SrSSKJr SSKJr SSKJr SSKJr Sr "SS\R5r "S S \R5r "S S \R5r "S S\R5r"SS\R5r"SS\R5r"SS\R5r"SS\R5r"SS\R5r"SS\R5r"SS\R5r"SS\R5r"SS \R5r"S!S"\R5r"S#S$\R5r"S%S&\R5r"S'S(\R5r"S)S*\R5r"S+S,\R5r"S-S.\R5r"S/S0\R5r"S1S2\R5r "S3S4\R5r!"S5S6\R5r""S7S8\R5r#"S9S:\R5r$"S;S<\R5r%"S=S>\R5r&"S?S@\R5r'"SASB\R5r("SCSD\R5r)"SESF\R5r*"SGSH\R5r+"SISJ\R5r,"SKSL\R5r-"SMSN\R5r."SOSP\R5r/"SQSR\R5r0"SSST\R5r1"SUSV\R5r2"SWSX\R5r3"SYSZ\R5r4"S[S\\R5r5"S]S^\R5r6\Rn"\2S_S`5 \Rp"\2RrSaSb5 \Rp"\2RrScSd5 ge)fz|Generated message classes for speech version v1p1beta1. Converts audio to text by applying powerful neural network models. )absolute_import)messages)encoding) extra_typesspeechc:\rSrSrSr\R "SSS9rSrg) ABNFGrammarzA ABNFGrammar object. Fields: abnfStrings: All declarations and rules of an ABNF grammar broken up into multiple strings that will end up concatenated. TrepeatedN) __name__ __module__ __qualname____firstlineno____doc__ _messages StringField abnfStrings__static_attributes__rWlib/googlecloudsdk/generated_clients/apis/speech/v1p1beta1/speech_v1p1beta1_messages.pyr r s%%a$7+rr c<\rSrSrSr\R "S5rSrg) ClassItemz@An item of the class. Fields: value: The class item's value. r rN) rrrrrrrvaluerrrrrrs    "%rrcb\rSrSrSr\R "SS5r\R"S5r Sr g)CreateCustomClassRequest&aMessage sent by the client for the `CreateCustomClass` method. Fields: customClass: Required. The custom class to create. customClassId: Required. The ID to use for the custom class, which will become the final component of the custom class' resource name. This value should restrict to letters, numbers, and hyphens, with the first character a letter, the last a letter or a number, and be 4-63 characters. CustomClassr rN) rrrrrr MessageField customClassr customClassIdrrrrrr&s+ &&}a8+''*-rrcb\rSrSrSr\R "SS5r\R"S5r Sr g)CreatePhraseSetRequest6aMessage sent by the client for the `CreatePhraseSet` method. Fields: phraseSet: Required. The phrase set to create. phraseSetId: Required. The ID to use for the phrase set, which will become the final component of the phrase set's resource name. This value should restrict to letters, numbers, and hyphens, with the first character a letter, the last a letter or a number, and be 4-63 characters. PhraseSetr r"rN) rrrrrrr# phraseSetr phraseSetIdrrrrr'r'6s+$$[!4)%%a(+rr'cn\rSrSrSr"SS\R 5r\R"S5"SS\R55r \R"SS5r \R"S 5r\R"S 5r\R"S 5r\R"S 5r\R"S 5r\R"SSSS9r\R"S5r\R"S5r\R"S5r\R0"S5r\R4"SS5r\R"S5rSrg)r!Ea A set of words or phrases that represents a common concept likely to appear in your audio, for example a list of passenger ship names. CustomClass items can be substituted into placeholders that you set in PhraseSet phrases. Enums: StateValueValuesEnum: Output only. The CustomClass lifecycle state. This field is not used. Messages: AnnotationsValue: Output only. Allows users to store small amounts of arbitrary data. Both the key and the value must be 63 characters or less each. At most 100 annotations. This field is not used. Fields: annotations: Output only. Allows users to store small amounts of arbitrary data. Both the key and the value must be 63 characters or less each. At most 100 annotations. This field is not used. customClassId: If this custom class is a resource, the custom_class_id is the resource id of the CustomClass. Case sensitive. deleteTime: Output only. The time at which this resource was requested for deletion. This field is not used. displayName: Output only. User-settable, human-readable name for the CustomClass. Must be 63 characters or less. This field is not used. etag: Output only. This checksum is computed by the server based on the value of other fields. This may be sent on update, undelete, and delete requests to ensure the client has an up-to-date value before proceeding. This field is not used. expireTime: Output only. The time at which this resource will be purged. This field is not used. items: A collection of class items. kmsKeyName: Output only. The [KMS key name](https://cloud.google.com/kms/docs/resource-hierarchy#keys) with which the content of the ClassItem is encrypted. The expected format is `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/ {crypto_key}`. kmsKeyVersionName: Output only. The [KMS key version name](https://cloud.google.com/kms/docs/resource-hierarchy#key_versions) with which content of the ClassItem is encrypted. The expected format is `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/ {crypto_key}/cryptoKeyVersions/{crypto_key_version}`. name: The resource name of the custom class. reconciling: Output only. Whether or not this CustomClass is in the process of being updated. This field is not used. state: Output only. The CustomClass lifecycle state. This field is not used. uid: Output only. System-assigned unique identifier for the CustomClass. This field is not used. c$\rSrSrSrSrSrSrSrg) CustomClass.StateValueValuesEnumx Output only. The CustomClass lifecycle state. This field is not used. Values: STATE_UNSPECIFIED: Unspecified state. This is only used/useful for distinguishing unset values. ACTIVE: The normal and active state. DELETED: This CustomClass has been deleted. rr r"rN rrrrrSTATE_UNSPECIFIEDACTIVEDELETEDrrrrStateValueValuesEnumr/x FGrr6additionalPropertiescf\rSrSrSr"SS\R 5r\R"SSSS9r Sr g ) CustomClass.AnnotationsValue_Output only. Allows users to store small amounts of arbitrary data. Both the key and the value must be 63 characters or less each. At most 100 annotations. This field is not used. Messages: AdditionalProperty: An additional property for a AnnotationsValue object. Fields: additionalProperties: Additional properties of type AnnotationsValue c`\rSrSrSr\R "S5r\R "S5rSr g)/CustomClass.AnnotationsValue.AdditionalPropertyAn additional property for a AnnotationsValue object. Fields: key: Name of the additional property. value: A string attribute. r r"rN rrrrrrrkeyrrrrrAdditionalPropertyr>)   ! !! $c##A&errCr Tr rN rrrrrrMessagerCr#r8rrrrAnnotationsValuer:2  'Y.. '%112FTXYrrGr r"rTr  rN)rrrrrrEnumr6rMapUnrecognizedFieldsrFrGr# annotationsrr% deleteTime displayNameetag expireTimeitems kmsKeyNamekmsKeyVersionNamename BooleanField reconciling EnumFieldstateuidrrrrr!r!Es%0d Y^^  !!"89Z**Z:Z4&&'91=+''*-$$Q'*%%a(+   q !$$$Q'*  a$ ?%$$Q'*++A.   r "$&&r*+   4b 9%b!#rr!c\rSrSrSrSrg)EmptyaA generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } rN)rrrrrrrrrreresrrec\rSrSrSr\R "S5r\R"S5r \R"S5r Sr g)EntryzA single replacement configuration. Fields: caseSensitive: Whether the search is case sensitive. replace: What to replace with. Max length is 100 characters. search: What to replace. Max length is 100 characters. r r"rIrN) rrrrrrr_ caseSensitiverreplacesearchrrrrrhrhs9((+-  ! !! $'   #&rrhc`\rSrSrSr\R "SSSS9r\R"S5r Sr g ) ListCustomClassesResponseaMessage returned to the client by the `ListCustomClasses` method. Fields: customClasses: The custom classes. nextPageToken: A token, which can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages. r!r Tr r"rN) rrrrrrr# customClassesr nextPageTokenrrrrrnrns-((DI-''*-rrnc\rSrSrSr\R "S5r\R"SSSS9r \R "SSS9r S r g ) ListOperationsResponseaThe response message for Operations.ListOperations. Fields: nextPageToken: The standard List next-page token. operations: A list of operations that matches the specified filter in the request. unreachable: Unordered list. Unreachable resources. Populated when the request sets `ListOperationsRequest.return_partial_success` and reads across collections e.g. when attempting to list all resources across all supported locations. r Operationr"Tr rIrN) rrrrrrrrqr# operations unreachablerrrrrsrss? ''*-%%k1tD*%%a$7+rrsc`\rSrSrSr\R "S5r\R"SSSS9r Sr g ) ListPhraseSetResponsezMessage returned to the client by the `ListPhraseSet` method. Fields: nextPageToken: A token, which can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages. phraseSets: The phrase set. r r)r"Tr rN) rrrrrrrrqr# phraseSetsrrrrryrys-''*-%%k1tD*rryc\rSrSrSr\R "S5r\R"SS5r \R"S\RRS9r \R "S5r\R "S 5rS rg ) LongRunningRecognizeMetadataaDescribes the progress of a long-running `LongRunningRecognize` call. It is included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service. Fields: lastUpdateTime: Time of the most recent processing update. outputConfig: Output only. A copy of the TranscriptOutputConfig if it was set in the request. progressPercent: Approximate percentage of audio processed thus far. Guaranteed to be 100 when the audio is fully processed and the results are available. startTime: Time when the request was received. uri: Output only. The URI of the audio file being transcribed. Empty if the audio was sent as byte content. r TranscriptOutputConfigr"rIvariantrJrKrN)rrrrrrrlastUpdateTimer# outputConfig IntegerFieldVariantINT32progressPercent startTimeurirrrrr}r}sj ((+.''(@!D,**1i6G6G6M6MN/##A&)a #rr}c\rSrSrSr\R "SS5r\R "SS5r\R "SS5r S r g ) LongRunningRecognizeRequesti aTThe top-level message sent by the client for the `LongRunningRecognize` method. Fields: audio: Required. The audio data to be recognized. config: Required. Provides information to the recognizer that specifies how to process the request. outputConfig: Optional. Specifies an optional destination for the recognition results. RecognitionAudior RecognitionConfigr"rrIrN) rrrrrrr#audioconfigrrrrrrr sB   !3Q 7%  ! !"5q 9&''(@!D,rrc\rSrSrSr\R "SS5r\R "SS5r\R"S5r \R "SS S S 9r \R "S S 5r \R"S5rSrg)LongRunningRecognizeResponseiajThe only message returned to the client by the `LongRunningRecognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages. It is included in the `result.response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service. Fields: outputConfig: Original output config if present in the request. outputError: If the transcript output fails this field contains the relevant error. requestId: The ID associated with the request. This is a unique ID specific only to the given request. results: Sequential list of transcription results corresponding to sequential portions of audio. speechAdaptationInfo: Provides information on speech adaptation behavior in response totalBilledTime: When available, billed audio seconds for the corresponding request. rr Statusr"rISpeechRecognitionResultrJTr SpeechAdaptationInforKrLrN)rrrrrrr#r outputErrorr requestIdresultsspeechAdaptationInfortotalBilledTimerrrrrrsw(''(@!D,&&x3+$$Q')  " "# 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. enableSpeakerDiarization: If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_label provided in the WordInfo. Note: Use diarization_config instead. enableSpokenEmojis: 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. enableSpokenPunctuation: 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. enableWordConfidence: 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`. enableWordTimeOffsets: 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`. encoding: 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. languageCode: 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-to-text/docs/languages) for a list of the currently supported language codes. maxAlternatives: 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. metadata: Metadata regarding this request. model: 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. *Model* *Description* latest_long Best for long form content like media or conversation. latest_short Best for short form content like commands or single shot directed speech. command_and_search Best for short queries such as voice commands or voice search. phone_call Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate). video 