2017-08-25 19:54:22 +00:00
|
|
|
# Copyright 2015 Google Inc.
|
|
|
|
#
|
|
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
|
|
# you may not use this file except in compliance with the License.
|
|
|
|
# You may obtain a copy of the License at
|
|
|
|
#
|
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
#
|
|
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
# See the License for the specific language governing permissions and
|
|
|
|
# limitations under the License.
|
|
|
|
|
|
|
|
require 'date'
|
|
|
|
require 'google/apis/core/base_service'
|
|
|
|
require 'google/apis/core/json_representation'
|
|
|
|
require 'google/apis/core/hashable'
|
|
|
|
require 'google/apis/errors'
|
|
|
|
|
|
|
|
module Google
|
|
|
|
module Apis
|
|
|
|
module SpeechV1
|
|
|
|
|
2018-09-12 00:36:25 +00:00
|
|
|
# The response message for Operations.ListOperations.
|
|
|
|
class ListOperationsResponse
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# The standard List next-page token.
|
|
|
|
# Corresponds to the JSON property `nextPageToken`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :next_page_token
|
|
|
|
|
|
|
|
# A list of operations that matches the specified filter in the request.
|
|
|
|
# Corresponds to the JSON property `operations`
|
|
|
|
# @return [Array<Google::Apis::SpeechV1::Operation>]
|
|
|
|
attr_accessor :operations
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@next_page_token = args[:next_page_token] if args.key?(:next_page_token)
|
|
|
|
@operations = args[:operations] if args.key?(:operations)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2018-12-01 00:36:27 +00:00
|
|
|
# Describes 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.
|
|
|
|
class LongRunningRecognizeMetadata
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# Time of the most recent processing update.
|
|
|
|
# Corresponds to the JSON property `lastUpdateTime`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :last_update_time
|
|
|
|
|
|
|
|
# Approximate percentage of audio processed thus far. Guaranteed to be 100
|
|
|
|
# when the audio is fully processed and the results are available.
|
|
|
|
# Corresponds to the JSON property `progressPercent`
|
|
|
|
# @return [Fixnum]
|
|
|
|
attr_accessor :progress_percent
|
|
|
|
|
|
|
|
# Time when the request was received.
|
|
|
|
# Corresponds to the JSON property `startTime`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :start_time
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@last_update_time = args[:last_update_time] if args.key?(:last_update_time)
|
|
|
|
@progress_percent = args[:progress_percent] if args.key?(:progress_percent)
|
|
|
|
@start_time = args[:start_time] if args.key?(:start_time)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2017-08-25 19:54:22 +00:00
|
|
|
# The top-level message sent by the client for the `LongRunningRecognize`
|
|
|
|
# method.
|
|
|
|
class LongRunningRecognizeRequest
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# Contains audio data in the encoding specified in the `RecognitionConfig`.
|
|
|
|
# Either `content` or `uri` must be supplied. Supplying both or neither
|
|
|
|
# returns google.rpc.Code.INVALID_ARGUMENT. See
|
2018-08-29 00:36:37 +00:00
|
|
|
# [content limits](/speech-to-text/quotas#content).
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `audio`
|
|
|
|
# @return [Google::Apis::SpeechV1::RecognitionAudio]
|
|
|
|
attr_accessor :audio
|
|
|
|
|
|
|
|
# Provides information to the recognizer that specifies how to process the
|
|
|
|
# request.
|
|
|
|
# Corresponds to the JSON property `config`
|
|
|
|
# @return [Google::Apis::SpeechV1::RecognitionConfig]
|
|
|
|
attr_accessor :config
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@audio = args[:audio] if args.key?(:audio)
|
|
|
|
@config = args[:config] if args.key?(:config)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2018-12-01 00:36:27 +00:00
|
|
|
# The 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.
|
|
|
|
class LongRunningRecognizeResponse
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# Output only. Sequential list of transcription results corresponding to
|
|
|
|
# sequential portions of audio.
|
|
|
|
# Corresponds to the JSON property `results`
|
|
|
|
# @return [Array<Google::Apis::SpeechV1::SpeechRecognitionResult>]
|
|
|
|
attr_accessor :results
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@results = args[:results] if args.key?(:results)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2017-08-25 19:54:22 +00:00
|
|
|
# This resource represents a long-running operation that is the result of a
|
|
|
|
# network API call.
|
|
|
|
class Operation
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# If the value is `false`, it means the operation is still in progress.
