docs: update docs (#916)
* fix: re-run script
* test: fix noxfile
diff --git a/docs/dyn/speech_v1p1beta1.speech.html b/docs/dyn/speech_v1p1beta1.speech.html
index 38e82f5..fee49eb 100644
--- a/docs/dyn/speech_v1p1beta1.speech.html
+++ b/docs/dyn/speech_v1p1beta1.speech.html
@@ -99,7 +99,71 @@
"config": { # Provides information to the recognizer that specifies how to process the # Required. Provides information to the recognizer that specifies how to
# process the request.
# request.
+ "enableWordTimeOffsets": True or False, # 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`.
+ "alternativeLanguageCodes": [ # A list of up to 3 additional
+ # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
+ # listing possible alternative languages of the supplied audio.
+ # See [Language
+ # Support](https://cloud.google.com/speech-to-text/docs/languages) 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).
+ "A String",
+ ],
+ "diarizationConfig": { # Config to enable speaker diarization. # 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.
+ "enableSpeakerDiarization": True or False, # 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.
+ "minSpeakerCount": 42, # Minimum number of speakers in the conversation. This range gives you more
+ # flexibility by allowing the system to automatically determine the correct
+ # number of speakers. If not set, the default value is 2.
+ "maxSpeakerCount": 42, # Maximum number of speakers in the conversation. This range gives you more
+ # flexibility by allowing the system to automatically determine the correct
+ # number of speakers. If not set, the default value is 6.
+ "speakerTag": 42, # Output only. Unused.
+ },
+ "languageCode": "A String", # 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.
+ "profanityFilter": True or False, # 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.
+ "enableSpeakerDiarization": True or False, # 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.
+ "useEnhanced": True or False, # 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.
"metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
+ "microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
+ "industryNaicsCodeOfAudio": 42, # 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/.
"originalMediaType": "A String", # The original media the speech was recorded on.
"obfuscatedId": "A String", # Obfuscated (privacy-protected) ID of the user, to identify number of
# unique users using the service.
@@ -114,11 +178,6 @@
# http://www.iana.org/assignments/media-types/media-types.xhtml#audio
"audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court
# hearings from 2012".
- "industryNaicsCodeOfAudio": 42, # 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/.
- "microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
},
"sampleRateHertz": 42, # Sample rate in Hertz of the audio data sent in all
# `RecognitionAudio` messages. Valid values are: 8000-48000.
@@ -147,15 +206,6 @@
# phrase set can use any custom class.
{ # Provides "hints" to the speech recognizer to favor specific words and phrases
# in the results.
- "boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific
- # phrase will be recognized over other similar sounding phrases. The higher
- # the boost, the higher the chance of false positive recognition as well.
- # Negative boost values would correspond to anti-biasing. Anti-biasing is not
- # enabled, so negative boost will simply be ignored. Though `boost` can
- # accept a wide range of positive values, most use cases are best served with
- # values between 0 (exclusive) and 20. We recommend using a binary search
- # approach to finding the optimal value for your use case. Speech recognition
- # will skip PhraseSets with a boost value of 0.
"name": "A String", # The resource name of the phrase set.
"phrases": [ # A list of word and phrases.
{ # A phrases containing words and phrase "hints" so that
@@ -177,7 +227,6 @@
# resources and inline classes. Then use the class' id wrapped in $`{...}`
# e.g. "${my-months}". To refer to custom classes resources, use the class'
# id wrapped in `${}` (e.g. `${my-months}`).
- "value": "A String", # The phrase itself.
"boost": 3.14, # Hint Boost. Overrides the boost set at the phrase set level.
# Positive value will increase the probability that a specific phrase will
# be recognized over other similar sounding phrases. The higher the boost,
@@ -188,8 +237,18 @@
# with values between 0 and 20. We recommend using a binary search approach
# to finding the optimal value for your use case. Speech recognition
# will skip PhraseSets with a boost value of 0.
+ "value": "A String", # The phrase itself.
