Class RecognitionConfig (4.4.0)

public final class RecognitionConfig extends GeneratedMessageV3 implements RecognitionConfigOrBuilder

Provides information to the recognizer that specifies how to process the request.

Protobuf type google.cloud.speech.v1p1beta1.RecognitionConfig

Static Fields

ADAPTATION_FIELD_NUMBER

public static final int ADAPTATION_FIELD_NUMBER
Field Value
TypeDescription
int

ALTERNATIVE_LANGUAGE_CODES_FIELD_NUMBER

public static final int ALTERNATIVE_LANGUAGE_CODES_FIELD_NUMBER
Field Value
TypeDescription
int

AUDIO_CHANNEL_COUNT_FIELD_NUMBER

public static final int AUDIO_CHANNEL_COUNT_FIELD_NUMBER
Field Value
TypeDescription
int

DIARIZATION_CONFIG_FIELD_NUMBER

public static final int DIARIZATION_CONFIG_FIELD_NUMBER
Field Value
TypeDescription
int

DIARIZATION_SPEAKER_COUNT_FIELD_NUMBER

public static final int DIARIZATION_SPEAKER_COUNT_FIELD_NUMBER
Field Value
TypeDescription
int

ENABLE_AUTOMATIC_PUNCTUATION_FIELD_NUMBER

public static final int ENABLE_AUTOMATIC_PUNCTUATION_FIELD_NUMBER
Field Value
TypeDescription
int

ENABLE_SEPARATE_RECOGNITION_PER_CHANNEL_FIELD_NUMBER

public static final int ENABLE_SEPARATE_RECOGNITION_PER_CHANNEL_FIELD_NUMBER
Field Value
TypeDescription
int

ENABLE_SPEAKER_DIARIZATION_FIELD_NUMBER

public static final int ENABLE_SPEAKER_DIARIZATION_FIELD_NUMBER
Field Value
TypeDescription
int

ENABLE_SPOKEN_EMOJIS_FIELD_NUMBER

public static final int ENABLE_SPOKEN_EMOJIS_FIELD_NUMBER
Field Value
TypeDescription
int

ENABLE_SPOKEN_PUNCTUATION_FIELD_NUMBER

public static final int ENABLE_SPOKEN_PUNCTUATION_FIELD_NUMBER
Field Value
TypeDescription
int

ENABLE_WORD_CONFIDENCE_FIELD_NUMBER

public static final int ENABLE_WORD_CONFIDENCE_FIELD_NUMBER
Field Value
TypeDescription
int

ENABLE_WORD_TIME_OFFSETS_FIELD_NUMBER

public static final int ENABLE_WORD_TIME_OFFSETS_FIELD_NUMBER
Field Value
TypeDescription
int

ENCODING_FIELD_NUMBER

public static final int ENCODING_FIELD_NUMBER
Field Value
TypeDescription
int

LANGUAGE_CODE_FIELD_NUMBER

public static final int LANGUAGE_CODE_FIELD_NUMBER
Field Value
TypeDescription
int

MAX_ALTERNATIVES_FIELD_NUMBER

public static final int MAX_ALTERNATIVES_FIELD_NUMBER
Field Value
TypeDescription
int

METADATA_FIELD_NUMBER

public static final int METADATA_FIELD_NUMBER
Field Value
TypeDescription
int

MODEL_FIELD_NUMBER

public static final int MODEL_FIELD_NUMBER
Field Value
TypeDescription
int

PROFANITY_FILTER_FIELD_NUMBER

public static final int PROFANITY_FILTER_FIELD_NUMBER
Field Value
TypeDescription
int

SAMPLE_RATE_HERTZ_FIELD_NUMBER

public static final int SAMPLE_RATE_HERTZ_FIELD_NUMBER
Field Value
TypeDescription
int

SPEECH_CONTEXTS_FIELD_NUMBER

public static final int SPEECH_CONTEXTS_FIELD_NUMBER
Field Value
TypeDescription
int

TRANSCRIPT_NORMALIZATION_FIELD_NUMBER

public static final int TRANSCRIPT_NORMALIZATION_FIELD_NUMBER
Field Value
TypeDescription
int