|
2017-08-30 00:35:07 +00:00
|
|
|
# If `true`, the operation is completed, and either `error` or `response` is
|
2017-08-25 19:54:22 +00:00
|
|
|
# available.
|
|
|
|
# Corresponds to the JSON property `done`
|
|
|
|
# @return [Boolean]
|
|
|
|
attr_accessor :done
|
|
|
|
alias_method :done?, :done
|
|
|
|
|
2019-03-12 00:37:23 +00:00
|
|
|
# The `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). The error model is designed to be:
|
2017-08-25 19:54:22 +00:00
|
|
|
# - Simple to use and understand for most users
|
|
|
|
# - Flexible enough to meet unexpected needs
|
|
|
|
# # Overview
|
2019-03-12 00:37:23 +00:00
|
|
|
# The `Status` message contains three pieces of data: error code, error
|
|
|
|
# message, and error details. The error code should be an enum value of
|
2017-08-25 19:54:22 +00:00
|
|
|
# google.rpc.Code, but it may accept additional error codes if needed. The
|
|
|
|
# error message should be a developer-facing English message that helps
|
|
|
|
# developers *understand* and *resolve* the error. If a localized user-facing
|
|
|
|
# error message is needed, put the localized message in the error details or
|
|
|
|
# localize it in the client. The optional error details may contain arbitrary
|
|
|
|
# information about the error. There is a predefined set of error detail types
|
|
|
|
# in the package `google.rpc` that can be used for common error conditions.
|
|
|
|
# # Language mapping
|
|
|
|
# The `Status` message is the logical representation of the error model, but it
|
|
|
|
# is not necessarily the actual wire format. When the `Status` message is
|
|
|
|
# exposed in different client libraries and different wire protocols, it can be
|
|
|
|
# mapped differently. For example, it will likely be mapped to some exceptions
|
|
|
|
# in Java, but more likely mapped to some error codes in C.
|
|
|
|
# # Other uses
|
|
|
|
# The error model and the `Status` message can be used in a variety of
|
|
|
|
# environments, either with or without APIs, to provide a
|
|
|
|
# consistent developer experience across different environments.
|
|
|
|
# Example uses of this error model include:
|
|
|
|
# - Partial errors. If a service needs to return partial errors to the client,
|
|
|
|
# it may embed the `Status` in the normal response to indicate the partial
|
|
|
|
# errors.
|
|
|
|
# - Workflow errors. A typical workflow has multiple steps. Each step may
|
|
|
|
# have a `Status` message for error reporting.
|
|
|
|
# - Batch operations. If a client uses batch request and batch response, the
|
|
|
|
# `Status` message should be used directly inside batch response, one for
|
|
|
|
# each error sub-response.
|
|
|
|
# - Asynchronous operations. If an API call embeds asynchronous operation
|
|
|
|
# results in its response, the status of those operations should be
|
|
|
|
# represented directly using the `Status` message.
|
|
|
|
# - Logging. If some API errors are stored in logs, the message `Status` could
|
|
|
|
# be used directly after any stripping needed for security/privacy reasons.
|
|
|
|
# Corresponds to the JSON property `error`
|
|
|
|
# @return [Google::Apis::SpeechV1::Status]
|
|
|
|
attr_accessor :error
|
|
|
|
|
|
|
|
# Service-specific metadata associated with the operation. It typically
|
|
|
|
# contains progress information and common metadata such as create time.
|
|
|
|
# Some services might not provide such metadata. Any method that returns a
|
|
|
|
# long-running operation should document the metadata type, if any.
|
|
|
|
# Corresponds to the JSON property `metadata`
|
|
|
|
# @return [Hash<String,Object>]
|
|
|
|
attr_accessor :metadata
|
|
|
|
|
|
|
|
# The server-assigned name, which is only unique within the same service that
|
|
|
|
# originally returns it. If you use the default HTTP mapping, the
|
2019-05-14 00:37:51 +00:00
|
|
|
# `name` should be a resource name ending with `operations/`unique_id``.
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `name`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :name
|
|
|
|
|
|
|
|
# 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`.
|
|
|
|
# Corresponds to the JSON property `response`
|
|
|
|
# @return [Hash<String,Object>]
|
|
|
|
attr_accessor :response
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@done = args[:done] if args.key?(:done)
|
|
|
|
@error = args[:error] if args.key?(:error)
|
|
|
|
@metadata = args[:metadata] if args.key?(:metadata)
|
|
|
|
@name = args[:name] if args.key?(:name)
|
|
|
|
@response = args[:response] if args.key?(:response)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
# Contains audio data in the encoding specified in the `RecognitionConfig`.
|
|
|
|
# Either `content` or `uri` must be supplied. Supplying both or neither
|
|
|
|
# returns google.rpc.Code.INVALID_ARGUMENT. See
|
2018-08-29 00:36:37 +00:00
|
|
|
# [content limits](/speech-to-text/quotas#content).
|
2017-08-25 19:54:22 +00:00
|
|
|
class RecognitionAudio
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# The audio data bytes encoded as specified in
|
2019-05-14 00:37:51 +00:00
|
|
|
# `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a
|
2017-08-25 19:54:22 +00:00
|
|
|
# pure binary representation, whereas JSON representations use base64.
|
|
|
|
# Corresponds to the JSON property `content`
|
|
|
|
# NOTE: Values are automatically base64 encoded/decoded in the client library.
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :content
|
|
|
|
|
|
|
|
# URI that points to a file that contains audio data bytes as specified in
|
2018-08-29 00:36:37 +00:00
|
|
|
# `RecognitionConfig`. The file must not be compressed (for example, gzip).
|
|
|
|
# Currently, only Google Cloud Storage URIs are
|
2017-08-25 19:54:22 +00:00
|
|
|
# supported, which must be specified in the following format:
|
|
|
|
# `gs://bucket_name/object_name` (other URI formats return
|
|
|
|
# google.rpc.Code.INVALID_ARGUMENT). For more information, see
|
|
|
|
# [Request URIs](https://cloud.google.com/storage/docs/reference-uris).
|
|
|
|
# Corresponds to the JSON property `uri`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :uri
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@content = args[:content] if args.key?(:content)
|
|
|
|
@uri = args[:uri] if args.key?(:uri)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
