google-cloud-speech-v1p1beta1 0.1.2 → 0.3.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/AUTHENTICATION.md +6 -6
- data/README.md +1 -1
- data/lib/google/cloud/speech/v1p1beta1.rb +1 -1
- data/lib/google/cloud/speech/v1p1beta1/cloud_speech_pb.rb +5 -0
- data/lib/google/cloud/speech/v1p1beta1/cloud_speech_services_pb.rb +1 -2
- data/lib/google/cloud/speech/v1p1beta1/resource_pb.rb +46 -0
- data/lib/google/cloud/speech/v1p1beta1/speech.rb +2 -1
- data/lib/google/cloud/speech/v1p1beta1/speech/client.rb +106 -91
- data/lib/google/cloud/speech/v1p1beta1/speech/credentials.rb +1 -1
- data/lib/google/cloud/speech/v1p1beta1/speech/operations.rb +109 -103
- data/lib/google/cloud/speech/v1p1beta1/speech/paths.rb +71 -0
- data/lib/google/cloud/speech/v1p1beta1/version.rb +1 -1
- data/proto_docs/google/api/resource.rb +12 -12
- data/proto_docs/google/cloud/speech/v1p1beta1/cloud_speech.rb +141 -126
- data/proto_docs/google/cloud/speech/v1p1beta1/resource.rb +133 -0
- data/proto_docs/google/longrunning/operations.rb +30 -30
- data/proto_docs/google/protobuf/any.rb +4 -4
- data/proto_docs/google/protobuf/duration.rb +4 -4
- data/proto_docs/google/protobuf/empty.rb +2 -2
- data/proto_docs/google/protobuf/timestamp.rb +4 -4
- data/proto_docs/google/rpc/status.rb +6 -6
- metadata +36 -6
- data/lib/google/cloud/common_resources_pb.rb +0 -15
@@ -0,0 +1,71 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
# Copyright 2020 Google LLC
|
4
|
+
#
|
5
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
6
|
+
# you may not use this file except in compliance with the License.
|
7
|
+
# You may obtain a copy of the License at
|
8
|
+
#
|
9
|
+
# https://www.apache.org/licenses/LICENSE-2.0
|
10
|
+
#
|
11
|
+
# Unless required by applicable law or agreed to in writing, software
|
12
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
13
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
14
|
+
# See the License for the specific language governing permissions and
|
15
|
+
# limitations under the License.
|
16
|
+
|
17
|
+
# Auto-generated by gapic-generator-ruby. DO NOT EDIT!
|
18
|
+
|
19
|
+
|
20
|
+
module Google
|
21
|
+
module Cloud
|
22
|
+
module Speech
|
23
|
+
module V1p1beta1
|
24
|
+
module Speech
|
25
|
+
# Path helper methods for the Speech API.
|
26
|
+
module Paths
|
27
|
+
##
|
28
|
+
# Create a fully-qualified CustomClass resource string.
|
29
|
+
#
|
30
|
+
# The resource will be in the following format:
|
31
|
+
#
|
32
|
+
# `projects/{project}/locations/{location}/customClasses/{custom_class}`
|
33
|
+
#
|
34
|
+
# @param project [String]
|
35
|
+
# @param location [String]
|
36
|
+
# @param custom_class [String]
|
37
|
+
#
|
38
|
+
# @return [::String]
|
39
|
+
def custom_class_path project:, location:, custom_class:
|
40
|
+
raise ::ArgumentError, "project cannot contain /" if project.to_s.include? "/"
|
41
|
+
raise ::ArgumentError, "location cannot contain /" if location.to_s.include? "/"
|
42
|
+
|
43
|
+
"projects/#{project}/locations/#{location}/customClasses/#{custom_class}"
|
44
|
+
end
|
45
|
+
|
46
|
+
##
|
47
|
+
# Create a fully-qualified PhraseSet resource string.
|
48
|
+
#
|
49
|
+
# The resource will be in the following format:
|
50
|
+
#
|
51
|
+
# `projects/{project}/locations/{location}/phraseSets/{phrase_set}`
|
52
|
+
#
|
53
|
+
# @param project [String]
|
54
|
+
# @param location [String]
|
55
|
+
# @param phrase_set [String]
|
56
|
+
#
|
57
|
+
# @return [::String]
|
58
|
+
def phrase_set_path project:, location:, phrase_set:
|
59
|
+
raise ::ArgumentError, "project cannot contain /" if project.to_s.include? "/"
|
60
|
+
raise ::ArgumentError, "location cannot contain /" if location.to_s.include? "/"
|
61
|
+
|
62
|
+
"projects/#{project}/locations/#{location}/phraseSets/#{phrase_set}"