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. default 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. medical_conversation Best for audio that originated from a conversation between a medical provider and patient. medical_dictation Best for audio that originated from dictation notes by a medical provider. profanityFilter: 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. sampleRateHertz: 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. speechContexts: Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see [speech adaptation](https://cloud.google.com/speech-to-text/docs/adaptation). transcriptNormalization: Optional. 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. useEnhanced: 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. cD\rSrSrSrSrSrSrSrSr Sr S r S r S r S rS rSrg))RecognitionConfig.EncodingValueValuesEnumia 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. Values: ENCODING_UNSPECIFIED: Not specified. LINEAR16: Uncompressed 16-bit signed little-endian samples (Linear PCM). FLAC: `FLAC` (Free Lossless Audio Codec) is the recommended encoding because it is lossless--therefore recognition is not compromised--and requires only about half the bandwidth of `LINEAR16`. `FLAC` stream encoding supports 16-bit and 24-bit samples, however, not all fields in `STREAMINFO` are supported. MULAW: 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law. AMR: Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000. AMR_WB: Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000. OGG_OPUS: Opus encoded audio frames in Ogg container ([OggOpus](https://wiki.xiph.org/OggOpus)). `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000. SPEEX_WITH_HEADER_BYTE: Although the use of lossy encodings is not recommended, if a very low bitrate encoding is required, `OGG_OPUS` is highly preferred over Speex encoding. The [Speex](https://speex.org/) encoding supported by Cloud Speech API has a header byte in each block, as in MIME type `audio/x-speex-with-header-byte`. It is a variant of the RTP Speex encoding defined in [RFC 5574](https://tools.ietf.org/html/rfc5574). The stream is a sequence of blocks, one block per RTP packet. Each block starts with a byte containing the length of the block, in bytes, followed by one or more frames of Speex data, padded to an integral number of bytes (octets) as specified in RFC 5574. In other words, each RTP header is replaced with a single byte containing the block length. Only Speex wideband is supported. `sample_rate_hertz` must be 16000. MP3: MP3 audio. MP3 encoding is a Beta feature and only available in v1p1beta1. Support all standard MP3 bitrates (which range from 32-320 kbps). When using this encoding, `sample_rate_hertz` has to match the sample rate of the file being used. WEBM_OPUS: Opus encoded audio frames in WebM container ([WebM](https://www.webmproject.org/docs/container/)). `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000. ALAW: 8-bit samples that compand 13-bit audio samples using G.711 PCMU/a-law. rr r"rIrJrKrLrMrNrOrPrN)rrrrrENCODING_UNSPECIFIEDLINEAR16FLACMULAWAMRAMR_WBOGG_OPUSSPEEX_WITH_HEADER_BYTEMP3 WEBM_OPUSALAWrrrrEncodingValueValuesEnumrsC,ZH D E C FH CI DrrSpeechAdaptationr r"Tr rIrSpeakerDiarizationConfigrJrKrLrMrNrOrPrQrRrSRecognitionMetadatar  SpeechContextTranscriptNormalizationrN)&rrrrrrrTrr# adaptationralternativeLanguageCodesrrraudioChannelCountdiarizationConfigdiarizationSpeakerCountr_enableAutomaticPunctuation#enableSeparateRecognitionPerChannelenableSpeakerDiarizationenableSpokenEmojisenableSpokenPunctuationenableWordConfidenceenableWordTimeOffsetsrar languageCodemaxAlternativesrmodelprofanityFiltersampleRateHertzspeechContextstranscriptNormalization useEnhancedrrrrrrTsGR8 8t%%&8!<*&221tD,,Q 8I8I8O8OP,,-GK%221i>O>O>U>UV(55a8(1(>(>q(A%&33A6 --a0%2226"//3#004  !:B ?(&&r*,**2y7H7H7N7NO/  # #$92 >(    #%**2./**2y7H7H7N7NO/))/2M.