# Provides information to the recognizer that specifies how to process the
|
|
|
|
# request.
|
|
|
|
class RecognitionConfig
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
2019-02-20 02:14:27 +00:00
|
|
|
# *Optional* 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).
|
|
|
|
# Note: We only recognize the first channel by default.
|
|
|
|
# To perform independent recognition on each channel set
|
|
|
|
# `enable_separate_recognition_per_channel` to 'true'.
|
|
|
|
# Corresponds to the JSON property `audioChannelCount`
|
|
|
|
# @return [Fixnum]
|
|
|
|
attr_accessor :audio_channel_count
|
|
|
|
|
2018-09-12 00:36:25 +00:00
|
|
|
# *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.
|
|
|
|
# Corresponds to the JSON property `enableAutomaticPunctuation`
|
|
|
|
# @return [Boolean]
|
|
|
|
attr_accessor :enable_automatic_punctuation
|
|
|
|
alias_method :enable_automatic_punctuation?, :enable_automatic_punctuation
|
|
|
|
|
2019-01-16 00:36:25 +00:00
|
|
|
# This needs to be set to `true` explicitly and `audio_channel_count` > 1
|
|
|
|
# to get each channel recognized separately. The recognition result will
|
|
|
|
# contain a `channel_tag` field to state which channel that result belongs
|
|
|
|
# to. If this is not true, we will only recognize the first channel. The
|
|
|
|
# request is billed cumulatively for all channels recognized:
|
|
|
|
# `audio_channel_count` multiplied by the length of the audio.
|
|
|
|
# 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
|
|
|
|
|
2017-08-25 19:54:22 +00:00
|
|
|
# *Optional* 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]
|
|
|
|
attr_accessor :enable_word_time_offsets
|
|
|
|
alias_method :enable_word_time_offsets?, :enable_word_time_offsets
|
|
|
|
|
2018-03-01 00:36:09 +00:00
|
|
|
# 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.
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `encoding`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :encoding