USE_ENHANCED_FIELD_NUMBER

public static final int USE_ENHANCED_FIELD_NUMBER
Field Value
TypeDescription
int

Static Methods

getDefaultInstance()

public static RecognitionConfig getDefaultInstance()
Returns
TypeDescription
RecognitionConfig

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
TypeDescription
Descriptor

newBuilder()

public static RecognitionConfig.Builder newBuilder()
Returns
TypeDescription
RecognitionConfig.Builder

newBuilder(RecognitionConfig prototype)

public static RecognitionConfig.Builder newBuilder(RecognitionConfig prototype)
Parameter
NameDescription
prototypeRecognitionConfig
Returns
TypeDescription
RecognitionConfig.Builder

parseDelimitedFrom(InputStream input)

public static RecognitionConfig parseDelimitedFrom(InputStream input)
Parameter
NameDescription
inputInputStream
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static RecognitionConfig parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
IOException

parseFrom(byte[] data)

public static RecognitionConfig parseFrom(byte[] data)
Parameter
NameDescription
databyte[]
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static RecognitionConfig parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
databyte[]
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteString data)

public static RecognitionConfig parseFrom(ByteString data)
Parameter
NameDescription
dataByteString
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static RecognitionConfig parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
dataByteString
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static RecognitionConfig parseFrom(CodedInputStream input)
Parameter
NameDescription
inputCodedInputStream
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static RecognitionConfig parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
IOException

parseFrom(InputStream input)

public static RecognitionConfig parseFrom(InputStream input)
Parameter
NameDescription
inputInputStream
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static RecognitionConfig parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
IOException

parseFrom(ByteBuffer data)

public static RecognitionConfig parseFrom(ByteBuffer data)
Parameter
NameDescription
dataByteBuffer
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static RecognitionConfig parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
dataByteBuffer
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
RecognitionConfig
Exceptions
TypeDescription
InvalidProtocolBufferException

parser()

public static Parser<RecognitionConfig> parser()
Returns
TypeDescription
Parser<RecognitionConfig>

Methods

equals(Object obj)

public boolean equals(Object obj)
Parameter
NameDescription
objObject
Returns
TypeDescription
boolean
Overrides

getAdaptation()

public SpeechAdaptation getAdaptation()

Speech adaptation configuration improves the accuracy of speech recognition. For more information, see the speech adaptation documentation. When speech adaptation is set it supersedes the speech_contexts field.

.google.cloud.speech.v1p1beta1.SpeechAdaptation adaptation = 20;

Returns
TypeDescription
SpeechAdaptation

The adaptation.

getAdaptationOrBuilder()

public SpeechAdaptationOrBuilder getAdaptationOrBuilder()

Speech adaptation configuration improves the accuracy of speech recognition. For more information, see the speech adaptation documentation. When speech adaptation is set it supersedes the speech_contexts field.

.google.cloud.speech.v1p1beta1.SpeechAdaptation adaptation = 20;

Returns
TypeDescription
SpeechAdaptationOrBuilder

getAlternativeLanguageCodes(int index)

public String getAlternativeLanguageCodes(int index)

A list of up to 3 additional BCP-47 language tags, listing possible alternative languages of the supplied audio. See Language Support for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).

repeated string alternative_language_codes = 18;

Parameter
NameDescription
indexint

The index of the element to return.

Returns
TypeDescription
String

The alternativeLanguageCodes at the given index.

getAlternativeLanguageCodesBytes(int index)

public ByteString getAlternativeLanguageCodesBytes(int index)

A list of up to 3 additional BCP-47 language tags, listing possible alternative languages of the supplied audio. See Language Support for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).

repeated string alternative_language_codes = 18;

Parameter
NameDescription
indexint

The index of the value to return.