%223LbQ&&r*+rrc2\rSrSrSr"SS\R 5r"SS\R 5r"SS\R 5r "S S \R 5r \R"S 5r \R"S \RRS 9r\R""SS5r\R""SS5r\R"S5r\R""SS5r\R"S5r\R"S5r\R""S S5rSrg)ri0aDescription of audio data to be recognized. Enums: InteractionTypeValueValuesEnum: The use case most closely describing the audio content to be recognized. MicrophoneDistanceValueValuesEnum: The audio type that most closely describes the audio being recognized. OriginalMediaTypeValueValuesEnum: The original media the speech was recorded on. RecordingDeviceTypeValueValuesEnum: The type of device the speech was recorded with. Fields: audioTopic: Description of the content. Eg. "Recordings of federal supreme court hearings from 2012". industryNaicsCodeOfAudio: The industry vertical to which this speech recognition request most closely applies. This is most indicative of the topics contained in the audio. Use the 6-digit NAICS code to identify the industry vertical - see https://www.naics.com/search/. interactionType: The use case most closely describing the audio content to be recognized. microphoneDistance: The audio type that most closely describes the audio being recognized. obfuscatedId: Obfuscated (privacy-protected) ID of the user, to identify number of unique users using the service. originalMediaType: The original media the speech was recorded on. originalMimeType: Mime type of the original audio file. For example `audio/m4a`, `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`. A list of possible audio mime types is maintained at http://www.iana.org/assignments/media-types/media-types.xhtml#audio recordingDeviceName: The device used to make the recording. Examples 'Nexus 5X' or 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or 'Cardioid Microphone'. recordingDeviceType: The type of device the speech was recorded with. c<\rSrSrSrSrSrSrSrSr Sr S r S r S r S rg )2RecognitionMetadata.InteractionTypeValueValuesEnumiUaMThe use case most closely describing the audio content to be recognized. Values: INTERACTION_TYPE_UNSPECIFIED: Use case is either unknown or is something other than one of the other values below. DISCUSSION: Multiple people in a conversation or discussion. For example in a meeting with two or more people actively participating. Typically all the primary people speaking would be in the same room (if not, see PHONE_CALL) PRESENTATION: One or more persons lecturing or presenting to others, mostly uninterrupted. PHONE_CALL: A phone-call or video-conference in which two or more people, who are not in the same room, are actively participating. VOICEMAIL: A recorded message intended for another person to listen to. PROFESSIONALLY_PRODUCED: Professionally produced audio (eg. TV Show, Podcast). VOICE_SEARCH: Transcribe spoken questions and queries into text. VOICE_COMMAND: Transcribe voice commands, such as for controlling a device. DICTATION: Transcribe speech to text to create a written document, such as a text-message, email or report. rr r"rIrJrKrLrMrNrN)rrrrrINTERACTION_TYPE_UNSPECIFIED DISCUSSION PRESENTATION PHONE_CALL VOICEMAILPROFESSIONALLY_PRODUCED VOICE_SEARCH VOICE_COMMAND DICTATIONrrrrInteractionTypeValueValuesEnumrUs8.$% JLJILMIrrc(\rSrSrSrSrSrSrSrSr g) 5RecognitionMetadata.MicrophoneDistanceValueValuesEnumiwaThe audio type that most closely describes the audio being recognized. Values: MICROPHONE_DISTANCE_UNSPECIFIED: Audio type is not known. NEARFIELD: The audio was captured from a closely placed microphone. Eg. phone, dictaphone, or handheld microphone. Generally if there speaker is within 1 meter of the microphone. MIDFIELD: The speaker if within 3 meters of the microphone. FARFIELD: The speaker is more than 3 meters away from the microphone. rr r"rIrN) rrrrrMICROPHONE_DISTANCE_UNSPECIFIED NEARFIELDMIDFIELDFARFIELDrrrr!MicrophoneDistanceValueValuesEnumrws '(#IHHrrc$\rSrSrSrSrSrSrSrg)4RecognitionMetadata.OriginalMediaTypeValueValuesEnumizThe original media the speech was recorded on. Values: ORIGINAL_MEDIA_TYPE_UNSPECIFIED: Unknown original media type. AUDIO: The speech data is an audio recording. VIDEO: The speech data originally recorded on a video. rr r"rN) rrrrrORIGINAL_MEDIA_TYPE_UNSPECIFIEDAUDIOVIDEOrrrr OriginalMediaTypeValueValuesEnumrs'(# E Errc4\rSrSrSrSrSrSrSrSr Sr S r S r g ) 6RecognitionMetadata.RecordingDeviceTypeValueValuesEnumiaThe type of device the speech was recorded with. Values: RECORDING_DEVICE_TYPE_UNSPECIFIED: The recording device is unknown. SMARTPHONE: Speech was recorded on a smartphone. PC: Speech was recorded using a personal computer or tablet. PHONE_LINE: Speech was recorded over a phone line. VEHICLE: Speech was recorded in a vehicle. OTHER_OUTDOOR_DEVICE: Speech was recorded outdoors. OTHER_INDOOR_DEVICE: Speech was recorded indoors. rr r"rIrJrKrLrN) rrrrr!RECORDING_DEVICE_TYPE_UNSPECIFIED SMARTPHONEPC PHONE_LINEVEHICLEOTHER_OUTDOOR_DEVICEOTHER_INDOOR_DEVICErrrr"RecordingDeviceTypeValueValuesEnumrs/ )*%J BJGrrr r"rrIrJrKrLrMrNrOrN)rrrrrrrTrrrrr audioTopicrrUINT32industryNaicsCodeOfAudiorainteractionTypemicrophoneDistance obfuscatedIdoriginalMediaTypeoriginalMimeTyperecordingDeviceNamerecordingDeviceTyperrrrrr0s"H y~~ D)..  9>>($$Q'*&33Ay?P?P?W?WX''(H!L/ **+NPQR''*,))*LaP**1-!--a0!++,PRSTrrcd\rSrSrSr\R "SS5r\R "SS5rSr g) RecognizeRequestizThe top-level message sent by the client for the `Recognize` method. Fields: audio: Required. The audio data to be recognized. config: Required. Provides information to the recognizer that specifies how to process the request. rr rr"rN) rrrrrrr#rrrrrrrrs/  !3Q 7%  ! !"5q 9&rrc\rSrSrSr\R "S5r\R"SSSS9r \R"SS 5r \R"S 5r \R"S 5rS rg )RecognizeResponseiaThe only message returned to the client by the `Recognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages. Fields: requestId: The ID associated with the request. This is a unique ID specific only to the given request. results: Sequential list of transcription results corresponding to sequential portions of audio. speechAdaptationInfo: Provides information on adaptation behavior in response totalBilledTime: When available, billed audio seconds for the corresponding request. usingLegacyModels: Whether request used legacy asr models (was not automatically migrated to use conformer models). r rr"Tr rrIrJrKrN)rrrrrrrrr#rrrrr_usingLegacyModelsrrrrrrsc"$$Q')  " "#rrJc:\rSrSrSr\R "SSS9rSrg)+SpeechProjectsLocationsPhraseSetsGetRequestia!A SpeechProjectsLocationsPhraseSetsGetRequest object. Fields: name: Required. The name of the phrase set to retrieve. Format: `projects/{project}/locations/{location}/phraseSets/{phrase_set}` Speech-to-Text supports three locations: `global`, `us` (US North America), and `eu` (Europe). If you are calling the `speech.googleapis.com` endpoint, use the `global` location. To specify a region, use a [regional endpoint](https://cloud.google.com/speech-to- text/docs/endpoints) with matching `us` or `eu` location value. r Tr,rNr.rrrrLrLr;rrLc\rSrSrSr\R "S\RRS9r \R"S5r \R"SSS9r S r g ) ,SpeechProjectsLocationsPhraseSetsListRequestiaA SpeechProjectsLocationsPhraseSetsListRequest object. Fields: pageSize: The maximum number of phrase sets to return. The service may return fewer than this value. If unspecified, at most 50 phrase sets will be returned. The maximum value is 1000; values above 1000 will be coerced to 1000. pageToken: A page token, received from a previous `ListPhraseSet` call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to `ListPhraseSet` must match the call that provided the page token. parent: Required. The parent, which owns this collection of phrase set. Format: `projects/{project}/locations/{location}` Speech-to-Text supports three locations: `global`, `us` (US North America), and `eu` (Europe). If