|
|
|
|
|
|
|
|
# *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".
|
2018-08-29 00:36:37 +00:00
|
|
|
# See [Language Support](/speech-to-text/docs/languages)
|
2017-08-25 19:54:22 +00:00
|
|
|
# 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.
|
|
|
|
# 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.
|
|
|
|
# Corresponds to the JSON property `maxAlternatives`
|
|
|
|
# @return [Fixnum]
|
|
|
|
attr_accessor :max_alternatives
|
|
|
|
|
2019-02-20 02:14:27 +00:00
|
|
|
# Description of audio data to be recognized.
|
|
|
|
# Corresponds to the JSON property `metadata`
|
|
|
|
# @return [Google::Apis::SpeechV1::RecognitionMetadata]
|
|
|
|
attr_accessor :metadata
|
|
|
|
|
2018-09-12 00:36:25 +00:00
|
|
|
# *Optional* Which model to select for the given request. Select the model
|
|
|
|
# best suited to your domain to get best results. If a model is not
|
|
|
|
# explicitly specified, then we auto-select a model based on the parameters
|
|
|
|
# in the RecognitionConfig.
|
|
|
|
# <table>
|
|
|
|
# <tr>
|
|
|
|
# <td><b>Model</b></td>
|
|
|
|
# <td><b>Description</b></td>
|
|
|
|
# </tr>
|
|
|
|
# <tr>
|
|
|
|
# <td><code>command_and_search</code></td>
|
|
|
|
# <td>Best for short queries such as voice commands or voice search.</td>
|
|
|
|
# </tr>
|
|
|
|
# <tr>
|
|
|
|
# <td><code>phone_call</code></td>
|
|
|
|
# <td>Best for audio that originated from a phone call (typically
|
|
|
|
# recorded at an 8khz sampling rate).</td>
|
|
|
|
# </tr>
|
|
|
|
# <tr>
|
|
|
|
# <td><code>video</code></td>
|
|
|
|
# <td>Best for audio that originated from from video or includes multiple
|
|
|
|
# speakers. Ideally the audio is recorded at a 16khz or greater
|
|
|
|
# sampling rate. This is a premium model that costs more than the
|
|
|
|
# standard rate.</td>
|
|
|
|
# </tr>
|
|
|
|
# <tr>
|
|
|
|
# <td><code>default</code></td>
|
|
|
|
# <td>Best for audio that is not one of the specific audio models.
|
|
|
|
# For example, long-form audio. Ideally the audio is high-fidelity,
|
|
|
|
# recorded at a 16khz or greater sampling rate.</td>
|
|
|
|
# </tr>
|
|
|
|
# </table>
|
|
|
|
# Corresponds to the JSON property `model`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :model
|
|
|
|
|
2017-08-25 19:54:22 +00:00
|
|
|
# *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.
|
|
|
|
# Corresponds to the JSON property `profanityFilter`
|
|
|
|
# @return [Boolean]
|
|
|
|
attr_accessor :profanity_filter
|
|
|
|
alias_method :profanity_filter?, :profanity_filter
|
|
|
|
|
2018-03-01 00:36:09 +00:00
|
|
|
# Sample rate in Hertz of the audio data sent in all
|
2017-08-25 19:54:22 +00:00
|
|
|
# `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).
|
2019-03-27 00:37:41 +00:00
|
|
|
# This field is optional for FLAC and WAV audio files, but is
|
2019-02-07 00:36:43 +00:00
|
|
|
# required for all other audio formats. For details, see AudioEncoding.
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `sampleRateHertz`
|
|
|
|
# @return [Fixnum]
|
|
|
|
attr_accessor :sample_rate_hertz
|
|
|
|
|