},
],
+ "boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific
+ # phrase will be recognized over other similar sounding phrases. The higher
+ # the boost, the higher the chance of false positive recognition as well.
+ # Negative boost values would correspond to anti-biasing. Anti-biasing is not
+ # enabled, so negative boost will simply be ignored. Though `boost` can
+ # accept a wide range of positive values, most use cases are best served with
+ # values between 0 (exclusive) and 20. We recommend using a binary search
+ # approach to finding the optimal value for your use case. Speech recognition
+ # will skip PhraseSets with a boost value of 0.
},
],
"customClasses": [ # A collection of custom classes. To specify the classes inline, leave the
@@ -199,29 +258,26 @@
{ # 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.
- "name": "A String", # The resource name of the custom class.
- "customClassId": "A String", # If this custom class is a resource, the custom_class_id is the resource id
- # of the CustomClass. Case sensitive.
"items": [ # A collection of class items.
{ # An item of the class.
"value": "A String", # The class item's value.
},
],
+ "name": "A String", # The resource name of the custom class.
+ "customClassId": "A String", # If this custom class is a resource, the custom_class_id is the resource id
+ # of the CustomClass. Case sensitive.
},
],
},
+ "diarizationSpeakerCount": 42, # 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.
"maxAlternatives": 42, # 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.
- "diarizationSpeakerCount": 42, # 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.
- "encoding": "A String", # 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.
"speechContexts": [ # Array of SpeechContext.
# A means to provide context to assist the speech recognition. For more
# information, see
@@ -253,6 +309,9 @@
# finding the optimal value for your use case.
},
],
+ "encoding": "A String", # 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.
"enableWordConfidence": True or False, # 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`.
@@ -297,65 +356,6 @@
# Note: We only recognize the first channel by default.
# To perform independent recognition on each channel set
# `enable_separate_recognition_per_channel` to 'true'.
- "enableWordTimeOffsets": True or False, # 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`.
- "alternativeLanguageCodes": [ # A list of up to 3 additional
- # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
- # listing possible alternative languages of the supplied audio.
- # See [Language
- # Support](https://cloud.google.com/speech-to-text/docs/languages) 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).
- "A String",
- ],
- "diarizationConfig": { # Config to enable speaker diarization. # 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.
- "minSpeakerCount": 42, # Minimum number of speakers in the conversation. This range gives you more
- # flexibility by allowing the system to automatically determine the correct
- # number of speakers. If not set, the default value is 2.
- "maxSpeakerCount": 42, # Maximum number of speakers in the conversation. This range gives you more
- # flexibility by allowing the system to automatically determine the correct
- # number of speakers. If not set, the default value is 6.
- "speakerTag": 42, # Output only. Unused.
- "enableSpeakerDiarization": True or False, # 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.
- },
- "languageCode": "A String", # 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.
- "profanityFilter": True or False, # 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.
- "enableSpeakerDiarization": True or False, # 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.
- "useEnhanced": True or False, # 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.
},
"audio": { # Contains audio data in the encoding specified in the `RecognitionConfig`. # Required. The audio data to be recognized.
# Either `content` or `uri` must be supplied. Supplying both or neither
@@ -384,6 +384,16 @@
{ # This resource represents a long-running operation that is the result of a
# network API call.
+ "response": { # The normal response of the operation in case of success. If the original
+ # method returns no data on success, such as `Delete`, the response is
+ # `google.protobuf.Empty`. If the original method is standard
+ # `Get`/`Create`/`Update`, the response should be the resource. For other
+ # methods, the response should have the type `XxxResponse`, where `Xxx`
+ # is the original method name. For example, if the original method name
+ # is `TakeSnapshot()`, the inferred response type is
+ # `TakeSnapshotResponse`.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
"name": "A String", # The server-assigned name, which is only unique within the same service that
# originally returns it. If you use the default HTTP mapping, the
# `name` should be a resource name ending with `operations/{unique_id}`.
@@ -414,16 +424,6 @@
"done": True or False, # If the value is `false`, it means the operation is still in progress.
