google-cloud-speech-v1p1beta1 0.2.0 → 0.2.1
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/speech/client.rb +88 -88
- data/lib/google/cloud/speech/v1p1beta1/speech/credentials.rb +1 -1
- data/lib/google/cloud/speech/v1p1beta1/speech/operations.rb +100 -100
- data/lib/google/cloud/speech/v1p1beta1/speech/paths.rb +6 -6
- data/lib/google/cloud/speech/v1p1beta1/speech.rb +1 -1
- data/lib/google/cloud/speech/v1p1beta1/version.rb +1 -1
- data/lib/google/cloud/speech/v1p1beta1.rb +1 -1
- data/proto_docs/google/api/resource.rb +12 -12
- data/proto_docs/google/cloud/speech/v1p1beta1/cloud_speech.rb +109 -109
- data/proto_docs/google/cloud/speech/v1p1beta1/resource.rb +21 -21
- 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 +2 -2
@@ -35,10 +35,10 @@ module Google
|
|
35
35
|
# @param location [String]
|
36
36
|
# @param custom_class [String]
|
37
37
|
#
|
38
|
-
# @return [String]
|
38
|
+
# @return [::String]
|
39
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? "/"
|
40
|
+
raise ::ArgumentError, "project cannot contain /" if project.to_s.include? "/"
|
41
|
+
raise ::ArgumentError, "location cannot contain /" if location.to_s.include? "/"
|
42
42
|
|
43
43
|
"projects/#{project}/locations/#{location}/customClasses/#{custom_class}"
|
44
44
|
end
|
@@ -54,10 +54,10 @@ module Google
|
|
54
54
|
# @param location [String]
|
55
55
|
# @param phrase_set [String]
|
56
56
|
#
|
57
|
-
# @return [String]
|
57
|
+
# @return [::String]
|
58
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? "/"
|
59
|
+
raise ::ArgumentError, "project cannot contain /" if project.to_s.include? "/"
|
60
|
+
raise ::ArgumentError, "location cannot contain /" if location.to_s.include? "/"
|
61
61
|
|
62
62
|
"projects/#{project}/locations/#{location}/phraseSets/#{phrase_set}"