|
63
|
+
end
|
64
|
+
|
65
|
+
extend self
|
66
|
+
end
|
67
|
+
end
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
@@ -128,7 +128,7 @@ module Google
|
|
128
128
|
# - pattern: "shelves/{shelf}"
|
129
129
|
# parent_type: "cloudresourcemanager.googleapis.com/Folder"
|
130
130
|
# @!attribute [rw] type
|
131
|
-
# @return [String]
|
131
|
+
# @return [::String]
|
132
132
|
# The resource type. It must be in the format of
|
133
133
|
# \\{service_name}/\\{resource_type_kind}. The `resource_type_kind` must be
|
134
134
|
# singular and must not include version numbers.
|
@@ -140,7 +140,7 @@ module Google
|
|
140
140
|
# should use PascalCase (UpperCamelCase). The maximum number of
|
141
141
|
# characters allowed for the `resource_type_kind` is 100.
|
142
142
|
# @!attribute [rw] pattern
|
143
|
-
# @return [Array
|
143
|
+
# @return [::Array<::String>]
|
144
144
|
# Optional. The relative resource name pattern associated with this resource
|
145
145
|
# type. The DNS prefix of the full resource name shouldn't be specified here.
|
146
146
|
#
|
@@ -161,11 +161,11 @@ module Google
|
|
161
161
|
# the same component name (e.g. "project") refers to IDs of the same
|
162
162
|
# type of resource.
|
163
163
|
# @!attribute [rw] name_field
|
164
|
-
# @return [String]
|
164
|
+
# @return [::String]
|
165
165
|
# Optional. The field on the resource that designates the resource name
|
166
166
|
# field. If omitted, this is assumed to be "name".
|
167
167
|
# @!attribute [rw] history
|
168
|
-
# @return [Google::Api::ResourceDescriptor::History]
|
168
|
+
# @return [::Google::Api::ResourceDescriptor::History]
|
169
169
|
# Optional. The historical or future-looking state of the resource pattern.
|
170
170
|
#
|
171
171
|
# Example:
|
@@ -182,19 +182,19 @@ module Google
|
|
182
182
|
# };
|
183
183
|
# }
|
184
184
|
# @!attribute [rw] plural
|
185
|
-
# @return [String]
|
185
|
+
# @return [::String]
|
186
186
|
# The plural name used in the resource name, such as 'projects' for
|
187
187
|
# the name of 'projects/\\{project}'. It is the same concept of the `plural`
|
188
188
|
# field in k8s CRD spec
|
189
189
|
# https://kubernetes.io/docs/tasks/access-kubernetes-api/custom-resources/custom-resource-definitions/
|
190
190
|
# @!attribute [rw] singular
|
191
|
-
# @return [String]
|
191
|
+
# @return [::String]
|
192
192
|
# The same concept of the `singular` field in k8s CRD spec
|
193
193
|
# https://kubernetes.io/docs/tasks/access-kubernetes-api/custom-resources/custom-resource-definitions/
|
194
194
|
# Such as "project" for the `resourcemanager.googleapis.com/Project` type.
|
195
195
|
class ResourceDescriptor
|
196
|
-
include Google::Protobuf::MessageExts
|
197
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
196
|
+
include ::Google::Protobuf::MessageExts
|
197
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
198
198
|
|
199
199
|
# A description of the historical or future-looking state of the
|
200
200
|
# resource pattern.
|
@@ -216,7 +216,7 @@ module Google
|
|
216
216
|
# Defines a proto annotation that describes a string field that refers to
|
217
217
|
# an API resource.
|
218
218
|
# @!attribute [rw] type
|
219
|
-
# @return [String]
|
219
|
+
# @return [::String]
|
220
220
|
# The resource type that the annotated field references.
|
221
221
|
#
|
222
222
|
# Example:
|
@@ -227,7 +227,7 @@ module Google
|
|
227
227
|
# }];
|
228
228
|
# }
|
229
229
|
# @!attribute [rw] child_type
|
230
|
-
# @return [String]
|
230
|
+
# @return [::String]
|
231
231
|
# The resource type of a child collection that the annotated field
|
232
232
|
# references. This is useful for annotating the `parent` field that
|
233
233
|
# doesn't have a fixed resource type.
|
@@ -240,8 +240,8 @@ module Google
|
|
240
240
|
# };
|
241
241
|
# }
|
242
242
|
class ResourceReference
|
243
|
-
include Google::Protobuf::MessageExts
|
244
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
243
|
+
include ::Google::Protobuf::MessageExts
|
244
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
245
245
|
end
|
246
246
|
end
|
247
247
|
end
|
@@ -23,29 +23,29 @@ module Google
|
|
23
23
|
module V1p1beta1
|
24
24
|
# The top-level message sent by the client for the `Recognize` method.
|
25
25
|
# @!attribute [rw] config
|
26
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionConfig]
|
26
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionConfig]
|
27
27
|
# Required. Provides information to the recognizer that specifies how to
|
28
28
|
# process the request.
|
29
29
|
# @!attribute [rw] audio
|
30
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionAudio]
|
30
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionAudio]
|
31
31
|
# Required. The audio data to be recognized.
|
32
32
|
class RecognizeRequest
|
33
|
-
include Google::Protobuf::MessageExts
|
34
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
33
|
+
include ::Google::Protobuf::MessageExts
|
34
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
35
35
|
end
|
36
36
|
|
37
37
|
# The top-level message sent by the client for the `LongRunningRecognize`
|
38
38
|
# method.
|
39
39
|
# @!attribute [rw] config
|
40
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionConfig]
|
40
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionConfig]
|
41
41
|
# Required. Provides information to the recognizer that specifies how to
|
42
42
|
# process the request.
|
43
43
|
# @!attribute [rw] audio
|
44
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionAudio]
|
44
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionAudio]
|
45
45
|
# Required. The audio data to be recognized.
|
46
46
|
class LongRunningRecognizeRequest
|
47
|
-
include Google::Protobuf::MessageExts
|
48
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
47
|
+
include ::Google::Protobuf::MessageExts
|
48
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
49
49
|
end
|
50
50
|
|
51
51
|
# The top-level message sent by the client for the `StreamingRecognize` method.
|
@@ -54,12 +54,12 @@ module Google
|
|
54
54
|
# `audio_content`. All subsequent messages must contain `audio_content` and
|
55
55
|
# must not contain a `streaming_config` message.
|
56
56
|
# @!attribute [rw] streaming_config
|
57
|
-
# @return [Google::Cloud::Speech::V1p1beta1::StreamingRecognitionConfig]
|
57
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::StreamingRecognitionConfig]