2018-08-29 00:36:37 +00:00
|
|
|
# *Optional* array of SpeechContext.
|
|
|
|
# A means to provide context to assist the speech recognition. For more
|
|
|
|
# information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `speechContexts`
|
|
|
|
# @return [Array<Google::Apis::SpeechV1::SpeechContext>]
|
|
|
|
attr_accessor :speech_contexts
|
|
|
|
|
2018-09-12 00:36:25 +00:00
|
|
|
# *Optional* Set to true to use an enhanced model for speech recognition.
|
2018-09-19 00:36:24 +00:00
|
|
|
# If `use_enhanced` is set to true and the `model` field is not set, then
|
|
|
|
# an appropriate enhanced model is chosen if:
|
|
|
|
# 1. project is eligible for requesting enhanced models
|
|
|
|
# 2. 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.
|
2018-09-12 00:36:25 +00:00
|
|
|
# Enhanced speech models require that you opt-in to data logging using
|
2018-09-19 00:36:24 +00:00
|
|
|
# instructions in the
|
|
|
|
# [documentation](/speech-to-text/docs/enable-data-logging). If you set
|
|
|
|
# `use_enhanced` to true and you have not enabled audio logging, then you
|
|
|
|
# will receive an error.
|
2018-09-12 00:36:25 +00:00
|
|
|
# Corresponds to the JSON property `useEnhanced`
|
|
|
|
# @return [Boolean]
|
|
|
|
attr_accessor :use_enhanced
|
|
|
|
alias_method :use_enhanced?, :use_enhanced
|
|
|
|
|
2017-08-25 19:54:22 +00:00
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
2019-02-20 02:14:27 +00:00
|
|
|
@audio_channel_count = args[:audio_channel_count] if args.key?(:audio_channel_count)
|
2018-09-12 00:36:25 +00:00
|
|
|
@enable_automatic_punctuation = args[:enable_automatic_punctuation] if args.key?(:enable_automatic_punctuation)
|
2019-01-16 00:36:25 +00:00
|
|
|
@enable_separate_recognition_per_channel = args[:enable_separate_recognition_per_channel] if args.key?(:enable_separate_recognition_per_channel)
|
2017-08-25 19:54:22 +00:00
|
|
|
@enable_word_time_offsets = args[:enable_word_time_offsets] if args.key?(:enable_word_time_offsets)
|
|
|
|
@encoding = args[:encoding] if args.key?(:encoding)
|
|
|
|
@language_code = args[:language_code] if args.key?(:language_code)
|
|
|
|
@max_alternatives = args[:max_alternatives] if args.key?(:max_alternatives)
|
2019-02-20 02:14:27 +00:00
|
|
|
@metadata = args[:metadata] if args.key?(:metadata)
|
2018-09-12 00:36:25 +00:00
|
|
|
@model = args[:model] if args.key?(:model)
|
2017-08-25 19:54:22 +00:00
|
|
|
@profanity_filter = args[:profanity_filter] if args.key?(:profanity_filter)
|
|
|
|
@sample_rate_hertz = args[:sample_rate_hertz] if args.key?(:sample_rate_hertz)
|
|
|
|
@speech_contexts = args[:speech_contexts] if args.key?(:speech_contexts)
|
2018-09-12 00:36:25 +00:00
|
|
|
@use_enhanced = args[:use_enhanced] if args.key?(:use_enhanced)
|
2017-08-25 19:54:22 +00:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2019-02-20 02:14:27 +00:00
|
|
|
# Description of audio data to be recognized.
|
|
|
|
class RecognitionMetadata
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# Description of the content. Eg. "Recordings of federal supreme court