Returns
TypeDescription
ByteString

The bytes of the alternativeLanguageCodes at the given index.

getAlternativeLanguageCodesCount()

public int getAlternativeLanguageCodesCount()

A list of up to 3 additional BCP-47 language tags, listing possible alternative languages of the supplied audio. See Language Support for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).

repeated string alternative_language_codes = 18;

Returns
TypeDescription
int

The count of alternativeLanguageCodes.

getAlternativeLanguageCodesList()

public ProtocolStringList getAlternativeLanguageCodesList()

A list of up to 3 additional BCP-47 language tags, listing possible alternative languages of the supplied audio. See Language Support for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).

repeated string alternative_language_codes = 18;

Returns
TypeDescription
ProtocolStringList

A list containing the alternativeLanguageCodes.

getAudioChannelCount()

public int getAudioChannelCount()

The number of channels in the input audio data. ONLY set this for MULTI-CHANNEL recognition. Valid values for LINEAR16, OGG_OPUS and FLAC are 1-8. Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only 1. If 0 or omitted, defaults to one channel (mono). Note: We only recognize the first channel by default. To perform independent recognition on each channel set enable_separate_recognition_per_channel to 'true'.

int32 audio_channel_count = 7;

Returns
TypeDescription
int

The audioChannelCount.

getDefaultInstanceForType()

public RecognitionConfig getDefaultInstanceForType()
Returns
TypeDescription
RecognitionConfig

getDiarizationConfig()

public SpeakerDiarizationConfig getDiarizationConfig()

Config to enable speaker diarization and set additional parameters to make diarization better suited for your application. Note: When this is enabled, we send all the words from the beginning of the audio for the top alternative in every consecutive STREAMING responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time. For non-streaming requests, the diarization results will be provided only in the top alternative of the FINAL SpeechRecognitionResult.

.google.cloud.speech.v1p1beta1.SpeakerDiarizationConfig diarization_config = 19;

Returns
TypeDescription
SpeakerDiarizationConfig

The diarizationConfig.

getDiarizationConfigOrBuilder()

public SpeakerDiarizationConfigOrBuilder getDiarizationConfigOrBuilder()

Config to enable speaker diarization and set additional parameters to make diarization better suited for your application. Note: When this is enabled, we send all the words from the beginning of the audio for the top alternative in every consecutive STREAMING responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time. For non-streaming requests, the diarization results will be provided only in the top alternative of the FINAL SpeechRecognitionResult.

.google.cloud.speech.v1p1beta1.SpeakerDiarizationConfig diarization_config = 19;

Returns
TypeDescription
SpeakerDiarizationConfigOrBuilder

getDiarizationSpeakerCount() (deprecated)

public int getDiarizationSpeakerCount()

Deprecated. google.cloud.speech.v1p1beta1.RecognitionConfig.diarization_speaker_count is deprecated. See google/cloud/speech/v1p1beta1/cloud_speech.proto;l=382

If set, specifies the estimated number of speakers in the conversation. Defaults to '2'. Ignored unless enable_speaker_diarization is set to true. Note: Use diarization_config instead.

int32 diarization_speaker_count = 17 [deprecated = true];

Returns
TypeDescription
int

The diarizationSpeakerCount.

getEnableAutomaticPunctuation()

public boolean getEnableAutomaticPunctuation()

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.

bool enable_automatic_punctuation = 11;

Returns
TypeDescription
boolean

The enableAutomaticPunctuation.

getEnableSeparateRecognitionPerChannel()

public boolean getEnableSeparateRecognitionPerChannel()

This needs to be set to true explicitly and audio_channel_count > 1 to get each channel recognized separately. The recognition result will contain a channel_tag field to state which channel that result belongs to. If this is not true, we will only recognize the first channel. The request is billed cumulatively for all channels recognized: audio_channel_count multiplied by the length of the audio.

bool enable_separate_recognition_per_channel = 12;

Returns
TypeDescription
boolean

The enableSeparateRecognitionPerChannel.

getEnableSpeakerDiarization() (deprecated)

public boolean getEnableSpeakerDiarization()

Deprecated. google.cloud.speech.v1p1beta1.RecognitionConfig.enable_speaker_diarization is deprecated. See google/cloud/speech/v1p1beta1/cloud_speech.proto;l=377

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: Use diarization_config instead.

bool enable_speaker_diarization = 16 [deprecated = true];

Returns
TypeDescription
boolean

The enableSpeakerDiarization.

getEnableSpokenEmojis()

public BoolValue getEnableSpokenEmojis()

The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.