|
58
58
|
# Provides information to the recognizer that specifies how to process the
|
59
59
|
# request. The first `StreamingRecognizeRequest` message must contain a
|
60
60
|
# `streaming_config` message.
|
61
61
|
# @!attribute [rw] audio_content
|
62
|
-
# @return [String]
|
62
|
+
# @return [::String]
|
63
63
|
# The audio data to be recognized. Sequential chunks of audio data are sent
|
64
64
|
# in sequential `StreamingRecognizeRequest` messages. The first
|
65
65
|
# `StreamingRecognizeRequest` message must not contain `audio_content` data
|
@@ -69,18 +69,18 @@ module Google
|
|
69
69
|
# pure binary representation (not base64). See
|
70
70
|
# [content limits](https://cloud.google.com/speech-to-text/quotas#content).
|
71
71
|
class StreamingRecognizeRequest
|
72
|
-
include Google::Protobuf::MessageExts
|
73
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
72
|
+
include ::Google::Protobuf::MessageExts
|
73
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
74
74
|
end
|
75
75
|
|
76
76
|
# Provides information to the recognizer that specifies how to process the
|
77
77
|
# request.
|
78
78
|
# @!attribute [rw] config
|
79
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionConfig]
|
79
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionConfig]
|
80
80
|
# Required. Provides information to the recognizer that specifies how to
|
81
81
|
# process the request.
|
82
82
|
# @!attribute [rw] single_utterance
|
83
|
-
# @return [Boolean]
|
83
|
+
# @return [::Boolean]
|
84
84
|
# If `false` or omitted, the recognizer will perform continuous
|
85
85
|
# recognition (continuing to wait for and process audio even if the user
|
86
86
|
# pauses speaking) until the client closes the input stream (gRPC API) or
|
@@ -93,34 +93,36 @@ module Google
|
|
93
93
|
# more than one `StreamingRecognitionResult` with the `is_final` flag set to
|
94
94
|
# `true`.
|
95
95
|
# @!attribute [rw] interim_results
|
96
|
-
# @return [Boolean]
|
96
|
+
# @return [::Boolean]
|
97
97
|
# If `true`, interim results (tentative hypotheses) may be
|
98
98
|
# returned as they become available (these interim results are indicated with
|
99
99
|
# the `is_final=false` flag).
|
100
100
|
# If `false` or omitted, only `is_final=true` result(s) are returned.
|
101
101
|
class StreamingRecognitionConfig
|
102
|
-
include Google::Protobuf::MessageExts
|
103
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
102
|
+
include ::Google::Protobuf::MessageExts
|
103
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
104
104
|
end
|
105
105
|
|
106
106
|
# Provides information to the recognizer that specifies how to process the
|
107
107
|
# request.
|
108
108
|
# @!attribute [rw] encoding
|
109
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding]
|
109
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding]