|
63
63
|
end
|
@@ -37,7 +37,7 @@ module Google
|
|
37
37
|
# To load this service and instantiate a client:
|
38
38
|
#
|
39
39
|
# require "google/cloud/speech/v1p1beta1/speech"
|
40
|
-
# client = Google::Cloud::Speech::V1p1beta1::Speech::Client.new
|
40
|
+
# client = ::Google::Cloud::Speech::V1p1beta1::Speech::Client.new
|
41
41
|
#
|
42
42
|
module Speech
|
43
43
|
end
|
@@ -26,7 +26,7 @@ module Google
|
|
26
26
|
# To load this package, including all its services, and instantiate a client:
|
27
27
|
#
|
28
28
|
# require "google/cloud/speech/v1p1beta1"
|
29
|
-
# client = Google::Cloud::Speech::V1p1beta1::Speech::Client.new
|
29
|
+
# client = ::Google::Cloud::Speech::V1p1beta1::Speech::Client.new
|
30
30
|
#
|
31
31
|
module V1p1beta1
|
32
32
|
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
|
@@ -93,26 +93,26 @@ 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
112
|
# for all other audio formats. For details, see
|
113
|
-
# {Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
|
113
|
+
# {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
|
114
114
|
# @!attribute [rw] sample_rate_hertz
|
115
|
-
# @return [Integer]
|
115
|
+
# @return [::Integer]
|
116
116
|
# Sample rate in Hertz of the audio data sent in all
|
117
117
|
# `RecognitionAudio` messages. Valid values are: 8000-48000.
|
118
118
|
# 16000 is optimal. For best results, set the sampling rate of the audio
|
@@ -120,9 +120,9 @@ module Google
|
|
120
120
|
# the audio source (instead of re-sampling).
|
121
121
|
# This field is optional for FLAC and WAV audio files, but is
|
122
122
|
# required for all other audio formats. For details, see
|
123
|
-
# {Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
|
123
|
+
# {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
|
124
124
|
# @!attribute [rw] audio_channel_count
|
125
|
-
# @return [Integer]
|
125
|
+
# @return [::Integer]
|
126
126
|
# The number of channels in the input audio data.
|
127
127
|
# ONLY set this for MULTI-CHANNEL recognition.
|
128
128
|
# Valid values for LINEAR16 and FLAC are `1`-`8`.
|
@@ -133,7 +133,7 @@ module Google
|
|
133
133
|
# To perform independent recognition on each channel set
|
134
134
|
# `enable_separate_recognition_per_channel` to 'true'.
|
135
135
|
# @!attribute [rw] enable_separate_recognition_per_channel
|
136
|
-
# @return [Boolean]
|
136
|
+
# @return [::Boolean]
|
137
137
|
# This needs to be set to `true` explicitly and `audio_channel_count` > 1
|
138
138
|
# to get each channel recognized separately. The recognition result will
|
139
139
|
# contain a `channel_tag` field to state which channel that result belongs
|
@@ -141,7 +141,7 @@ module Google
|
|
141
141
|
# request is billed cumulatively for all channels recognized:
|
142
142
|
# `audio_channel_count` multiplied by the length of the audio.
|
143
143
|
# @!attribute [rw] language_code
|
144
|
-
# @return [String]
|
144
|
+
# @return [::String]
|
145
145
|
# Required. The language of the supplied audio as a
|
146
146
|
# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
|
147
147
|
# Example: "en-US".
|
@@ -149,7 +149,7 @@ module Google
|
|
149
149
|
# Support](https://cloud.google.com/speech-to-text/docs/languages) for a list
|
150
150
|
# of the currently supported language codes.
|
151
151
|
# @!attribute [rw] alternative_language_codes
|
152
|
-
# @return [Array
|
152
|
+
# @return [::Array<::String>]
|
153
153
|
# A list of up to 3 additional
|
154
154
|
# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
|
155
155
|
# listing possible alternative languages of the supplied audio.
|
@@ -163,7 +163,7 @@ module Google
|
|
163
163
|
# and performance may vary for other use cases (e.g., phone call
|
164
164
|
# transcription).
|
165
165
|
# @!attribute [rw] max_alternatives
|
166
|
-
# @return [Integer]
|
166
|
+
# @return [::Integer]
|
167
167
|
# Maximum number of recognition hypotheses to be returned.
|
168
168
|
# Specifically, the maximum number of `SpeechRecognitionAlternative` messages
|
169
169
|
# within each `SpeechRecognitionResult`.
|
@@ -171,55 +171,55 @@ module Google
|
|
171
171
|
# Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of
|
172
172
|
# one. If omitted, will return a maximum of one.
|
173
173
|
# @!attribute [rw] profanity_filter
|
174
|
-
# @return [Boolean]
|
174
|
+
# @return [::Boolean]
|
175
175
|
# If set to `true`, the server will attempt to filter out
|
176
176
|
# profanities, replacing all but the initial character in each filtered word
|
177
177
|
# with asterisks, e.g. "f***". If set to `false` or omitted, profanities
|
178
178
|
# won't be filtered out.
|
179
179
|
# @!attribute [rw] adaptation
|
180
|
-
# @return [Google::Cloud::Speech::V1p1beta1::SpeechAdaptation]
|
180
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::SpeechAdaptation]
