com.google.cloud.videointelligence.v1p3beta1

Interface SpeechTranscriptionConfigOrBuilder

All Superinterfaces:

com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder

All Known Implementing Classes:

SpeechTranscriptionConfig, SpeechTranscriptionConfig.Builder

public interface SpeechTranscriptionConfigOrBuilder
extends com.google.protobuf.MessageOrBuilder

Method Summary

Modifier and Type	Method and Description
int	getAudioTracks(int index) *Optional* For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks.
int	getAudioTracksCount() *Optional* For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks.
List<Integer>	getAudioTracksList() *Optional* For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks.
int	getDiarizationSpeakerCount() *Optional* If set, specifies the estimated number of speakers in the conversation.
boolean	getEnableAutomaticPunctuation() *Optional* If 'true', adds punctuation to recognition result hypotheses.
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.
boolean	getEnableWordConfidence() *Optional* If `true`, the top result includes a list of words and the confidence for those words.
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.
String	getLanguageCode() *Required* The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
com.google.protobuf.ByteString	getLanguageCodeBytes() *Required* The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
int	getMaxAlternatives() *Optional* Maximum number of recognition hypotheses to be returned.
SpeechContext	getSpeechContexts(int index) *Optional* A means to provide context to assist the speech recognition.
int	getSpeechContextsCount() *Optional* A means to provide context to assist the speech recognition.
List<SpeechContext>	getSpeechContextsList() *Optional* A means to provide context to assist the speech recognition.
SpeechContextOrBuilder	getSpeechContextsOrBuilder(int index) *Optional* A means to provide context to assist the speech recognition.
List<? extends SpeechContextOrBuilder>	getSpeechContextsOrBuilderList() *Optional* A means to provide context to assist the speech recognition.

Methods inherited from interface com.google.protobuf.MessageOrBuilder

findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof

Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

isInitialized

Method Detail

getLanguageCode

String getLanguageCode()

 *Required* The language of the supplied audio as a
 [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
 Example: "en-US".
 See [Language Support](https://cloud.google.com/speech/docs/languages)
 for a list of the currently supported language codes.
 

string language_code = 1;

getLanguageCodeBytes

com.google.protobuf.ByteString getLanguageCodeBytes()

 *Required* The language of the supplied audio as a
 [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
 Example: "en-US".
 See [Language Support](https://cloud.google.com/speech/docs/languages)
 for a list of the currently supported language codes.
 

string language_code = 1;

getMaxAlternatives

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;

getFilterProfanity

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;

getSpeechContextsList

List<SpeechContext> getSpeechContextsList()

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

repeated .google.cloud.videointelligence.v1p3beta1.SpeechContext speech_contexts = 4;

getSpeechContexts

SpeechContext getSpeechContexts(int index)

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

repeated .google.cloud.videointelligence.v1p3beta1.SpeechContext speech_contexts = 4;

getSpeechContextsCount

int getSpeechContextsCount()

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

repeated .google.cloud.videointelligence.v1p3beta1.SpeechContext speech_contexts = 4;

getSpeechContextsOrBuilderList

List<? extends SpeechContextOrBuilder> getSpeechContextsOrBuilderList()

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

repeated .google.cloud.videointelligence.v1p3beta1.SpeechContext speech_contexts = 4;

getSpeechContextsOrBuilder

SpeechContextOrBuilder getSpeechContextsOrBuilder(int index)

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

repeated .google.cloud.videointelligence.v1p3beta1.SpeechContext speech_contexts = 4;

getEnableAutomaticPunctuation

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;

getAudioTracksList

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;

getAudioTracksCount

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;

getAudioTracks

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;

getEnableSpeakerDiarization

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 responses.
 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;

getDiarizationSpeakerCount

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;

getEnableWordConfidence

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;