|
110
110
|
# Encoding of audio data sent in all `RecognitionAudio` messages.
|
111
111
|
# This field is optional for `FLAC` and `WAV` audio files and required
|
112
|
-
# for all other audio formats. For details, see
|
112
|
+
# for all other audio formats. For details, see
|
113
|
+
# {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
|
113
114
|
# @!attribute [rw] sample_rate_hertz
|
114
|
-
# @return [Integer]
|
115
|
+
# @return [::Integer]
|
115
116
|
# Sample rate in Hertz of the audio data sent in all
|
116
117
|
# `RecognitionAudio` messages. Valid values are: 8000-48000.
|
117
118
|
# 16000 is optimal. For best results, set the sampling rate of the audio
|
118
119
|
# source to 16000 Hz. If that's not possible, use the native sample rate of
|
119
120
|
# the audio source (instead of re-sampling).
|
120
121
|
# This field is optional for FLAC and WAV audio files, but is
|
121
|
-
# required for all other audio formats. For details, see
|
122
|
+
# required for all other audio formats. For details, see
|
123
|
+
# {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
|
122
124
|
# @!attribute [rw] audio_channel_count
|
123
|
-
# @return [Integer]
|
125
|
+
# @return [::Integer]
|
124
126
|
# The number of channels in the input audio data.
|
125
127
|
# ONLY set this for MULTI-CHANNEL recognition.
|
126
128
|
# Valid values for LINEAR16 and FLAC are `1`-`8`.
|
@@ -131,7 +133,7 @@ module Google
|
|
131
133
|
# To perform independent recognition on each channel set
|
132
134
|
# `enable_separate_recognition_per_channel` to 'true'.
|
133
135
|
# @!attribute [rw] enable_separate_recognition_per_channel
|
134
|
-
# @return [Boolean]
|
136
|
+
# @return [::Boolean]
|
135
137
|
# This needs to be set to `true` explicitly and `audio_channel_count` > 1
|
136
138
|
# to get each channel recognized separately. The recognition result will
|
137
139
|
# contain a `channel_tag` field to state which channel that result belongs
|
@@ -139,7 +141,7 @@ module Google
|
|
139
141
|
# request is billed cumulatively for all channels recognized:
|
140
142
|
# `audio_channel_count` multiplied by the length of the audio.
|
141
143
|
# @!attribute [rw] language_code
|
142
|
-
# @return [String]
|
144
|
+
# @return [::String]
|
143
145
|
# Required. The language of the supplied audio as a
|
144
146
|
# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
|
145
147
|
# Example: "en-US".
|
@@ -147,7 +149,7 @@ module Google
|
|
147
149
|
# Support](https://cloud.google.com/speech-to-text/docs/languages) for a list
|
148
150
|
# of the currently supported language codes.
|
149
151
|
# @!attribute [rw] alternative_language_codes
|
150
|
-
# @return [Array
|
152
|
+
# @return [::Array<::String>]
|
151
153
|
# A list of up to 3 additional
|
152
154
|
# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
|
153
155
|
# listing possible alternative languages of the supplied audio.
|
@@ -161,7 +163,7 @@ module Google
|
|
161
163
|
# and performance may vary for other use cases (e.g., phone call
|
162
164
|
# transcription).
|
163
165
|
# @!attribute [rw] max_alternatives
|
164
|
-
# @return [Integer]
|
166
|
+
# @return [::Integer]
|
165
167
|
# Maximum number of recognition hypotheses to be returned.
|
166
168
|
# Specifically, the maximum number of `SpeechRecognitionAlternative` messages
|
167
169
|
# within each `SpeechRecognitionResult`.
|
@@ -169,51 +171,55 @@ module Google
|
|
169
171
|
# Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of
|
170
172
|
# one. If omitted, will return a maximum of one.
|
171
173
|
# @!attribute [rw] profanity_filter
|
172
|
-
# @return [Boolean]
|
174
|
+
# @return [::Boolean]
|
173
175
|
# If set to `true`, the server will attempt to filter out
|
174
176
|
# profanities, replacing all but the initial character in each filtered word
|
175
177
|
# with asterisks, e.g. "f***". If set to `false` or omitted, profanities
|
176
178
|
# won't be filtered out.
|
179
|
+
# @!attribute [rw] adaptation
|
180
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::SpeechAdaptation]
|
181
|
+
# Speech adaptation configuration improves the accuracy of speech
|
182
|
+
# recognition. When speech adaptation is set it supersedes the
|
183
|
+
# `speech_contexts` field. For more information, see the [speech
|
184
|
+
# adaptation](https://cloud.google.com/speech-to-text/docs/context-strength)
|
185
|
+
# documentation.
|
177
186
|
# @!attribute [rw] speech_contexts
|
178
|
-
# @return [Array
|
179
|
-
# Array of {Google::Cloud::Speech::V1p1beta1::SpeechContext SpeechContext}.
|
187
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechContext>]
|
188
|
+
# Array of {::Google::Cloud::Speech::V1p1beta1::SpeechContext SpeechContext}.
|
180
189
|
# A means to provide context to assist the speech recognition. For more
|
181
190
|
# information, see
|
182
191
|
# [speech
|
183
192
|
# adaptation](https://cloud.google.com/speech-to-text/docs/context-strength).
|
184
193
|
# @!attribute [rw] enable_word_time_offsets
|
185
|
-
# @return [Boolean]
|
194
|
+
# @return [::Boolean]
|
186
195
|
# If `true`, the top result includes a list of words and
|
187
196
|
# the start and end time offsets (timestamps) for those words. If
|
188
197
|
# `false`, no word-level time offset information is returned. The default is
|
189
198
|
# `false`.
|
190
199
|
# @!attribute [rw] enable_word_confidence
|
191
|
-
# @return [Boolean]
|
200
|
+
# @return [::Boolean]
|
192
201
|
# If `true`, the top result includes a list of words and the
|
193
202
|
# confidence for those words. If `false`, no word-level confidence
|
194
203
|
# information is returned. The default is `false`.
|
195
204
|
# @!attribute [rw] enable_automatic_punctuation
|
196
|
-
# @return [Boolean]
|
205
|
+
# @return [::Boolean]
|
197
206
|
# If 'true', adds punctuation to recognition result hypotheses.
|
198
207
|
# This feature is only available in select languages. Setting this for
|
199
208
|
# requests in other languages has no effect at all.
|
200
209
|
# The default 'false' value does not add punctuation to result hypotheses.
|
201
|
-
# Note: This is currently offered as an experimental service, complimentary
|
202
|
-
# to all users. In the future this may be exclusively available as a
|
203
|
-
# premium feature.
|
204
210
|
# @!attribute [rw] enable_speaker_diarization
|
205
|
-
# @return [Boolean]
|
211
|
+
# @return [::Boolean]
|
206
212
|
# If 'true', enables speaker detection for each recognized word in
|
207
213
|
# the top alternative of the recognition result using a speaker_tag provided
|
208
214
|
# in the WordInfo.
|
209
215
|
# Note: Use diarization_config instead.
|
210
216
|
# @!attribute [rw] diarization_speaker_count
|
211
|
-
# @return [Integer]
|
217
|
+
# @return [::Integer]
|
212
218
|
# If set, specifies the estimated number of speakers in the conversation.
|
213
219
|
# Defaults to '2'. Ignored unless enable_speaker_diarization is set to true.
|
214
220
|
# Note: Use diarization_config instead.
|
215
221
|
# @!attribute [rw] diarization_config
|
216
|
-
# @return [Google::Cloud::Speech::V1p1beta1::SpeakerDiarizationConfig]
|
222
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::SpeakerDiarizationConfig]
|
217
223
|
# Config to enable speaker diarization and set additional
|
218
224
|
# parameters to make diarization better suited for your application.
|
219
225
|
# Note: When this is enabled, we send all the words from the beginning of the
|
@@ -223,10 +229,10 @@ module Google
|
|
223
229
|
# For non-streaming requests, the diarization results will be provided only
|
224
230
|
# in the top alternative of the FINAL SpeechRecognitionResult.
|
225
231
|
# @!attribute [rw] metadata
|
226
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata]
|
232
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata]