|
181
181
|
# Speech adaptation configuration improves the accuracy of speech
|
182
182
|
# recognition. When speech adaptation is set it supersedes the
|
183
183
|
# `speech_contexts` field. For more information, see the [speech
|
184
184
|
# adaptation](https://cloud.google.com/speech-to-text/docs/context-strength)
|
185
185
|
# documentation.
|
186
186
|
# @!attribute [rw] speech_contexts
|
187
|
-
# @return [Array
|
188
|
-
# 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}.
|
189
189
|
# A means to provide context to assist the speech recognition. For more
|
190
190
|
# information, see
|
191
191
|
# [speech
|
192
192
|
# adaptation](https://cloud.google.com/speech-to-text/docs/context-strength).
|
193
193
|
# @!attribute [rw] enable_word_time_offsets
|
194
|
-
# @return [Boolean]
|
194
|
+
# @return [::Boolean]
|
195
195
|
# If `true`, the top result includes a list of words and
|
196
196
|
# the start and end time offsets (timestamps) for those words. If
|
197
197
|
# `false`, no word-level time offset information is returned. The default is
|
198
198
|
# `false`.
|
199
199
|
# @!attribute [rw] enable_word_confidence
|
200
|
-
# @return [Boolean]
|
200
|
+
# @return [::Boolean]
|
201
201
|
# If `true`, the top result includes a list of words and the
|
202
202
|
# confidence for those words. If `false`, no word-level confidence
|
203
203
|
# information is returned. The default is `false`.
|
204
204
|
# @!attribute [rw] enable_automatic_punctuation
|
205
|
-
# @return [Boolean]
|
205
|
+
# @return [::Boolean]
|
206
206
|
# If 'true', adds punctuation to recognition result hypotheses.
|
207
207
|
# This feature is only available in select languages. Setting this for
|
208
208
|
# requests in other languages has no effect at all.
|
209
209
|
# The default 'false' value does not add punctuation to result hypotheses.
|
210
210
|
# @!attribute [rw] enable_speaker_diarization
|
211
|
-
# @return [Boolean]
|
211
|
+
# @return [::Boolean]
|
212
212
|
# If 'true', enables speaker detection for each recognized word in
|
213
213
|
# the top alternative of the recognition result using a speaker_tag provided
|
214
214
|
# in the WordInfo.
|
215
215
|
# Note: Use diarization_config instead.
|
216
216
|
# @!attribute [rw] diarization_speaker_count
|
217
|
-
# @return [Integer]
|
217
|
+
# @return [::Integer]
|
218
218
|
# If set, specifies the estimated number of speakers in the conversation.
|
219
219
|
# Defaults to '2'. Ignored unless enable_speaker_diarization is set to true.
|
220
220
|
# Note: Use diarization_config instead.
|
221
221
|
# @!attribute [rw] diarization_config
|
222
|
-
# @return [Google::Cloud::Speech::V1p1beta1::SpeakerDiarizationConfig]
|
222
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::SpeakerDiarizationConfig]
|
223
223
|
# Config to enable speaker diarization and set additional
|
224
224
|
# parameters to make diarization better suited for your application.
|
225
225
|
# Note: When this is enabled, we send all the words from the beginning of the
|
@@ -229,10 +229,10 @@ module Google
|
|
229
229
|
# For non-streaming requests, the diarization results will be provided only
|
230
230
|
# in the top alternative of the FINAL SpeechRecognitionResult.
|
231
231
|
# @!attribute [rw] metadata
|
232
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata]
|
232
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata]
