generated/google/apis/speech_v1p1beta1/classes.rb in google-api-client-0.31.0 vs generated/google/apis/speech_v1p1beta1/classes.rb in google-api-client-0.32.0
- old
+ new
@@ -117,11 +117,11 @@
# returned by the `GetOperation` call of the `google::longrunning::Operations`
# service.
class LongRunningRecognizeResponse
include Google::Apis::Core::Hashable
- # Output only. Sequential list of transcription results corresponding to
+ # Sequential list of transcription results corresponding to
# sequential portions of audio.
# Corresponds to the JSON property `results`
# @return [Array<Google::Apis::SpeechV1p1beta1::SpeechRecognitionResult>]
attr_accessor :results
@@ -239,11 +239,11 @@
# Provides information to the recognizer that specifies how to process the
# request.
class RecognitionConfig
include Google::Apis::Core::Hashable
- # *Optional* A list of up to 3 additional
+ # 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
@@ -255,11 +255,11 @@
# transcription).
# Corresponds to the JSON property `alternativeLanguageCodes`
# @return [Array<String>]
attr_accessor :alternative_language_codes
- # *Optional* The number of channels in the input audio data.
+ # The number of channels in the input audio data.
# ONLY set this for MULTI-CHANNEL recognition.
# Valid values for LINEAR16 and FLAC are `1`-`8`.
# Valid values for OGG_OPUS are '1'-'254'.
# Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
# If `0` or omitted, defaults to one channel (mono).
@@ -268,24 +268,23 @@
# `enable_separate_recognition_per_channel` to 'true'.
# Corresponds to the JSON property `audioChannelCount`
# @return [Fixnum]
attr_accessor :audio_channel_count
- # *Optional* Config to enable speaker diarization.
+ # Config to enable speaker diarization.
# Corresponds to the JSON property `diarizationConfig`
# @return [Google::Apis::SpeechV1p1beta1::SpeakerDiarizationConfig]
attr_accessor :diarization_config
- # *Optional*
# 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.
# Corresponds to the JSON property `diarizationSpeakerCount`
# @return [Fixnum]
attr_accessor :diarization_speaker_count
- # *Optional* If 'true', adds punctuation to recognition result hypotheses.
+ # 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
@@ -304,28 +303,28 @@
# Corresponds to the JSON property `enableSeparateRecognitionPerChannel`
# @return [Boolean]
attr_accessor :enable_separate_recognition_per_channel
alias_method :enable_separate_recognition_per_channel?, :enable_separate_recognition_per_channel
- # *Optional* If 'true', enables speaker detection for each recognized word in
+ # 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.
# Corresponds to the JSON property `enableSpeakerDiarization`
# @return [Boolean]
attr_accessor :enable_speaker_diarization
alias_method :enable_speaker_diarization?, :enable_speaker_diarization
- # *Optional* If `true`, the top result includes a list of words and the
+ # 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`.
# Corresponds to the JSON property `enableWordConfidence`
# @return [Boolean]
attr_accessor :enable_word_confidence
alias_method :enable_word_confidence?, :enable_word_confidence
- # *Optional* If `true`, the top result includes a list of words and
+ # 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`.
# Corresponds to the JSON property `enableWordTimeOffsets`
# @return [Boolean]
@@ -337,21 +336,21 @@
# for all other audio formats. For details, see AudioEncoding.
# Corresponds to the JSON property `encoding`
# @return [String]
attr_accessor :encoding
- # *Required* The language of the supplied audio as a
+ # 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.
# Corresponds to the JSON property `languageCode`
# @return [String]
attr_accessor :language_code
- # *Optional* Maximum number of recognition hypotheses to be returned.
+ # 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.
@@ -362,11 +361,11 @@
# Description of audio data to be recognized.
# Corresponds to the JSON property `metadata`
# @return [Google::Apis::SpeechV1p1beta1::RecognitionMetadata]
attr_accessor :metadata
- # *Optional* Which model to select for the given request. Select the 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.
# <table>
# <tr>
@@ -398,11 +397,11 @@
# </table>
# Corresponds to the JSON property `model`
# @return [String]
attr_accessor :model
- # *Optional* If set to `true`, the server will attempt to filter out
+ # 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.
# Corresponds to the JSON property `profanityFilter`
# @return [Boolean]
@@ -418,20 +417,20 @@
# required for all other audio formats. For details, see AudioEncoding.
# Corresponds to the JSON property `sampleRateHertz`
# @return [Fixnum]
attr_accessor :sample_rate_hertz
- # *Optional* array of SpeechContext.
+ # 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/context-strength).
# Corresponds to the JSON property `speechContexts`
# @return [Array<Google::Apis::SpeechV1p1beta1::SpeechContext>]
attr_accessor :speech_contexts
- # *Optional* Set to true to use an enhanced model for speech recognition.