|
227
233
|
# Metadata regarding this request.
|
228
234
|
# @!attribute [rw] model
|
229
|
-
# @return [String]
|
235
|
+
# @return [::String]
|
230
236
|
# Which model to select for the given request. Select the model
|
231
237
|
# best suited to your domain to get best results. If a model is not
|
232
238
|
# explicitly specified, then we auto-select a model based on the parameters
|
@@ -260,7 +266,7 @@ module Google
|
|
260
266
|
# </tr>
|
261
267
|
# </table>
|
262
268
|
# @!attribute [rw] use_enhanced
|
263
|
-
# @return [Boolean]
|
269
|
+
# @return [::Boolean]
|
264
270
|
# Set to true to use an enhanced model for speech recognition.
|
265
271
|
# If `use_enhanced` is set to true and the `model` field is not set, then
|
266
272
|
# an appropriate enhanced model is chosen if an enhanced model exists for
|
@@ -270,8 +276,8 @@ module Google
|
|
270
276
|
# does not exist, then the speech is recognized using the standard version
|
271
277
|
# of the specified model.
|
272
278
|
class RecognitionConfig
|
273
|
-
include Google::Protobuf::MessageExts
|
274
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
279
|
+
include ::Google::Protobuf::MessageExts
|
280
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
275
281
|
|
276
282
|
# The encoding of the audio data sent in the request.
|
277
283
|
#
|
@@ -294,7 +300,8 @@ module Google
|
|
294
300
|
# an `AudioEncoding` when you send send `FLAC` or `WAV` audio, the
|
295
301
|
# encoding configuration must match the encoding described in the audio
|
296
302
|
# header; otherwise the request returns an
|
297
|
-
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
|
303
|
+
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
|
304
|
+
# code.
|
298
305
|
module AudioEncoding
|
299
306
|
# Not specified.
|
300
307
|
ENCODING_UNSPECIFIED = 0
|
@@ -340,74 +347,77 @@ module Google
|
|
340
347
|
SPEEX_WITH_HEADER_BYTE = 7
|
341
348
|
|
342
349
|
# MP3 audio. Support all standard MP3 bitrates (which range from 32-320
|
343
|
-
# kbps). When using this encoding, `sample_rate_hertz`
|
344
|
-
#
|
350
|
+
# kbps). When using this encoding, `sample_rate_hertz` has to match the
|
351
|
+
# sample rate of the file being used.
|
345
352
|
MP3 = 8
|
346
353
|
end
|
347
354
|
end
|
348
355
|
|
349
356
|
# Config to enable speaker diarization.
|
350
357
|
# @!attribute [rw] enable_speaker_diarization
|
351
|
-
# @return [Boolean]
|
358
|
+
# @return [::Boolean]
|
352
359
|
# If 'true', enables speaker detection for each recognized word in
|
353
360
|
# the top alternative of the recognition result using a speaker_tag provided
|
354
361
|
# in the WordInfo.
|
355
362
|
# @!attribute [rw] min_speaker_count
|
356
|
-
# @return [Integer]
|
363
|
+
# @return [::Integer]
|
357
364
|
# Minimum number of speakers in the conversation. This range gives you more
|
358
365
|
# flexibility by allowing the system to automatically determine the correct
|
359
366
|
# number of speakers. If not set, the default value is 2.
|
360
367
|
# @!attribute [rw] max_speaker_count
|
361
|
-
# @return [Integer]
|
368
|
+
# @return [::Integer]
|
362
369
|
# Maximum number of speakers in the conversation. This range gives you more
|
363
370
|
# flexibility by allowing the system to automatically determine the correct
|
364
371
|
# number of speakers. If not set, the default value is 6.
|
372
|
+
# @!attribute [r] speaker_tag
|
373
|
+
# @return [::Integer]
|
374
|
+
# Output only. Unused.
|
365
375
|
class SpeakerDiarizationConfig
|
366
|
-
include Google::Protobuf::MessageExts
|
367
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
376
|
+
include ::Google::Protobuf::MessageExts
|
377
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
368
378
|
end
|
369
379
|
|
370
380
|
# Description of audio data to be recognized.
|
371
381
|
# @!attribute [rw] interaction_type
|
372
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::InteractionType]
|
382
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::InteractionType]
|
373
383
|
# The use case most closely describing the audio content to be recognized.
|
374
384
|
# @!attribute [rw] industry_naics_code_of_audio
|
375
|
-
# @return [Integer]
|
385
|
+
# @return [::Integer]
|
376
386
|
# The industry vertical to which this speech recognition request most
|
377
387
|
# closely applies. This is most indicative of the topics contained
|
378
388
|
# in the audio. Use the 6-digit NAICS code to identify the industry
|
379
389
|
# vertical - see https://www.naics.com/search/.
|
380
390
|
# @!attribute [rw] microphone_distance
|
381
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::MicrophoneDistance]
|
391
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::MicrophoneDistance]
|
382
392
|
# The audio type that most closely describes the audio being recognized.
|
383
393
|
# @!attribute [rw] original_media_type
|
384
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::OriginalMediaType]
|
394
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::OriginalMediaType]
|
385
395
|
# The original media the speech was recorded on.
|
386
396
|
# @!attribute [rw] recording_device_type
|
387
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::RecordingDeviceType]
|
397
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::RecordingDeviceType]
