Class SpeechTranscriptionConfig (2.44.0)

public final class SpeechTranscriptionConfig extends GeneratedMessageV3 implements SpeechTranscriptionConfigOrBuilder

Config for SPEECH_TRANSCRIPTION.

Protobuf type google.cloud.videointelligence.v1.SpeechTranscriptionConfig

Static Fields

AUDIO_TRACKS_FIELD_NUMBER

public static final int AUDIO_TRACKS_FIELD_NUMBER
Field Value
Type Description
int

DIARIZATION_SPEAKER_COUNT_FIELD_NUMBER

public static final int DIARIZATION_SPEAKER_COUNT_FIELD_NUMBER
Field Value
Type Description
int

ENABLE_AUTOMATIC_PUNCTUATION_FIELD_NUMBER

public static final int ENABLE_AUTOMATIC_PUNCTUATION_FIELD_NUMBER
Field Value
Type Description
int

ENABLE_SPEAKER_DIARIZATION_FIELD_NUMBER

public static final int ENABLE_SPEAKER_DIARIZATION_FIELD_NUMBER
Field Value
Type Description
int

ENABLE_WORD_CONFIDENCE_FIELD_NUMBER

public static final int ENABLE_WORD_CONFIDENCE_FIELD_NUMBER
Field Value
Type Description
int

FILTER_PROFANITY_FIELD_NUMBER

public static final int FILTER_PROFANITY_FIELD_NUMBER
Field Value
Type Description
int

LANGUAGE_CODE_FIELD_NUMBER

public static final int LANGUAGE_CODE_FIELD_NUMBER
Field Value
Type Description
int

MAX_ALTERNATIVES_FIELD_NUMBER

public static final int MAX_ALTERNATIVES_FIELD_NUMBER
Field Value
Type Description
int

SPEECH_CONTEXTS_FIELD_NUMBER

public static final int SPEECH_CONTEXTS_FIELD_NUMBER
Field Value
Type Description
int

Static Methods

getDefaultInstance()

public static SpeechTranscriptionConfig getDefaultInstance()
Returns
Type Description
SpeechTranscriptionConfig

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

newBuilder()

public static SpeechTranscriptionConfig.Builder newBuilder()
Returns
Type Description
SpeechTranscriptionConfig.Builder

newBuilder(SpeechTranscriptionConfig prototype)

public static SpeechTranscriptionConfig.Builder newBuilder(SpeechTranscriptionConfig prototype)
Parameter
Name Description
prototype SpeechTranscriptionConfig
Returns
Type Description
SpeechTranscriptionConfig.Builder

parseDelimitedFrom(InputStream input)

public static SpeechTranscriptionConfig parseDelimitedFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static SpeechTranscriptionConfig parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
IOException

parseFrom(byte[] data)

public static SpeechTranscriptionConfig parseFrom(byte[] data)
Parameter
Name Description
data byte[]
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static SpeechTranscriptionConfig parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data byte[]
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data)

public static SpeechTranscriptionConfig parseFrom(ByteString data)
Parameter
Name Description
data ByteString
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static SpeechTranscriptionConfig parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteString
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static SpeechTranscriptionConfig parseFrom(CodedInputStream input)
Parameter
Name Description
input CodedInputStream
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static SpeechTranscriptionConfig parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
IOException

parseFrom(InputStream input)

public static SpeechTranscriptionConfig parseFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static SpeechTranscriptionConfig parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
IOException

parseFrom(ByteBuffer data)

public static SpeechTranscriptionConfig parseFrom(ByteBuffer data)
Parameter
Name Description
data ByteBuffer
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static SpeechTranscriptionConfig parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteBuffer
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechTranscriptionConfig
Exceptions
Type Description
InvalidProtocolBufferException

parser()

public static Parser<SpeechTranscriptionConfig> parser()
Returns
Type Description
Parser<SpeechTranscriptionConfig>

Methods

equals(Object obj)

public boolean equals(Object obj)
Parameter
Name Description
obj Object
Returns
Type Description
boolean
Overrides

getAudioTracks(int index)

public int getAudioTracks(int index)

Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.

repeated int32 audio_tracks = 6 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
int

The audioTracks at the given index.

getAudioTracksCount()

public int getAudioTracksCount()

Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.

repeated int32 audio_tracks = 6 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of audioTracks.

getAudioTracksList()

public List<Integer> getAudioTracksList()

Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.

repeated int32 audio_tracks = 6 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
List<Integer>

A list containing the audioTracks.