+ # 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
@@ -561,11 +560,11 @@
# request.
# Corresponds to the JSON property `config`
# @return [Google::Apis::SpeechV1p1beta1::RecognitionConfig]
attr_accessor :config
- # *Optional* The name of the model to use for recognition.
+ # Use `model` field in RecognitionConfig instead.
# Corresponds to the JSON property `name`
# @return [String]
attr_accessor :name
def initialize(**args)
@@ -584,11 +583,11 @@
# contains the result as zero or more sequential `SpeechRecognitionResult`
# messages.
class RecognizeResponse
include Google::Apis::Core::Hashable
- # Output only. Sequential list of transcription results corresponding to
+ # Sequential list of transcription results corresponding to
# sequential portions of audio.
# Corresponds to the JSON property `results`
# @return [Array<Google::Apis::SpeechV1p1beta1::SpeechRecognitionResult>]
attr_accessor :results
@@ -600,31 +599,29 @@
def update!(**args)
@results = args[:results] if args.key?(:results)
end
end
- # *Optional* Config to enable speaker diarization.
+ # Config to enable speaker diarization.
class SpeakerDiarizationConfig
include Google::Apis::Core::Hashable
- # *Optional* If 'true', enables speaker detection for each recognized word in
+ # 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.
# Corresponds to the JSON property `enableSpeakerDiarization`
# @return [Boolean]
attr_accessor :enable_speaker_diarization
alias_method :enable_speaker_diarization?, :enable_speaker_diarization
- # *Optional*
# 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.
# Corresponds to the JSON property `maxSpeakerCount`
# @return [Fixnum]
attr_accessor :max_speaker_count
- # *Optional*
# 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.
# Corresponds to the JSON property `minSpeakerCount`
# @return [Fixnum]
@@ -657,11 +654,11 @@
# finding the optimal value for your use case.
# Corresponds to the JSON property `boost`
# @return [Float]
attr_accessor :boost
- # *Optional* A list of strings containing words and phrases "hints" so that
+ # A list of strings containing words and phrases "hints" so that
# the speech recognition is more likely to recognize them. This can be used
# to improve the accuracy for specific words and phrases, for example, if
# specific commands are typically spoken by the user. This can also be used
# to add additional words to the vocabulary of the recognizer. See
# [usage limits](https://cloud.google.com/speech-to-text/quotas#content).
@@ -687,27 +684,27 @@
# Alternative hypotheses (a.k.a. n-best list).
class SpeechRecognitionAlternative
include Google::Apis::Core::Hashable
- # Output only. The confidence estimate between 0.0 and 1.0. A higher number
+ # 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.
# Corresponds to the JSON property `confidence`
# @return [Float]
attr_accessor :confidence
- # Output only. Transcript text representing the words that the user spoke.
+ # Transcript text representing the words that the user spoke.
# Corresponds to the JSON property `transcript`
# @return [String]
attr_accessor :transcript
- # Output only. A list of word-specific information for each recognized word.
+ # 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.
# Corresponds to the JSON property `words`
# @return [Array<Google::Apis::SpeechV1p1beta1::WordInfo>]
attr_accessor :words
@@ -726,11 +723,11 @@
# A speech recognition result corresponding to a portion of the audio.
class SpeechRecognitionResult
include Google::Apis::Core::Hashable
- # Output only. May contain one or more recognition hypotheses (up to the
+ # 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.
# Corresponds to the JSON property `alternatives`
# @return [Array<Google::Apis::SpeechV1p1beta1::SpeechRecognitionAlternative>]
@@ -741,14 +738,13 @@
# For audio_channel_count = N, its output values can range from '1' to 'N'.
# Corresponds to the JSON property `channelTag`
# @return [Fixnum]
attr_accessor :channel_tag
- # 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.
+ # 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.
# Corresponds to the JSON property `languageCode`
# @return [String]
attr_accessor :language_code
def initialize(**args)
@@ -804,50 +800,50 @@
# Word-specific information for recognized words.
class WordInfo
include Google::Apis::Core::Hashable
- # Output only. The confidence estimate between 0.0 and 1.0. A higher number
+ # 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.
# Corresponds to the JSON property `confidence`
# @return [Float]
attr_accessor :confidence
- # Output only. Time offset relative to the beginning of the audio,
+ # 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.
# Corresponds to the JSON property `endTime`
# @return [String]
attr_accessor :end_time
- # Output only. A distinct integer value is assigned for every speaker within
+ # 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.
# Corresponds to the JSON property `speakerTag`
# @return [Fixnum]
attr_accessor :speaker_tag
- # Output only. Time offset relative to the beginning of the audio,
+ # 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.
# Corresponds to the JSON property `startTime`
# @return [String]
attr_accessor :start_time
- # Output only. The word corresponding to this set of information.
+ # The word corresponding to this set of information.
# Corresponds to the JSON property `word`
# @return [String]
attr_accessor :word
def initialize(**args)