|
233
233
|
# Metadata regarding this request.
|
234
234
|
# @!attribute [rw] model
|
235
|
-
# @return [String]
|
235
|
+
# @return [::String]
|
236
236
|
# Which model to select for the given request. Select the model
|
237
237
|
# best suited to your domain to get best results. If a model is not
|
238
238
|
# explicitly specified, then we auto-select a model based on the parameters
|
@@ -266,7 +266,7 @@ module Google
|
|
266
266
|
# </tr>
|
267
267
|
# </table>
|
268
268
|
# @!attribute [rw] use_enhanced
|
269
|
-
# @return [Boolean]
|
269
|
+
# @return [::Boolean]
|
270
270
|
# Set to true to use an enhanced model for speech recognition.
|
271
271
|
# If `use_enhanced` is set to true and the `model` field is not set, then
|
272
272
|
# an appropriate enhanced model is chosen if an enhanced model exists for
|
@@ -276,8 +276,8 @@ module Google
|
|
276
276
|
# does not exist, then the speech is recognized using the standard version
|
277
277
|
# of the specified model.
|
278
278
|
class RecognitionConfig
|
279
|
-
include Google::Protobuf::MessageExts
|
280
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
279
|
+
include ::Google::Protobuf::MessageExts
|
280
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
281
281
|
|
282
282
|
# The encoding of the audio data sent in the request.
|
283
283
|
#
|
@@ -355,69 +355,69 @@ module Google
|
|
355
355
|
|
356
356
|
# Config to enable speaker diarization.
|
357
357
|
# @!attribute [rw] enable_speaker_diarization
|
358
|
-
# @return [Boolean]
|
358
|
+
# @return [::Boolean]
|
359
359
|
# If 'true', enables speaker detection for each recognized word in
|
360
360
|
# the top alternative of the recognition result using a speaker_tag provided
|
361
361
|
# in the WordInfo.
|
362
362
|
# @!attribute [rw] min_speaker_count
|
363
|
-
# @return [Integer]
|
363
|
+
# @return [::Integer]
|
364
364
|
# Minimum number of speakers in the conversation. This range gives you more
|
365
365
|
# flexibility by allowing the system to automatically determine the correct
|
366
366
|
# number of speakers. If not set, the default value is 2.
|
367
367
|
# @!attribute [rw] max_speaker_count
|
368
|
-
# @return [Integer]
|
368
|
+
# @return [::Integer]
|
369
369
|
# Maximum number of speakers in the conversation. This range gives you more
|
370
370
|
# flexibility by allowing the system to automatically determine the correct
|
371
371
|
# number of speakers. If not set, the default value is 6.
|
372
372
|
# @!attribute [r] speaker_tag
|
373
|
-
# @return [Integer]
|
373
|
+
# @return [::Integer]
|
374
374
|
# Output only. Unused.
|
375
375
|
class SpeakerDiarizationConfig
|
376
|
-
include Google::Protobuf::MessageExts
|
377
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
376
|
+
include ::Google::Protobuf::MessageExts
|
377
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
378
378
|
end
|
379
379
|
|
380
380
|
# Description of audio data to be recognized.
|
381
381
|
# @!attribute [rw] interaction_type
|
382
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::InteractionType]
|
382
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::InteractionType]
|
383
383
|
# The use case most closely describing the audio content to be recognized.
|
384
384
|
# @!attribute [rw] industry_naics_code_of_audio
|
385
|
-
# @return [Integer]
|
385
|
+
# @return [::Integer]
|
386
386
|
# The industry vertical to which this speech recognition request most
|
387
387
|
# closely applies. This is most indicative of the topics contained
|
388
388
|
# in the audio. Use the 6-digit NAICS code to identify the industry
|
389
389
|
# vertical - see https://www.naics.com/search/.
|
390
390
|
# @!attribute [rw] microphone_distance
|
391
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::MicrophoneDistance]
|
391
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::MicrophoneDistance]
|
392
392
|
# The audio type that most closely describes the audio being recognized.
|
393
393
|
# @!attribute [rw] original_media_type
|
394
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::OriginalMediaType]
|
394
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::OriginalMediaType]
|
395
395
|
# The original media the speech was recorded on.
|
396
396
|
# @!attribute [rw] recording_device_type
|
397
|
-
# @return [Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::RecordingDeviceType]
|
397
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionMetadata::RecordingDeviceType]