|
388
398
|
# The type of device the speech was recorded with.
|
389
399
|
# @!attribute [rw] recording_device_name
|
390
|
-
# @return [String]
|
400
|
+
# @return [::String]
|
391
401
|
# The device used to make the recording. Examples 'Nexus 5X' or
|
392
402
|
# 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
|
393
403
|
# 'Cardioid Microphone'.
|
394
404
|
# @!attribute [rw] original_mime_type
|
395
|
-
# @return [String]
|
405
|
+
# @return [::String]
|
396
406
|
# Mime type of the original audio file. For example `audio/m4a`,
|
397
407
|
# `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`.
|
398
408
|
# A list of possible audio mime types is maintained at
|
399
409
|
# http://www.iana.org/assignments/media-types/media-types.xhtml#audio
|
400
410
|
# @!attribute [rw] obfuscated_id
|
401
|
-
# @return [Integer]
|
411
|
+
# @return [::Integer]
|
402
412
|
# Obfuscated (privacy-protected) ID of the user, to identify number of
|
403
413
|
# unique users using the service.
|
404
414
|
# @!attribute [rw] audio_topic
|
405
|
-
# @return [String]
|
415
|
+
# @return [::String]
|
406
416
|
# Description of the content. Eg. "Recordings of federal supreme court
|
407
417
|
# hearings from 2012".
|
408
418
|
class RecognitionMetadata
|
409
|
-
include Google::Protobuf::MessageExts
|
410
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
419
|
+
include ::Google::Protobuf::MessageExts
|
420
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
411
421
|
|
412
422
|
# Use case categories that the audio recognition request can be described
|
413
423
|
# by.
|
@@ -504,7 +514,7 @@ module Google
|
|
504
514
|
# Provides "hints" to the speech recognizer to favor specific words and phrases
|
505
515
|
# in the results.
|
506
516
|
# @!attribute [rw] phrases
|
507
|
-
# @return [Array
|
517
|
+
# @return [::Array<::String>]
|
508
518
|
# A list of strings containing words and phrases "hints" so that
|
509
519
|
# the speech recognition is more likely to recognize them. This can be used
|
510
520
|
# to improve the accuracy for specific words and phrases, for example, if
|
@@ -518,7 +528,7 @@ module Google
|
|
518
528
|
# improves the likelihood of correctly transcribing audio that includes
|
519
529
|
# months.
|
520
530
|
# @!attribute [rw] boost
|
521
|
-
# @return [Float]
|
531
|
+
# @return [::Float]
|
522
532
|
# Hint Boost. Positive value will increase the probability that a specific
|
523
533
|
# phrase will be recognized over other similar sounding phrases. The higher
|
524
534
|
# the boost, the higher the chance of false positive recognition as well.
|
@@ -528,43 +538,44 @@ module Google
|
|
528
538
|
# values between 0 and 20. We recommend using a binary search approach to
|
529
539
|
# finding the optimal value for your use case.
|
530
540
|
class SpeechContext
|
531
|
-
include Google::Protobuf::MessageExts
|
532
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
541
|
+
include ::Google::Protobuf::MessageExts
|
542
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
533
543
|
end
|
534
544
|
|
535
545
|
# Contains audio data in the encoding specified in the `RecognitionConfig`.
|
536
546
|
# Either `content` or `uri` must be supplied. Supplying both or neither
|
537
|
-
# returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
|
538
|
-
# [content limits](https://cloud.google.com/speech-to-text/quotas#content).
|
547
|
+
# returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
|
548
|
+
# See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
|
539
549
|
# @!attribute [rw] content
|
540
|
-
# @return [String]
|
550
|
+
# @return [::String]
|
541
551
|
# The audio data bytes encoded as specified in
|
542
552
|
# `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a
|
543
553
|
# pure binary representation, whereas JSON representations use base64.
|
544
554
|
# @!attribute [rw] uri
|
545
|
-
# @return [String]
|
555
|
+
# @return [::String]
|
546
556
|
# URI that points to a file that contains audio data bytes as specified in
|
547
557
|
# `RecognitionConfig`. The file must not be compressed (for example, gzip).
|
548
558
|
# Currently, only Google Cloud Storage URIs are
|
549
559
|
# supported, which must be specified in the following format:
|
550
560
|
# `gs://bucket_name/object_name` (other URI formats return
|
551
|
-
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
|
552
|
-
# [Request
|
561
|
+
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
|
562
|
+
# For more information, see [Request
|
563
|
+
# URIs](https://cloud.google.com/storage/docs/reference-uris).
|
553
564
|
class RecognitionAudio
|
554
|
-
include Google::Protobuf::MessageExts
|
555
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
565
|
+
include ::Google::Protobuf::MessageExts
|
566
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
556
567
|
end
|
557
568
|
|
558
569
|
# The only message returned to the client by the `Recognize` method. It
|
559
570
|
# contains the result as zero or more sequential `SpeechRecognitionResult`
|
560
571
|
# messages.
|
561
572
|
# @!attribute [rw] results
|
562
|
-
# @return [Array
|
573
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechRecognitionResult>]
|
563
574
|
# Sequential list of transcription results corresponding to
|
564
575
|
# sequential portions of audio.
|
565
576
|
class RecognizeResponse
|
566
|
-
include Google::Protobuf::MessageExts
|
567
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
577
|
+
include ::Google::Protobuf::MessageExts
|
578
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
568
579
|
end
|
569
580
|
|
570
581
|
# The only message returned to the client by the `LongRunningRecognize` method.
|
@@ -573,30 +584,34 @@ module Google
|
|
573
584
|
# returned by the `GetOperation` call of the `google::longrunning::Operations`
|
574
585
|
# service.
|
575
586
|
# @!attribute [rw] results
|
576
|
-
# @return [Array
|
587
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechRecognitionResult>]
