Structure

字段概要

从类继承的字段 com.sun.jna.Structure

构造器概要

方法概要

从类继承的方法 com.sun.jna.Structure

从类继承的方法 java.lang.Object

字段详细资料

strategy

n_threads

n_max_text_ctx

offset_ms

duration_ms

translate

no_context

single_segment

print_special

print_progress

print_realtime

print_timestamps

token_timestamps

thold_pt

thold_ptsum

max_len

split_on_word

max_tokens

speed_up

audio_ctx

tdrz_enable

initial_prompt

prompt_tokens

prompt_n_tokens

language

detect_language

suppress_blank

suppress_non_speech_tokens

temperature

max_initial_ts

length_penalty

temperature_inc

entropy_thold

logprob_thold

no_speech_thold

greedy

beam_search

new_segment_callback

new_segment_callback_user_data

progress_callback

progress_callback_user_data

encoder_begin_callback

encoder_begin_callback_user_data

logits_filter_callback

logits_filter_callback_user_data

构造器详细资料

WhisperFullParams

方法详细资料

transcribeMode

translateMode

enableContext

singleSegment

printSpecial

printProgress

printRealtime

printTimestamps

tokenTimestamps

splitOnWord

speedUp

tdrzEnable

setPromptTokens

detectLanguage

suppressBlanks

suppressNonSpeechTokens

setBestOf

setBeamSize

setBeamSizeAndPatience

setNewSegmentCallback

setProgressCallback

setEncoderBeginCallbackeginCallbackCallback