.google.protobuf.BoolValue enable_spoken_emojis = 23;

Returns
TypeDescription
BoolValue

The enableSpokenEmojis.

getEnableSpokenEmojisOrBuilder()

public BoolValueOrBuilder getEnableSpokenEmojisOrBuilder()

The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.

.google.protobuf.BoolValue enable_spoken_emojis = 23;

Returns
TypeDescription
BoolValueOrBuilder

getEnableSpokenPunctuation()

public BoolValue getEnableSpokenPunctuation()

The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, "how are you question mark" becomes "how are you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.

.google.protobuf.BoolValue enable_spoken_punctuation = 22;

Returns
TypeDescription
BoolValue

The enableSpokenPunctuation.

getEnableSpokenPunctuationOrBuilder()

public BoolValueOrBuilder getEnableSpokenPunctuationOrBuilder()

The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, "how are you question mark" becomes "how are you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.

.google.protobuf.BoolValue enable_spoken_punctuation = 22;

Returns
TypeDescription
BoolValueOrBuilder

getEnableWordConfidence()

public boolean getEnableWordConfidence()

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 = 15;

Returns
TypeDescription
boolean

The enableWordConfidence.

getEnableWordTimeOffsets()

public boolean getEnableWordTimeOffsets()

If true, the top result includes a list of words and the start and end time offsets (timestamps) for those words. If false, no word-level time offset information is returned. The default is false.

bool enable_word_time_offsets = 8;

Returns
TypeDescription
boolean

The enableWordTimeOffsets.

getEncoding()

public RecognitionConfig.AudioEncoding getEncoding()

Encoding of audio data sent in all RecognitionAudio messages. This field is optional for FLAC and WAV audio files and required for all other audio formats. For details, see AudioEncoding.

.google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding encoding = 1;

Returns
TypeDescription
RecognitionConfig.AudioEncoding

The encoding.

getEncodingValue()

public int getEncodingValue()

Encoding of audio data sent in all RecognitionAudio messages. This field is optional for FLAC and WAV audio files and required for all other audio formats. For details, see AudioEncoding.

.google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding encoding = 1;

Returns
TypeDescription
int

The enum numeric value on the wire for encoding.

getLanguageCode()

public String getLanguageCode()

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 = 3 [(.google.api.field_behavior) = REQUIRED];

Returns
TypeDescription
String

The languageCode.

getLanguageCodeBytes()

public ByteString getLanguageCodeBytes()

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 = 3 [(.google.api.field_behavior) = REQUIRED];

Returns
TypeDescription
ByteString

The bytes for languageCode.

getMaxAlternatives()

public int getMaxAlternatives()

Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of SpeechRecognitionAlternative messages within each SpeechRecognitionResult. 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 = 4;

Returns
TypeDescription
int

The maxAlternatives.

getMetadata()

public RecognitionMetadata getMetadata()

Metadata regarding this request.

.google.cloud.speech.v1p1beta1.RecognitionMetadata metadata = 9;

Returns
TypeDescription
RecognitionMetadata

The metadata.

getMetadataOrBuilder()

public RecognitionMetadataOrBuilder getMetadataOrBuilder()

Metadata regarding this request.

.google.cloud.speech.v1p1beta1.RecognitionMetadata metadata = 9;

Returns
TypeDescription
RecognitionMetadataOrBuilder

getModel()

public String getModel()

Which model to select for the given request. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then we auto-select a model based on the parameters in the RecognitionConfig. <table> <tr> <td><b>Model</b></td> <td><b>Description</b></td> </tr> <tr> <td><code>latest_long</code></td> <td>Best for long form content like media or conversation.</td> </tr> <tr> <td><code>latest_short</code></td> <td>Best for short form content like commands or single shot directed speech.</td> </tr> <tr> <td><code>command_and_search</code></td> <td>Best for short queries such as voice commands or voice search.</td> </tr> <tr> <td><code>phone_call</code></td> <td>Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate).</td> </tr> <tr> <td><code>video</code></td> <td>Best for audio that originated from video or includes multiple speakers. Ideally the audio is recorded at a 16khz or greater sampling rate. This is a premium model that costs more than the standard rate.</td> </tr> <tr> <td><code>default</code></td> <td>Best for audio that is not one of the specific audio models. For example, long-form audio. Ideally the audio is high-fidelity, recorded at a 16khz or greater sampling rate.</td> </tr> <tr> <td><code>medical_conversation</code></td> <td>Best for audio that originated from a conversation between a medical provider and patient.</td> </tr> <tr> <td><code>medical_dictation</code></td> <td>Best for audio that originated from dictation notes by a medical provider.</td> </tr> </table>

string model = 13;