|
577
588
|
# Sequential list of transcription results corresponding to
|
578
589
|
# sequential portions of audio.
|
579
590
|
class LongRunningRecognizeResponse
|
580
|
-
include Google::Protobuf::MessageExts
|
581
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
591
|
+
include ::Google::Protobuf::MessageExts
|
592
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
582
593
|
end
|
583
594
|
|
584
595
|
# Describes the progress of a long-running `LongRunningRecognize` call. It is
|
585
596
|
# included in the `metadata` field of the `Operation` returned by the
|
586
597
|
# `GetOperation` call of the `google::longrunning::Operations` service.
|
587
598
|
# @!attribute [rw] progress_percent
|
588
|
-
# @return [Integer]
|
599
|
+
# @return [::Integer]
|
589
600
|
# Approximate percentage of audio processed thus far. Guaranteed to be 100
|
590
601
|
# when the audio is fully processed and the results are available.
|
591
602
|
# @!attribute [rw] start_time
|
592
|
-
# @return [Google::Protobuf::Timestamp]
|
603
|
+
# @return [::Google::Protobuf::Timestamp]
|
593
604
|
# Time when the request was received.
|
594
605
|
# @!attribute [rw] last_update_time
|
595
|
-
# @return [Google::Protobuf::Timestamp]
|
606
|
+
# @return [::Google::Protobuf::Timestamp]
|
596
607
|
# Time of the most recent processing update.
|
608
|
+
# @!attribute [r] uri
|
609
|
+
# @return [::String]
|
610
|
+
# The URI of the audio file being transcribed. Empty if the audio was sent
|
611
|
+
# as byte content.
|
597
612
|
class LongRunningRecognizeMetadata
|
598
|
-
include Google::Protobuf::MessageExts
|
599
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
613
|
+
include ::Google::Protobuf::MessageExts
|
614
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
600
615
|
end
|
601
616
|
|
602
617
|
# `StreamingRecognizeResponse` is the only message returned to the client by
|
@@ -649,21 +664,21 @@ module Google
|
|
649
664
|
# `speech_event_type`, or
|
650
665
|
# one or more (repeated) `results`.
|
651
666
|
# @!attribute [rw] error
|
652
|
-
# @return [Google::Rpc::Status]
|
653
|
-
# If set, returns a {Google::Rpc::Status google.rpc.Status} message that
|
667
|
+
# @return [::Google::Rpc::Status]
|
668
|
+
# If set, returns a {::Google::Rpc::Status google.rpc.Status} message that
|
654
669
|
# specifies the error for the operation.
|
655
670
|
# @!attribute [rw] results
|
656
|
-
# @return [Array
|
671
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::StreamingRecognitionResult>]
|
657
672
|
# This repeated list contains zero or more results that
|
658
673
|
# correspond to consecutive portions of the audio currently being processed.
|
659
674
|
# It contains zero or one `is_final=true` result (the newly settled portion),
|
660
675
|
# followed by zero or more `is_final=false` results (the interim results).
|
661
676
|
# @!attribute [rw] speech_event_type
|
662
|
-
# @return [Google::Cloud::Speech::V1p1beta1::StreamingRecognizeResponse::SpeechEventType]
|
677
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::StreamingRecognizeResponse::SpeechEventType]
|
663
678
|
# Indicates the type of speech event.
|
664
679
|
class StreamingRecognizeResponse
|
665
|
-
include Google::Protobuf::MessageExts
|
666
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
680
|
+
include ::Google::Protobuf::MessageExts
|
681
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
667
682
|
|
668
683
|
# Indicates the type of speech event.
|
669
684
|
module SpeechEventType
|
@@ -684,72 +699,72 @@ module Google
|
|
684
699
|
# A streaming speech recognition result corresponding to a portion of the audio
|
685
700
|
# that is currently being processed.
|
686
701
|
# @!attribute [rw] alternatives
|
687
|
-
# @return [Array
|
702
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechRecognitionAlternative>]