|
|
|
|
# hearings from 2012".
|
|
|
|
# Corresponds to the JSON property `audioTopic`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :audio_topic
|
|
|
|
|
|
|
|
# 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/.
|
|
|
|
# Corresponds to the JSON property `industryNaicsCodeOfAudio`
|
|
|
|
# @return [Fixnum]
|
|
|
|
attr_accessor :industry_naics_code_of_audio
|
|
|
|
|
|
|
|
# The use case most closely describing the audio content to be recognized.
|
|
|
|
# Corresponds to the JSON property `interactionType`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :interaction_type
|
|
|
|
|
|
|
|
# The audio type that most closely describes the audio being recognized.
|
|
|
|
# Corresponds to the JSON property `microphoneDistance`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :microphone_distance
|
|
|
|
|
|
|
|
# Obfuscated (privacy-protected) ID of the user, to identify number of
|
|
|
|
# unique users using the service.
|
|
|
|
# Corresponds to the JSON property `obfuscatedId`
|
|
|
|
# @return [Fixnum]
|
|
|
|
attr_accessor :obfuscated_id
|
|
|
|
|
|
|
|
# The original media the speech was recorded on.
|
|
|
|
# Corresponds to the JSON property `originalMediaType`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :original_media_type
|
|
|
|
|
|
|
|
# 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
|
|
|
|
# Corresponds to the JSON property `originalMimeType`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :original_mime_type
|
|
|
|
|
|
|
|
# The device used to make the recording. Examples 'Nexus 5X' or
|
|
|
|
# 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
|
|
|
|
# 'Cardioid Microphone'.
|
|
|
|
# Corresponds to the JSON property `recordingDeviceName`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :recording_device_name
|
|
|
|
|
|
|
|
# The type of device the speech was recorded with.
|
|
|
|
# Corresponds to the JSON property `recordingDeviceType`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :recording_device_type
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@audio_topic = args[:audio_topic] if args.key?(:audio_topic)
|
|
|
|
@industry_naics_code_of_audio = args[:industry_naics_code_of_audio] if args.key?(:industry_naics_code_of_audio)
|
|
|
|
@interaction_type = args[:interaction_type] if args.key?(:interaction_type)
|
|
|
|
@microphone_distance = args[:microphone_distance] if args.key?(:microphone_distance)
|
|
|
|
@obfuscated_id = args[:obfuscated_id] if args.key?(:obfuscated_id)
|
|
|
|
@original_media_type = args[:original_media_type] if args.key?(:original_media_type)
|
|
|
|
@original_mime_type = args[:original_mime_type] if args.key?(:original_mime_type)
|
|
|
|
@recording_device_name = args[:recording_device_name] if args.key?(:recording_device_name)
|
|
|
|
@recording_device_type = args[:recording_device_type] if args.key?(:recording_device_type)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2017-08-25 19:54:22 +00:00
|
|
|
# The top-level message sent by the client for the `Recognize` method.
|
|
|
|
class RecognizeRequest
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# Contains audio data in the encoding specified in the `RecognitionConfig`.
|
|
|
|
# Either `content` or `uri` must be supplied. Supplying both or neither
|
|
|
|
# returns google.rpc.Code.INVALID_ARGUMENT. See
|
2018-08-29 00:36:37 +00:00
|
|
|
# [content limits](/speech-to-text/quotas#content).
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `audio`
|
|
|
|
# @return [Google::Apis::SpeechV1::RecognitionAudio]
|
|
|
|
attr_accessor :audio
|
|
|
|
|
|
|
|
# Provides information to the recognizer that specifies how to process the
|
|
|
|
# request.
|
|
|
|
# Corresponds to the JSON property `config`
|
|
|
|
# @return [Google::Apis::SpeechV1::RecognitionConfig]
|
|
|
|
attr_accessor :config
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@audio = args[:audio] if args.key?(:audio)
|
|
|
|
@config = args[:config] if args.key?(:config)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
# The only message returned to the client by the `Recognize` method. It
|
|
|
|
# contains the result as zero or more sequential `SpeechRecognitionResult`
|
|
|
|
# messages.
|
|
|
|
class RecognizeResponse
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
2018-03-27 00:35:45 +00:00
|
|
|
# Output only. Sequential list of transcription results corresponding to
|
2017-08-25 19:54:22 +00:00
|
|
|
# sequential portions of audio.
|
|
|
|
# Corresponds to the JSON property `results`
|
|
|
|
# @return [Array<Google::Apis::SpeechV1::SpeechRecognitionResult>]
|
|
|
|
attr_accessor :results
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@results = args[:results] if args.key?(:results)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
# Provides "hints" to the speech recognizer to favor specific words and phrases
|
|
|
|
# in the results.
|
|
|
|
class SpeechContext
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# *Optional* 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