# If `true`, the operation is completed, and either `error` or `response` is
# available.
- "response": { # The normal response of the operation in case of success. If the original
- # method returns no data on success, such as `Delete`, the response is
- # `google.protobuf.Empty`. If the original method is standard
- # `Get`/`Create`/`Update`, the response should be the resource. For other
- # methods, the response should have the type `XxxResponse`, where `Xxx`
- # is the original method name. For example, if the original method name
- # is `TakeSnapshot()`, the inferred response type is
- # `TakeSnapshotResponse`.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
}</pre>
</div>
@@ -440,7 +440,71 @@
"config": { # Provides information to the recognizer that specifies how to process the # Required. Provides information to the recognizer that specifies how to
# process the request.
# request.
+ "enableWordTimeOffsets": True or False, # 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`.
+ "alternativeLanguageCodes": [ # A list of up to 3 additional
+ # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
+ # listing possible alternative languages of the supplied audio.
+ # See [Language
+ # Support](https://cloud.google.com/speech-to-text/docs/languages) 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).
+ "A String",
+ ],
+ "diarizationConfig": { # Config to enable speaker diarization. # 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.
+ "enableSpeakerDiarization": True or False, # 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.
+ "minSpeakerCount": 42, # Minimum number of speakers in the conversation. This range gives you more
+ # flexibility by allowing the system to automatically determine the correct
+ # number of speakers. If not set, the default value is 2.
+ "maxSpeakerCount": 42, # Maximum number of speakers in the conversation. This range gives you more
+ # flexibility by allowing the system to automatically determine the correct
+ # number of speakers. If not set, the default value is 6.
+ "speakerTag": 42, # Output only. Unused.
+ },
+ "languageCode": "A String", # 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.
+ "profanityFilter": True or False, # 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.
+ "enableSpeakerDiarization": True or False, # 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.
+ "useEnhanced": True or False, # 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.
"metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
+ "microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
+ "industryNaicsCodeOfAudio": 42, # 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/.
"originalMediaType": "A String", # The original media the speech was recorded on.
"obfuscatedId": "A String", # Obfuscated (privacy-protected) ID of the user, to identify number of
# unique users using the service.
@@ -455,11 +519,6 @@
# http://www.iana.org/assignments/media-types/media-types.xhtml#audio
"audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court
# hearings from 2012".
- "industryNaicsCodeOfAudio": 42, # 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/.
- "microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
},
"sampleRateHertz": 42, # Sample rate in Hertz of the audio data sent in all
# `RecognitionAudio` messages. Valid values are: 8000-48000.
@@ -488,15 +547,6 @@
# phrase set can use any custom class.
{ # Provides "hints" to the speech recognizer to favor specific words and phrases
# in the results.
- "boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific
- # phrase will be recognized over other similar sounding phrases. The higher
- # the boost, the higher the chance of false positive recognition as well.
- # Negative boost values would correspond to anti-biasing. Anti-biasing is not
- # enabled, so negative boost will simply be ignored. Though `boost` can
- # accept a wide range of positive values, most use cases are best served with
- # values between 0 (exclusive) and 20. We recommend using a binary search
- # approach to finding the optimal value for your use case. Speech recognition
- # will skip PhraseSets with a boost value of 0.
"name": "A String", # The resource name of the phrase set.
"phrases": [ # A list of word and phrases.
{ # A phrases containing words and phrase "hints" so that
@@ -518,7 +568,6 @@
# resources and inline classes. Then use the class' id wrapped in $`{...}`
# e.g. "${my-months}". To refer to custom classes resources, use the class'
# id wrapped in `${}` (e.g. `${my-months}`).
- "value": "A String", # The phrase itself.
"boost": 3.14, # Hint Boost. Overrides the boost set at the phrase set level.