Returns
TypeDescription
String

The model.

getModelBytes()

public ByteString getModelBytes()

Which model to select for the given request. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then we auto-select a model based on the parameters in the RecognitionConfig. <table> <tr> <td><b>Model</b></td> <td><b>Description</b></td> </tr> <tr> <td><code>latest_long</code></td> <td>Best for long form content like media or conversation.</td> </tr> <tr> <td><code>latest_short</code></td> <td>Best for short form content like commands or single shot directed speech.</td> </tr> <tr> <td><code>command_and_search</code></td> <td>Best for short queries such as voice commands or voice search.</td> </tr> <tr> <td><code>phone_call</code></td> <td>Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate).</td> </tr> <tr> <td><code>video</code></td> <td>Best for audio that originated from video or includes multiple speakers. Ideally the audio is recorded at a 16khz or greater sampling rate. This is a premium model that costs more than the standard rate.</td> </tr> <tr> <td><code>default</code></td> <td>Best for audio that is not one of the specific audio models. For example, long-form audio. Ideally the audio is high-fidelity, recorded at a 16khz or greater sampling rate.</td> </tr> <tr> <td><code>medical_conversation</code></td> <td>Best for audio that originated from a conversation between a medical provider and patient.</td> </tr> <tr> <td><code>medical_dictation</code></td> <td>Best for audio that originated from dictation notes by a medical provider.</td> </tr> </table>

string model = 13;

Returns
TypeDescription
ByteString

The bytes for model.

getParserForType()

public Parser<RecognitionConfig> getParserForType()
Returns
TypeDescription
Parser<RecognitionConfig>
Overrides

getProfanityFilter()

public boolean getProfanityFilter()

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 profanity_filter = 5;

Returns
TypeDescription
boolean

The profanityFilter.

getSampleRateHertz()

public int getSampleRateHertz()

Sample rate in Hertz of the audio data sent in all RecognitionAudio messages. Valid values are: 8000-48000. 16000 is optimal. For best results, set the sampling rate of the audio source to 16000 Hz. If that's not possible, use the native sample rate of the audio source (instead of re-sampling). This field is optional for FLAC and WAV audio files, but is required for all other audio formats. For details, see AudioEncoding.

int32 sample_rate_hertz = 2;

Returns
TypeDescription
int

The sampleRateHertz.

getSerializedSize()

public int getSerializedSize()
Returns
TypeDescription
int
Overrides

getSpeechContexts(int index)

public SpeechContext getSpeechContexts(int index)

Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see speech adaptation.

repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;

Parameter
NameDescription
indexint
Returns
TypeDescription
SpeechContext

getSpeechContextsCount()

public int getSpeechContextsCount()

Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see speech adaptation.

repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;

Returns
TypeDescription
int

getSpeechContextsList()

public List<SpeechContext> getSpeechContextsList()

Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see speech adaptation.

repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;

Returns
TypeDescription
List<SpeechContext>

getSpeechContextsOrBuilder(int index)

public SpeechContextOrBuilder getSpeechContextsOrBuilder(int index)

Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see speech adaptation.

repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;

Parameter
NameDescription
indexint
Returns
TypeDescription
SpeechContextOrBuilder

getSpeechContextsOrBuilderList()

public List<? extends SpeechContextOrBuilder> getSpeechContextsOrBuilderList()

Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see speech adaptation.

repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;

Returns
TypeDescription
List<? extends com.google.cloud.speech.v1p1beta1.SpeechContextOrBuilder>

getTranscriptNormalization()

public TranscriptNormalization getTranscriptNormalization()

Use transcription normalization to automatically replace parts of the transcript with phrases of your choosing. For StreamingRecognize, this normalization only applies to stable partial transcripts (stability > 0.8) and final transcripts.