|
398
398
|
# The type of device the speech was recorded with.
|
399
399
|
# @!attribute [rw] recording_device_name
|
400
|
-
# @return [String]
|
400
|
+
# @return [::String]
|
401
401
|
# The device used to make the recording. Examples 'Nexus 5X' or
|
402
402
|
# 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
|
403
403
|
# 'Cardioid Microphone'.
|
404
404
|
# @!attribute [rw] original_mime_type
|
405
|
-
# @return [String]
|
405
|
+
# @return [::String]
|
406
406
|
# Mime type of the original audio file. For example `audio/m4a`,
|
407
407
|
# `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`.
|
408
408
|
# A list of possible audio mime types is maintained at
|
409
409
|
# http://www.iana.org/assignments/media-types/media-types.xhtml#audio
|
410
410
|
# @!attribute [rw] obfuscated_id
|
411
|
-
# @return [Integer]
|
411
|
+
# @return [::Integer]
|
412
412
|
# Obfuscated (privacy-protected) ID of the user, to identify number of
|
413
413
|
# unique users using the service.
|
414
414
|
# @!attribute [rw] audio_topic
|
415
|
-
# @return [String]
|
415
|
+
# @return [::String]
|
416
416
|
# Description of the content. Eg. "Recordings of federal supreme court
|
417
417
|
# hearings from 2012".
|
418
418
|
class RecognitionMetadata
|
419
|
-
include Google::Protobuf::MessageExts
|
420
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
419
|
+
include ::Google::Protobuf::MessageExts
|
420
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
421
421
|
|
422
422
|
# Use case categories that the audio recognition request can be described
|
423
423
|
# by.
|
@@ -514,7 +514,7 @@ module Google
|
|
514
514
|
# Provides "hints" to the speech recognizer to favor specific words and phrases
|
515
515
|
# in the results.
|
516
516
|
# @!attribute [rw] phrases
|
517
|
-
# @return [Array
|
517
|
+
# @return [::Array<::String>]
|
518
518
|
# A list of strings containing words and phrases "hints" so that
|
519
519
|
# the speech recognition is more likely to recognize them. This can be used
|
520
520
|
# to improve the accuracy for specific words and phrases, for example, if
|
@@ -528,7 +528,7 @@ module Google
|
|
528
528
|
# improves the likelihood of correctly transcribing audio that includes
|
529
529
|
# months.
|
530
530
|
# @!attribute [rw] boost
|
531
|
-
# @return [Float]
|
531
|
+
# @return [::Float]
|
532
532
|
# Hint Boost. Positive value will increase the probability that a specific
|
533
533
|
# phrase will be recognized over other similar sounding phrases. The higher
|
534
534
|
# the boost, the higher the chance of false positive recognition as well.
|
@@ -538,8 +538,8 @@ module Google
|
|
538
538
|
# values between 0 and 20. We recommend using a binary search approach to
|
539
539
|
# finding the optimal value for your use case.
|
540
540
|
class SpeechContext
|
541
|
-
include Google::Protobuf::MessageExts
|
542
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
541
|
+
include ::Google::Protobuf::MessageExts
|
542
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
543
543
|
end
|
544
544
|
|
545
545
|
# Contains audio data in the encoding specified in the `RecognitionConfig`.
|
@@ -547,12 +547,12 @@ module Google
|
|
547
547
|
# returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
|
548
548
|
# See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
|
549
549
|
# @!attribute [rw] content
|
550
|
-
# @return [String]
|
550
|
+
# @return [::String]
|
551
551
|
# The audio data bytes encoded as specified in
|
552
552
|
# `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a
|
553
553
|
# pure binary representation, whereas JSON representations use base64.
|
554
554
|
# @!attribute [rw] uri
|
555
|
-
# @return [String]
|
555
|
+
# @return [::String]
|
556
556
|
# URI that points to a file that contains audio data bytes as specified in
|
557
557
|
# `RecognitionConfig`. The file must not be compressed (for example, gzip).
|
558
558
|
# Currently, only Google Cloud Storage URIs are
|
@@ -562,20 +562,20 @@ module Google
|
|
562
562
|
# For more information, see [Request
|
563
563
|
# URIs](https://cloud.google.com/storage/docs/reference-uris).
|
564
564
|
class RecognitionAudio
|
565
|
-
include Google::Protobuf::MessageExts
|
566
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
565
|
+
include ::Google::Protobuf::MessageExts
|
566
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
567
567
|
end
|
568
568
|
|
569
569
|
# The only message returned to the client by the `Recognize` method. It
|
570
570
|
# contains the result as zero or more sequential `SpeechRecognitionResult`
|
571
571
|
# messages.
|
572
572
|
# @!attribute [rw] results
|
573
|
-
# @return [Array
|
573
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechRecognitionResult>]
|
574
574
|
# Sequential list of transcription results corresponding to
|
575
575
|
# sequential portions of audio.
|
576
576
|
class RecognizeResponse
|
577
|
-
include Google::Protobuf::MessageExts
|
578
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
577
|
+
include ::Google::Protobuf::MessageExts
|
578
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
579
579
|
end
|
580
580
|
|
581
581
|
# The only message returned to the client by the `LongRunningRecognize` method.
|
@@ -584,34 +584,34 @@ module Google
|
|
584
584
|
# returned by the `GetOperation` call of the `google::longrunning::Operations`
|
585
585
|
# service.
|
586
586
|
# @!attribute [rw] results
|
587
|
-
# @return [Array
|
587
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechRecognitionResult>]