you are calling the `speech.googleapis.com` endpoint, use the `global` location. To specify a region, use a [regional endpoint](https://cloud.google.com/speech-to-text/docs/endpoints) with matching `us` or `eu` location value. r rr"rITr,rNrArrrrNrNrBrrNc\rSrSrSr\R "SSS9r\R"SS5r \R "S5r S r g ) -SpeechProjectsLocationsPhraseSetsPatchRequestizA SpeechProjectsLocationsPhraseSetsPatchRequest object. Fields: name: The resource name of the phrase set. phraseSet: A PhraseSet resource to be passed as the request body. updateMask: The list of fields to be updated. r Tr,r)r"rIrN) rrrrrrrr^r#r*rErrrrrPrPs=   q4 0$$$[!4)$$Q'*rrPc\rSrSrSr\R "S\RRS9r \R"S5r \R"SSSS 9r S rg ) SpeechRecognitionAlternativeiaAlternative hypotheses (a.k.a. n-best list). Fields: confidence: The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative of a non- streaming result or, of a streaming result where `is_final=true`. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set. transcript: Transcript text representing the words that the user spoke. In languages that use spaces to separate words, the transcript might have a leading space if it isn't the first result. You can concatenate each result to obtain the full transcript without using a separator. words: A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is true, you will see all the words from the beginning of the audio. r rr"WordInforITr rN)rrrrrrrrr confidencer transcriptr#wordsrrrrrRrRsK&##Ay/@/@/F/FG*$$Q'*  Q >%rrRc\rSrSrSr\R "SSSS9r\R"S\RRS9r \R"S 5r \R"S 5rS rg ) riaA speech recognition result corresponding to a portion of the audio. Fields: alternatives: May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer. channelTag: For multi-channel audio, this is the channel number corresponding to the recognized result for the audio from that channel. For audio_channel_count = N, its output values can range from '1' to 'N'. languageCode: Output only. The [BCP-47](https://www.rfc- editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio. resultEndTime: Time offset of the end of this result relative to the beginning of the audio. rRr Tr r"rrIrJrN)rrrrrrr# alternativesrrr channelTagrr resultEndTimerrrrrrs]&''(FTXY,%%a1B1B1H1HI*&&q),''*-rrc\rSrSrSr"SS\R 5r"SS\R 5r\R"SS5r \R"S5r \R"SS S S 9r \R"S 5r\R"S 5r\R"S5r\R"S5r\R$"SSS 9r\R"S5r\R"S5r\R"S5r\R"S5rSrg)StandardQueryParametersi6aQuery parameters accepted by all methods. Enums: FXgafvValueValuesEnum: V1 error format. AltValueValuesEnum: Data format for response. Fields: f__xgafv: V1 error format. access_token: OAuth access token. alt: Data format for response. callback: JSONP fields: Selector specifying which fields to include in a partial response. key: API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token. oauth_token: OAuth 2.0 token for the current user. prettyPrint: Returns response with indentations and line breaks. quotaUser: Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters. trace: A tracing token of the form "token:" to include in api requests. uploadType: Legacy upload protocol for media (e.g. "media", "multipart"). upload_protocol: Upload protocol for media (e.g. "raw", "multipart"). c$\rSrSrSrSrSrSrSrg)*StandardQueryParameters.AltValueValuesEnumiQzData format for response. Values: json: Responses with Content-Type of application/json media: Media download with context-dependent Content-Type proto: Responses with Content-Type of application/x-protobuf rr r"rN) rrrrrjsonmediaprotorrrrAltValueValuesEnumr^Qs D E Errbc \rSrSrSrSrSrSrg)-StandardQueryParameters.FXgafvValueValuesEnumi]zFV1 error format. Values: _1: v1 error format _2: v2 error format rr rN)rrrrr_1_2rrrrFXgafvValueValuesEnumrd]s B Brrgr r"rIr_)defaultrJrKrLrMrNTrOrPrQrRrN)rrrrrrrTrbrgraf__xgafvr access_tokenaltcallbackfieldsrB oauth_tokenr_ prettyPrint quotaUsertrace uploadTypeupload_protocolrrrrr\r\6s4 