.google.cloud.speech.v1p1beta1.TranscriptNormalization transcript_normalization = 24;

Returns
TypeDescription
TranscriptNormalization

The transcriptNormalization.

getTranscriptNormalizationOrBuilder()

public TranscriptNormalizationOrBuilder getTranscriptNormalizationOrBuilder()

Use transcription normalization to automatically replace parts of the transcript with phrases of your choosing. For StreamingRecognize, this normalization only applies to stable partial transcripts (stability > 0.8) and final transcripts.

.google.cloud.speech.v1p1beta1.TranscriptNormalization transcript_normalization = 24;

Returns
TypeDescription
TranscriptNormalizationOrBuilder

getUnknownFields()

public final UnknownFieldSet getUnknownFields()
Returns
TypeDescription
UnknownFieldSet
Overrides

getUseEnhanced()

public boolean getUseEnhanced()

Set to true to use an enhanced model for speech recognition. If use_enhanced is set to true and the model field is not set, then an appropriate enhanced model is chosen if an enhanced model exists for the audio. If use_enhanced is true and an enhanced version of the specified model does not exist, then the speech is recognized using the standard version of the specified model.

bool use_enhanced = 14;

Returns
TypeDescription
boolean

The useEnhanced.

hasAdaptation()

public boolean hasAdaptation()

Speech adaptation configuration improves the accuracy of speech recognition. For more information, see the speech adaptation documentation. When speech adaptation is set it supersedes the speech_contexts field.

.google.cloud.speech.v1p1beta1.SpeechAdaptation adaptation = 20;

Returns
TypeDescription
boolean

Whether the adaptation field is set.

hasDiarizationConfig()

public boolean hasDiarizationConfig()

Config to enable speaker diarization and set additional parameters to make diarization better suited for your application. Note: When this is enabled, we send all the words from the beginning of the audio for the top alternative in every consecutive STREAMING responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time. For non-streaming requests, the diarization results will be provided only in the top alternative of the FINAL SpeechRecognitionResult.

.google.cloud.speech.v1p1beta1.SpeakerDiarizationConfig diarization_config = 19;

Returns
TypeDescription
boolean

Whether the diarizationConfig field is set.

hasEnableSpokenEmojis()

public boolean hasEnableSpokenEmojis()

The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.

.google.protobuf.BoolValue enable_spoken_emojis = 23;

Returns
TypeDescription
boolean

Whether the enableSpokenEmojis field is set.

hasEnableSpokenPunctuation()

public boolean hasEnableSpokenPunctuation()

The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, "how are you question mark" becomes "how are you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.

.google.protobuf.BoolValue enable_spoken_punctuation = 22;

Returns
TypeDescription
boolean

Whether the enableSpokenPunctuation field is set.

hasMetadata()

public boolean hasMetadata()

Metadata regarding this request.

.google.cloud.speech.v1p1beta1.RecognitionMetadata metadata = 9;

Returns
TypeDescription
boolean

Whether the metadata field is set.

hasTranscriptNormalization()

public boolean hasTranscriptNormalization()

Use transcription normalization to automatically replace parts of the transcript with phrases of your choosing. For StreamingRecognize, this normalization only applies to stable partial transcripts (stability > 0.8) and final transcripts.

.google.cloud.speech.v1p1beta1.TranscriptNormalization transcript_normalization = 24;

Returns
TypeDescription
boolean

Whether the transcriptNormalization field is set.

hashCode()

public int hashCode()
Returns
TypeDescription
int
Overrides

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

newBuilderForType()

public RecognitionConfig.Builder newBuilderForType()
Returns
TypeDescription
RecognitionConfig.Builder

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected RecognitionConfig.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
NameDescription
parentBuilderParent
Returns
TypeDescription
RecognitionConfig.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
NameDescription
unusedUnusedPrivateParameter
Returns
TypeDescription
Object
Overrides

toBuilder()

public RecognitionConfig.Builder toBuilder()
Returns
TypeDescription
RecognitionConfig.Builder

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
NameDescription
outputCodedOutputStream
Overrides Exceptions
TypeDescription
IOException