|
588
588
|
# Sequential list of transcription results corresponding to
|
589
589
|
# sequential portions of audio.
|
590
590
|
class LongRunningRecognizeResponse
|
591
|
-
include Google::Protobuf::MessageExts
|
592
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
591
|
+
include ::Google::Protobuf::MessageExts
|
592
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
593
593
|
end
|
594
594
|
|
595
595
|
# Describes the progress of a long-running `LongRunningRecognize` call. It is
|
596
596
|
# included in the `metadata` field of the `Operation` returned by the
|
597
597
|
# `GetOperation` call of the `google::longrunning::Operations` service.
|
598
598
|
# @!attribute [rw] progress_percent
|
599
|
-
# @return [Integer]
|
599
|
+
# @return [::Integer]
|
600
600
|
# Approximate percentage of audio processed thus far. Guaranteed to be 100
|
601
601
|
# when the audio is fully processed and the results are available.
|
602
602
|
# @!attribute [rw] start_time
|
603
|
-
# @return [Google::Protobuf::Timestamp]
|
603
|
+
# @return [::Google::Protobuf::Timestamp]
|
604
604
|
# Time when the request was received.
|
605
605
|
# @!attribute [rw] last_update_time
|
606
|
-
# @return [Google::Protobuf::Timestamp]
|
606
|
+
# @return [::Google::Protobuf::Timestamp]
|
607
607
|
# Time of the most recent processing update.
|
608
608
|
# @!attribute [r] uri
|
609
|
-
# @return [String]
|
609
|
+
# @return [::String]
|
610
610
|
# The URI of the audio file being transcribed. Empty if the audio was sent
|
611
611
|
# as byte content.
|
612
612
|
class LongRunningRecognizeMetadata
|
613
|
-
include Google::Protobuf::MessageExts
|
614
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
613
|
+
include ::Google::Protobuf::MessageExts
|
614
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
615
615
|
end
|
616
616
|
|
617
617
|
# `StreamingRecognizeResponse` is the only message returned to the client by
|
@@ -664,21 +664,21 @@ module Google
|
|
664
664
|
# `speech_event_type`, or
|
665
665
|
# one or more (repeated) `results`.
|
666
666
|
# @!attribute [rw] error
|
667
|
-
# @return [Google::Rpc::Status]
|
668
|
-
# 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
|
669
669
|
# specifies the error for the operation.
|
670
670
|
# @!attribute [rw] results
|
671
|
-
# @return [Array
|
671
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::StreamingRecognitionResult>]
|
672
672
|
# This repeated list contains zero or more results that
|
673
673
|
# correspond to consecutive portions of the audio currently being processed.
|
674
674
|
# It contains zero or one `is_final=true` result (the newly settled portion),
|
675
675
|
# followed by zero or more `is_final=false` results (the interim results).
|
676
676
|
# @!attribute [rw] speech_event_type
|
677
|
-
# @return [Google::Cloud::Speech::V1p1beta1::StreamingRecognizeResponse::SpeechEventType]
|
677
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::StreamingRecognizeResponse::SpeechEventType]
|
678
678
|
# Indicates the type of speech event.
|
679
679
|
class StreamingRecognizeResponse
|
680
|
-
include Google::Protobuf::MessageExts
|
681
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
680
|
+
include ::Google::Protobuf::MessageExts
|
681
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
682
682
|
|
683
683
|
# Indicates the type of speech event.
|
684
684
|
module SpeechEventType
|
@@ -699,72 +699,72 @@ module Google
|
|
699
699
|
# A streaming speech recognition result corresponding to a portion of the audio
|
700
700
|
# that is currently being processed.
|
701
701
|
# @!attribute [rw] alternatives
|
702
|
-
# @return [Array
|
702
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechRecognitionAlternative>]