|
2018-08-29 00:36:37 +00:00
|
|
|
# [usage limits](/speech-to-text/quotas#content).
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `phrases`
|
|
|
|
# @return [Array<String>]
|
|
|
|
attr_accessor :phrases
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@phrases = args[:phrases] if args.key?(:phrases)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
# Alternative hypotheses (a.k.a. n-best list).
|
|
|
|
class SpeechRecognitionAlternative
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
2018-03-27 00:35:45 +00:00
|
|
|
# Output only. The confidence estimate between 0.0 and 1.0. A higher number
|
2017-08-25 19:54:22 +00:00
|
|
|
# indicates an estimated greater likelihood that the recognized words are
|
2018-01-25 00:35:00 +00:00
|
|
|
# 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.
|
2017-08-25 19:54:22 +00:00
|
|
|
# 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
|
|
|
|
|
2018-03-27 00:35:45 +00:00
|
|
|
# Output only. Transcript text representing the words that the user spoke.
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `transcript`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :transcript
|
|
|
|
|
2018-03-27 00:35:45 +00:00
|
|
|
# Output only. A list of word-specific information for each recognized word.
|
2018-08-29 00:36:37 +00:00
|
|
|
# Note: When `enable_speaker_diarization` is true, you will see all the words
|
2018-04-25 00:36:07 +00:00
|
|
|
# from the beginning of the audio.
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `words`
|
|
|
|
# @return [Array<Google::Apis::SpeechV1::WordInfo>]
|
|
|
|
attr_accessor :words
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@confidence = args[:confidence] if args.key?(:confidence)
|
|
|
|
@transcript = args[:transcript] if args.key?(:transcript)
|
|
|
|
@words = args[:words] if args.key?(:words)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
# A speech recognition result corresponding to a portion of the audio.
|
|
|
|
class SpeechRecognitionResult
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
2018-03-27 00:35:45 +00:00
|
|
|
# Output only. May contain one or more recognition hypotheses (up to the
|
2017-08-25 19:54:22 +00:00
|
|
|
# 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::SpeechV1::SpeechRecognitionAlternative>]
|
|
|
|
attr_accessor :alternatives
|
|
|
|
|
2019-01-16 00:36:25 +00:00
|
|
|
# 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'.
|
|
|
|
# Corresponds to the JSON property `channelTag`
|
|
|
|
# @return [Fixnum]
|
|
|
|
attr_accessor :channel_tag
|
|
|
|
|
2017-08-25 19:54:22 +00:00
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@alternatives = args[:alternatives] if args.key?(:alternatives)
|
2019-01-16 00:36:25 +00:00
|
|
|
@channel_tag = args[:channel_tag] if args.key?(:channel_tag)
|
2017-08-25 19:54:22 +00:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2019-03-12 00:37:23 +00:00