getDefaultInstanceForType()

public SpeechTranscriptionConfig getDefaultInstanceForType()
Returns
Type Description
SpeechTranscriptionConfig

getDiarizationSpeakerCount()

public int getDiarizationSpeakerCount()

Optional. If set, specifies the estimated number of speakers in the conversation. If not set, defaults to '2'. Ignored unless enable_speaker_diarization is set to true.

int32 diarization_speaker_count = 8 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The diarizationSpeakerCount.

getEnableAutomaticPunctuation()

public boolean getEnableAutomaticPunctuation()

Optional. If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses. NOTE: "This is currently offered as an experimental service, complimentary to all users. In the future this may be exclusively available as a premium feature."

bool enable_automatic_punctuation = 5 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
boolean

The enableAutomaticPunctuation.

getEnableSpeakerDiarization()

public boolean getEnableSpeakerDiarization()

Optional. If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo. Note: When this is true, we send all the words from the beginning of the audio for the top alternative in every consecutive response. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.

bool enable_speaker_diarization = 7 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
boolean

The enableSpeakerDiarization.

getEnableWordConfidence()

public boolean getEnableWordConfidence()

Optional. If true, the top result includes a list of words and the confidence for those words. If false, no word-level confidence information is returned. The default is false.

bool enable_word_confidence = 9 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
boolean

The enableWordConfidence.

getFilterProfanity()

public boolean getFilterProfanity()

Optional. If set to true, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. "f***". If set to false or omitted, profanities won't be filtered out.

bool filter_profanity = 3 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
boolean

The filterProfanity.

getLanguageCode()

public String getLanguageCode()

Required. Required The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.

string language_code = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
String

The languageCode.

getLanguageCodeBytes()

public ByteString getLanguageCodeBytes()

Required. Required The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.

string language_code = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
ByteString

The bytes for languageCode.

getMaxAlternatives()

public int getMaxAlternatives()

Optional. Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of SpeechRecognitionAlternative messages within each SpeechTranscription. The server may return fewer than max_alternatives. Valid values are 0-30. A value of 0 or 1 will return a maximum of one. If omitted, will return a maximum of one.

int32 max_alternatives = 2 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The maxAlternatives.

getParserForType()

public Parser<SpeechTranscriptionConfig> getParserForType()
Returns
Type Description
Parser<SpeechTranscriptionConfig>
Overrides

getSerializedSize()

public int getSerializedSize()
Returns
Type Description
int
Overrides

getSpeechContexts(int index)

public SpeechContext getSpeechContexts(int index)

Optional. A means to provide context to assist the speech recognition.

repeated .google.cloud.videointelligence.v1.SpeechContext speech_contexts = 4 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int
Returns
Type Description
SpeechContext

getSpeechContextsCount()

public int getSpeechContextsCount()

Optional. A means to provide context to assist the speech recognition.

repeated .google.cloud.videointelligence.v1.SpeechContext speech_contexts = 4 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

getSpeechContextsList()

public List<SpeechContext> getSpeechContextsList()

Optional. A means to provide context to assist the speech recognition.

repeated .google.cloud.videointelligence.v1.SpeechContext speech_contexts = 4 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
List<SpeechContext>

getSpeechContextsOrBuilder(int index)

public SpeechContextOrBuilder getSpeechContextsOrBuilder(int index)

Optional. A means to provide context to assist the speech recognition.

repeated .google.cloud.videointelligence.v1.SpeechContext speech_contexts = 4 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int
Returns
Type Description
SpeechContextOrBuilder

getSpeechContextsOrBuilderList()

public List<? extends SpeechContextOrBuilder> getSpeechContextsOrBuilderList()

Optional. A means to provide context to assist the speech recognition.

repeated .google.cloud.videointelligence.v1.SpeechContext speech_contexts = 4 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
List<? extends com.google.cloud.videointelligence.v1.SpeechContextOrBuilder>

hashCode()

public int hashCode()
Returns
Type Description
int
Overrides

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

newBuilderForType()

public SpeechTranscriptionConfig.Builder newBuilderForType()
Returns
Type Description
SpeechTranscriptionConfig.Builder

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected SpeechTranscriptionConfig.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Name Description
parent BuilderParent
Returns
Type Description
SpeechTranscriptionConfig.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Name Description
unused UnusedPrivateParameter
Returns
Type Description
Object
Overrides

toBuilder()

public SpeechTranscriptionConfig.Builder toBuilder()
Returns
Type Description
SpeechTranscriptionConfig.Builder

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
Name Description
output CodedOutputStream
Overrides
Exceptions
Type Description
IOException