# Positive value will increase the probability that a specific phrase will
# be recognized over other similar sounding phrases. The higher the boost,
@@ -529,8 +578,18 @@
# with values between 0 and 20. We recommend using a binary search approach
# to finding the optimal value for your use case. Speech recognition
# will skip PhraseSets with a boost value of 0.
+ "value": "A String", # The phrase itself.
},
],
+ "boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific
+ # phrase will be recognized over other similar sounding phrases. The higher
+ # the boost, the higher the chance of false positive recognition as well.
+ # Negative boost values would correspond to anti-biasing. Anti-biasing is not
+ # enabled, so negative boost will simply be ignored. Though `boost` can
+ # accept a wide range of positive values, most use cases are best served with
+ # values between 0 (exclusive) and 20. We recommend using a binary search
+ # approach to finding the optimal value for your use case. Speech recognition
+ # will skip PhraseSets with a boost value of 0.
},
],
"customClasses": [ # A collection of custom classes. To specify the classes inline, leave the
@@ -540,29 +599,26 @@
{ # 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.
- "name": "A String", # The resource name of the custom class.
- "customClassId": "A String", # If this custom class is a resource, the custom_class_id is the resource id
- # of the CustomClass. Case sensitive.
"items": [ # A collection of class items.
{ # An item of the class.
"value": "A String", # The class item's value.
},
],
+ "name": "A String", # The resource name of the custom class.
+ "customClassId": "A String", # If this custom class is a resource, the custom_class_id is the resource id
+ # of the CustomClass. Case sensitive.
},
],
},
+ "diarizationSpeakerCount": 42, # 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.
"maxAlternatives": 42, # 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.
- "diarizationSpeakerCount": 42, # 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.
- "encoding": "A String", # 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.
"speechContexts": [ # Array of SpeechContext.
# A means to provide context to assist the speech recognition. For more
# information, see
@@ -594,6 +650,9 @@
# finding the optimal value for your use case.
},
],
+ "encoding": "A String", # 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.
"enableWordConfidence": True or False, # 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`.
@@ -638,65 +697,6 @@
# Note: We only recognize the first channel by default.
# To perform independent recognition on each channel set
# `enable_separate_recognition_per_channel` to 'true'.
- "enableWordTimeOffsets": True or False, # 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`.
- "alternativeLanguageCodes": [ # A list of up to 3 additional
- # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
- # listing possible alternative languages of the supplied audio.
- # See [Language
- # Support](https://cloud.google.com/speech-to-text/docs/languages) 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).
- "A String",
- ],
- "diarizationConfig": { # Config to enable speaker diarization. # 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.
- "minSpeakerCount": 42, # Minimum number of speakers in the conversation. This range gives you more
- # flexibility by allowing the system to automatically determine the correct
- # number of speakers. If not set, the default value is 2.
- "maxSpeakerCount": 42, # Maximum number of speakers in the conversation. This range gives you more
- # flexibility by allowing the system to automatically determine the correct
- # number of speakers. If not set, the default value is 6.
- "speakerTag": 42, # Output only. Unused.
- "enableSpeakerDiarization": True or False, # 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.
- },
- "languageCode": "A String", # 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.
- "profanityFilter": True or False, # 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.
- "enableSpeakerDiarization": True or False, # 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.
- "useEnhanced": True or False, # 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.
},
"audio": { # Contains audio data in the encoding specified in the `RecognitionConfig`. # Required. The audio data to be recognized.
# Either `content` or `uri` must be supplied. Supplying both or neither
@@ -752,11 +752,6 @@
# Note: When `enable_speaker_diarization` is true, you will see all the words
# from the beginning of the audio.
{ # Word-specific information for recognized words.
- "speakerTag": 42, # 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 in the
- # top alternative.
"endTime": "A String", # 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
@@ -777,6 +772,11 @@
# This is an experimental feature and the accuracy of the time offset can
# vary.
"word": "A String", # The word corresponding to this set of information.
+ "speakerTag": 42, # 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 in the
+ # top alternative.
},
],
},