|
|
|
# The `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). The error model is designed to be:
|
2017-08-25 19:54:22 +00:00
|
|
|
# - Simple to use and understand for most users
|
|
|
|
# - Flexible enough to meet unexpected needs
|
|
|
|
# # Overview
|
2019-03-12 00:37:23 +00:00
|
|
|
# The `Status` message contains three pieces of data: error code, error
|
|
|
|
# message, and error details. The error code should be an enum value of
|
2017-08-25 19:54:22 +00:00
|
|
|
# google.rpc.Code, but it may accept additional error codes if needed. The
|
|
|
|
# error message should be a developer-facing English message that helps
|
|
|
|
# developers *understand* and *resolve* the error. If a localized user-facing
|
|
|
|
# error message is needed, put the localized message in the error details or
|
|
|
|
# localize it in the client. The optional error details may contain arbitrary
|
|
|
|
# information about the error. There is a predefined set of error detail types
|
|
|
|
# in the package `google.rpc` that can be used for common error conditions.
|
|
|
|
# # Language mapping
|
|
|
|
# The `Status` message is the logical representation of the error model, but it
|
|
|
|
# is not necessarily the actual wire format. When the `Status` message is
|
|
|
|
# exposed in different client libraries and different wire protocols, it can be
|
|
|
|
# mapped differently. For example, it will likely be mapped to some exceptions
|
|
|
|
# in Java, but more likely mapped to some error codes in C.
|
|
|
|
# # Other uses
|
|
|
|
# The error model and the `Status` message can be used in a variety of
|
|
|
|
# environments, either with or without APIs, to provide a
|
|
|
|
# consistent developer experience across different environments.
|
|
|
|
# Example uses of this error model include:
|
|
|
|
# - Partial errors. If a service needs to return partial errors to the client,
|
|
|
|
# it may embed the `Status` in the normal response to indicate the partial
|
|
|
|
# errors.
|
|
|
|
# - Workflow errors. A typical workflow has multiple steps. Each step may
|
|
|
|
# have a `Status` message for error reporting.
|
|
|
|
# - Batch operations. If a client uses batch request and batch response, the
|
|
|
|
# `Status` message should be used directly inside batch response, one for
|
|
|
|
# each error sub-response.
|
|
|
|
# - Asynchronous operations. If an API call embeds asynchronous operation
|
|
|
|
# results in its response, the status of those operations should be
|
|
|
|
# represented directly using the `Status` message.
|
|
|
|
# - Logging. If some API errors are stored in logs, the message `Status` could
|
|
|
|
# be used directly after any stripping needed for security/privacy reasons.
|
|
|
|
class Status
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
|
|
|
# The status code, which should be an enum value of google.rpc.Code.
|
|
|
|
# Corresponds to the JSON property `code`
|
|
|
|
# @return [Fixnum]
|
|
|
|
attr_accessor :code
|
|
|
|
|
|
|
|
# A list of messages that carry the error details. There is a common set of
|
|
|
|
# message types for APIs to use.
|
|
|
|
# Corresponds to the JSON property `details`
|
|
|
|
# @return [Array<Hash<String,Object>>]
|
|
|
|
attr_accessor :details
|
|
|
|
|
|
|
|
# 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.
|
|
|
|
# Corresponds to the JSON property `message`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :message
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@code = args[:code] if args.key?(:code)
|
|
|
|
@details = args[:details] if args.key?(:details)
|
|
|
|
@message = args[:message] if args.key?(:message)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2018-01-25 00:35:00 +00:00
|
|
|
# Word-specific information for recognized words.
|
2017-08-25 19:54:22 +00:00
|
|
|
class WordInfo
|
|
|
|
include Google::Apis::Core::Hashable
|
|
|
|
|
2018-03-27 00:35:45 +00:00
|
|
|
# Output only. Time offset relative to the beginning of the audio,
|
2017-08-25 19:54:22 +00:00
|
|
|
# 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
|
|
|
|
|
2018-03-27 00:35:45 +00:00
|
|
|
# Output only. Time offset relative to the beginning of the audio,
|
2017-08-25 19:54:22 +00:00
|
|
|
# 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
|
|
|
|
|
2018-03-27 00:35:45 +00:00
|
|
|
# Output only. The word corresponding to this set of information.
|
2017-08-25 19:54:22 +00:00
|
|
|
# Corresponds to the JSON property `word`
|
|
|
|
# @return [String]
|
|
|
|
attr_accessor :word
|
|
|
|
|
|
|
|
def initialize(**args)
|
|
|
|
update!(**args)
|
|
|
|
end
|
|
|
|
|
|
|
|
# Update properties of this object
|
|
|
|
def update!(**args)
|
|
|
|
@end_time = args[:end_time] if args.key?(:end_time)
|
|
|
|
@start_time = args[:start_time] if args.key?(:start_time)
|
|
|
|
@word = args[:word] if args.key?(:word)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|