|
688
703
|
# May contain one or more recognition hypotheses (up to the
|
689
704
|
# maximum specified in `max_alternatives`).
|
690
705
|
# These alternatives are ordered in terms of accuracy, with the top (first)
|
691
706
|
# alternative being the most probable, as ranked by the recognizer.
|
692
707
|
# @!attribute [rw] is_final
|
693
|
-
# @return [Boolean]
|
708
|
+
# @return [::Boolean]
|
694
709
|
# If `false`, this `StreamingRecognitionResult` represents an
|
695
710
|
# interim result that may change. If `true`, this is the final time the
|
696
711
|
# speech service will return this particular `StreamingRecognitionResult`,
|
697
712
|
# the recognizer will not return any further hypotheses for this portion of
|
698
713
|
# the transcript and corresponding audio.
|
699
714
|
# @!attribute [rw] stability
|
700
|
-
# @return [Float]
|
715
|
+
# @return [::Float]
|
701
716
|
# An estimate of the likelihood that the recognizer will not
|
702
717
|
# change its guess about this interim result. Values range from 0.0
|
703
718
|
# (completely unstable) to 1.0 (completely stable).
|
704
719
|
# This field is only provided for interim results (`is_final=false`).
|
705
720
|
# The default of 0.0 is a sentinel value indicating `stability` was not set.
|
706
721
|
# @!attribute [rw] result_end_time
|
707
|
-
# @return [Google::Protobuf::Duration]
|
722
|
+
# @return [::Google::Protobuf::Duration]
|
708
723
|
# Time offset of the end of this result relative to the
|
709
724
|
# beginning of the audio.
|
710
725
|
# @!attribute [rw] channel_tag
|
711
|
-
# @return [Integer]
|
726
|
+
# @return [::Integer]
|
712
727
|
# For multi-channel audio, this is the channel number corresponding to the
|
713
728
|
# recognized result for the audio from that channel.
|
714
729
|
# For audio_channel_count = N, its output values can range from '1' to 'N'.
|
715
|
-
# @!attribute [
|
716
|
-
# @return [String]
|
717
|
-
# The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
718
|
-
# of the language in this result. This language code was
|
719
|
-
# the most likelihood of being spoken in the audio.
|
730
|
+
# @!attribute [r] language_code
|
731
|
+
# @return [::String]
|
732
|
+
# Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
733
|
+
# language tag of the language in this result. This language code was
|
734
|
+
# detected to have the most likelihood of being spoken in the audio.
|
720
735
|
class StreamingRecognitionResult
|
721
|
-
include Google::Protobuf::MessageExts
|
722
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
736
|
+
include ::Google::Protobuf::MessageExts
|
737
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
723
738
|
end
|
724
739
|
|
725
740
|
# A speech recognition result corresponding to a portion of the audio.
|
726
741
|
# @!attribute [rw] alternatives
|
727
|
-
# @return [Array
|
742
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechRecognitionAlternative>]
|
728
743
|
# May contain one or more recognition hypotheses (up to the
|
729
744
|
# maximum specified in `max_alternatives`).
|
730
745
|
# These alternatives are ordered in terms of accuracy, with the top (first)
|
731
746
|
# alternative being the most probable, as ranked by the recognizer.
|
732
747
|
# @!attribute [rw] channel_tag
|
733
|
-
# @return [Integer]
|
748
|
+
# @return [::Integer]
|
734
749
|
# For multi-channel audio, this is the channel number corresponding to the
|
735
750
|
# recognized result for the audio from that channel.
|
736
751
|
# For audio_channel_count = N, its output values can range from '1' to 'N'.
|
737
|
-
# @!attribute [
|
738
|
-
# @return [String]
|
739
|
-
# The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
740
|
-
# of the language in this result. This language code was
|
741
|
-
# the most likelihood of being spoken in the audio.
|
752
|
+
# @!attribute [r] language_code
|
753
|
+
# @return [::String]
|
754
|
+
# Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
755
|
+
# language tag of the language in this result. This language code was
|
756
|
+
# detected to have the most likelihood of being spoken in the audio.
|
742
757
|
class SpeechRecognitionResult
|
743
|
-
include Google::Protobuf::MessageExts
|
744
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
758
|
+
include ::Google::Protobuf::MessageExts
|
759
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
745
760
|
end
|
746
761
|
|
747
762
|
# Alternative hypotheses (a.k.a. n-best list).
|
748
763
|
# @!attribute [rw] transcript
|
749
|
-
# @return [String]
|
764
|
+
# @return [::String]
|
750
765
|
# Transcript text representing the words that the user spoke.
|
751
766
|
# @!attribute [rw] confidence
|
752
|
-
# @return [Float]
|
767
|
+
# @return [::Float]
|
753
768
|
# The confidence estimate between 0.0 and 1.0. A higher number
|
754
769
|
# indicates an estimated greater likelihood that the recognized words are
|
755
770
|
# correct. This field is set only for the top alternative of a non-streaming
|
@@ -758,18 +773,18 @@ module Google
|
|
758
773
|
# to be always provided.
|
759
774
|
# The default of 0.0 is a sentinel value indicating `confidence` was not set.
|
760
775
|
# @!attribute [rw] words
|
761
|
-
# @return [Array
|
776
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::WordInfo>]
|
762
777
|
# A list of word-specific information for each recognized word.
|
763
778
|
# Note: When `enable_speaker_diarization` is true, you will see all the words
|
764
779
|
# from the beginning of the audio.
|
765
780
|
class SpeechRecognitionAlternative
|
766
|
-
include Google::Protobuf::MessageExts
|
767
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
781
|
+
include ::Google::Protobuf::MessageExts
|
782
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
768
783
|
end
|
769
784
|
|
770
785
|
# Word-specific information for recognized words.
|
771
786
|
# @!attribute [rw] start_time
|
772
|
-
# @return [Google::Protobuf::Duration]
|
787
|
+
# @return [::Google::Protobuf::Duration]
|
773
788
|
# Time offset relative to the beginning of the audio,
|
774
789
|
# and corresponding to the start of the spoken word.
|
775
790
|
# This field is only set if `enable_word_time_offsets=true` and only
|
@@ -777,7 +792,7 @@ module Google
|
|
777
792
|
# This is an experimental feature and the accuracy of the time offset can
|
778
793
|
# vary.
|
779
794
|
# @!attribute [rw] end_time
|
780
|
-
# @return [Google::Protobuf::Duration]
|
795
|
+
# @return [::Google::Protobuf::Duration]
|
781
796
|
# Time offset relative to the beginning of the audio,
|
782
797
|
# and corresponding to the end of the spoken word.
|
783
798
|
# This field is only set if `enable_word_time_offsets=true` and only
|
@@ -785,10 +800,10 @@ module Google
|
|
785
800
|
# This is an experimental feature and the accuracy of the time offset can
|
786
801
|
# vary.
|
787
802
|
# @!attribute [rw] word
|
788
|
-
# @return [String]
|
803
|
+
# @return [::String]
|
789
804
|
# The word corresponding to this set of information.
|
790
805
|
# @!attribute [rw] confidence
|
791
|
-
# @return [Float]
|
806
|
+
# @return [::Float]
|
792
807
|
# The confidence estimate between 0.0 and 1.0. A higher number
|
793
808
|
# indicates an estimated greater likelihood that the recognized words are
|
794
809
|
# correct. This field is set only for the top alternative of a non-streaming
|
@@ -796,16 +811,16 @@ module Google
|
|
796
811
|
# This field is not guaranteed to be accurate and users should not rely on it
|
797
812
|
# to be always provided.
|
798
813
|
# The default of 0.0 is a sentinel value indicating `confidence` was not set.
|
799
|
-
# @!attribute [
|
800
|
-
# @return [Integer]
|
801
|
-
# A distinct integer value is assigned for every speaker within
|
814
|
+
# @!attribute [r] speaker_tag
|
815
|
+
# @return [::Integer]
|
816
|
+
# Output only. A distinct integer value is assigned for every speaker within
|
802
817
|
# the audio. This field specifies which one of those speakers was detected to
|
803
818
|
# have spoken this word. Value ranges from '1' to diarization_speaker_count.
|
804
819
|
# speaker_tag is set if enable_speaker_diarization = 'true' and only in the
|
805
820
|
# top alternative.
|
806
821
|
class WordInfo
|
807
|
-
include Google::Protobuf::MessageExts
|
808
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
822
|
+
include ::Google::Protobuf::MessageExts
|
823
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
809
824
|
end
|
810
825
|
end
|
811
826
|
end
|