9>>  inn  !8! <(&&q),0!VD#  " "1 %(   #&a #%%a(+&&q$7+##A&)    #%$$R(*))"-/rr\c\rSrSrSr\R "S5"SS\R55r \R"S\RRS9r \R"SSS S 9r\R "S 5rS rg )riuaThe `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). Messages: DetailsValueListEntry: A DetailsValueListEntry object. Fields: code: The status code, which should be an enum value of google.rpc.Code. details: A list of messages that carry the error details. There is a common set of message types for APIs to use. message: A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. r8cf\rSrSrSr"SS\R 5r\R"SSSS9r Sr g ) Status.DetailsValueListEntryizA DetailsValueListEntry object. Messages: AdditionalProperty: An additional property for a DetailsValueListEntry object. Fields: additionalProperties: Properties of the object. Contains field @type with type URL. cb\rSrSrSr\R "S5r\R"SS5r Sr g)/Status.DetailsValueListEntry.AdditionalPropertyizAn additional property for a DetailsValueListEntry object. Fields: key: Name of the additional property. value: A extra_types.JsonValue attribute. r rr"rNrrrrrCrxrrrCr Tr rNrErrrDetailsValueListEntryrvs4  AY.. A%112FTXYrryr rr"Tr rIrN)rrrrrrrUrrFryrrrcoder#detailsrmessagerrrrrrus|& !!"89Zi//Z:Z2   9+<+<+B+B C$  " "#:A M'  ! !! $'rrc<\rSrSrSr\R "SSSS9rSrg) riaHTranscription normalization configuration. 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. Fields: entries: A list of replacement entries. We will perform replacement with one entry at a time. For example, the second entry in ["cat" => "dog", "mountain cat" => "mountain dog"] will never be applied because we will always process the first entry before it. At most 100 entries. rhr Tr rN) rrrrrrr#entriesrrrrrrs   " "7A ='rrc<\rSrSrSr\R "S5rSrg)rizSpecifies an optional destination for the recognition results. Fields: gcsUri: Specifies a Cloud Storage URI for the recognition results. Must be specified in the format: `gs://bucket_name/object_name`, and the bucket must already exist. r rN) rrrrrrrgcsUrirrrrrrs   #&rrc<\rSrSrSr\R "S\RRS9r \R"S5r \R"S5r \R"S\RRS9r\R"S5r\R"S 5rS rg ) rSiaWord-specific information for recognized words. Fields: confidence: The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative of a non- streaming result or, of a streaming result where `is_final=true`. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set. endTime: Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary. speakerLabel: Output only. A label value assigned for every unique speaker within the audio. This field specifies which speaker was detected to have spoken this word. For some models, like medical_conversation this can be actual speaker role, for example "patient" or "provider", but generally this would be a number identifying a speaker. This field is only set if enable_speaker_diarization = 'true' and only for the top alternative. speakerTag: Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from '1' to diarization_speaker_count. speaker_tag is set if enable_speaker_diarization = 'true' and only for the top alternative. Note: Use speaker_label instead. startTime: Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary. word: The word corresponding to this set of information. r rr"rIrJrKrLrN)rrrrrrrrrrTrendTime speakerLabelrrr"rwordrrrrrSrSs D##Ay/@/@/F/FG*  ! !! $'&&q),%%a1B1B1H1HI*##A&)   q !$rrSriz$.xgafvre1rf2N):r __future__rapitools.base.protorpcliterrapitools.base.pyrrpackagerFr rrr'r!rerhrnrsryr}rrrurr)rrrrrrrrrr+r0r6r:r=r@rDrGrJrLrNrPrRrr\rrrrSAddCustomJsonFieldMappingAddCustomJsonEnumMappingrgrrrrs '<%( 8)##8# !!# +y00 + )Y.. )g")##g"TI   $I   $ + 1 1 +8Y..8$ EI-- E!9#4#4!0E)"3"3E"-9#4#4-:i8 !!i8X&#Y  &#Rm" !!m"`!y((!.Y+ ))Y+xU)++UD :y(( :0 ))02Jy00J0Ey((E. ,9,, ,4I%%4>1!2!213)"3"3303 8I8I3& 1 8I8I 1 1Y5F5F13i6G6G34 (y7H7H (3Y5F5F3&1Y5F5F1 1)2C2C 1 393D3D34 (I4E4E (?9#4#4?2+i//+4<.i//<.~0%Y  0%f >i// > $Y.. $("y  ("V ""Z4!!114>!!114>r