|
703
703
|
# May contain one or more recognition hypotheses (up to the
|
704
704
|
# maximum specified in `max_alternatives`).
|
705
705
|
# These alternatives are ordered in terms of accuracy, with the top (first)
|
706
706
|
# alternative being the most probable, as ranked by the recognizer.
|
707
707
|
# @!attribute [rw] is_final
|
708
|
-
# @return [Boolean]
|
708
|
+
# @return [::Boolean]
|
709
709
|
# If `false`, this `StreamingRecognitionResult` represents an
|
710
710
|
# interim result that may change. If `true`, this is the final time the
|
711
711
|
# speech service will return this particular `StreamingRecognitionResult`,
|
712
712
|
# the recognizer will not return any further hypotheses for this portion of
|
713
713
|
# the transcript and corresponding audio.
|
714
714
|
# @!attribute [rw] stability
|
715
|
-
# @return [Float]
|
715
|
+
# @return [::Float]
|
716
716
|
# An estimate of the likelihood that the recognizer will not
|
717
717
|
# change its guess about this interim result. Values range from 0.0
|
718
718
|
# (completely unstable) to 1.0 (completely stable).
|
719
719
|
# This field is only provided for interim results (`is_final=false`).
|
720
720
|
# The default of 0.0 is a sentinel value indicating `stability` was not set.
|
721
721
|
# @!attribute [rw] result_end_time
|
722
|
-
# @return [Google::Protobuf::Duration]
|
722
|
+
# @return [::Google::Protobuf::Duration]
|
723
723
|
# Time offset of the end of this result relative to the
|
724
724
|
# beginning of the audio.
|
725
725
|
# @!attribute [rw] channel_tag
|
726
|
-
# @return [Integer]
|
726
|
+
# @return [::Integer]
|
727
727
|
# For multi-channel audio, this is the channel number corresponding to the
|
728
728
|
# recognized result for the audio from that channel.
|
729
729
|
# For audio_channel_count = N, its output values can range from '1' to 'N'.
|
730
730
|
# @!attribute [r] language_code
|
731
|
-
# @return [String]
|
731
|
+
# @return [::String]
|
732
732
|
# Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
733
733
|
# language tag of the language in this result. This language code was
|
734
734
|
# detected to have the most likelihood of being spoken in the audio.
|
735
735
|
class StreamingRecognitionResult
|
736
|
-
include Google::Protobuf::MessageExts
|
737
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
736
|
+
include ::Google::Protobuf::MessageExts
|
737
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
738
738
|
end
|
739
739
|
|
740
740
|
# A speech recognition result corresponding to a portion of the audio.
|
741
741
|
# @!attribute [rw] alternatives
|
742
|
-
# @return [Array
|
742
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::SpeechRecognitionAlternative>]
|
743
743
|
# May contain one or more recognition hypotheses (up to the
|
744
744
|
# maximum specified in `max_alternatives`).
|
745
745
|
# These alternatives are ordered in terms of accuracy, with the top (first)
|
746
746
|
# alternative being the most probable, as ranked by the recognizer.
|
747
747
|
# @!attribute [rw] channel_tag
|
748
|
-
# @return [Integer]
|
748
|
+
# @return [::Integer]
|
749
749
|
# For multi-channel audio, this is the channel number corresponding to the
|
750
750
|
# recognized result for the audio from that channel.
|
751
751
|
# For audio_channel_count = N, its output values can range from '1' to 'N'.
|
752
752
|
# @!attribute [r] language_code
|
753
|
-
# @return [String]
|
753
|
+
# @return [::String]
|
754
754
|
# Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
755
755
|
# language tag of the language in this result. This language code was
|
756
756
|
# detected to have the most likelihood of being spoken in the audio.
|
757
757
|
class SpeechRecognitionResult
|
758
|
-
include Google::Protobuf::MessageExts
|
759
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
758
|
+
include ::Google::Protobuf::MessageExts
|
759
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
760
760
|
end
|
761
761
|
|
762
762
|
# Alternative hypotheses (a.k.a. n-best list).
|
763
763
|
# @!attribute [rw] transcript
|
764
|
-
# @return [String]
|
764
|
+
# @return [::String]
|
765
765
|
# Transcript text representing the words that the user spoke.
|
766
766
|
# @!attribute [rw] confidence
|
767
|
-
# @return [Float]
|
767
|
+
# @return [::Float]
|
768
768
|
# The confidence estimate between 0.0 and 1.0. A higher number
|
769
769
|
# indicates an estimated greater likelihood that the recognized words are
|
770
770
|
# correct. This field is set only for the top alternative of a non-streaming
|
@@ -773,18 +773,18 @@ module Google
|
|
773
773
|
# to be always provided.
|
774
774
|
# The default of 0.0 is a sentinel value indicating `confidence` was not set.
|
775
775
|
# @!attribute [rw] words
|
776
|
-
# @return [Array
|
776
|
+
# @return [::Array<::Google::Cloud::Speech::V1p1beta1::WordInfo>]
|
777
777
|
# A list of word-specific information for each recognized word.
|
778
778
|
# Note: When `enable_speaker_diarization` is true, you will see all the words
|
779
779
|
# from the beginning of the audio.
|
780
780
|
class SpeechRecognitionAlternative
|
781
|
-
include Google::Protobuf::MessageExts
|
782
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
781
|
+
include ::Google::Protobuf::MessageExts
|
782
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
783
783
|
end
|
784
784
|
|
785
785
|
# Word-specific information for recognized words.
|
786
786
|
# @!attribute [rw] start_time
|
787
|
-
# @return [Google::Protobuf::Duration]
|
787
|
+
# @return [::Google::Protobuf::Duration]
|
788
788
|
# Time offset relative to the beginning of the audio,
|
789
789
|
# and corresponding to the start of the spoken word.
|
790
790
|
# This field is only set if `enable_word_time_offsets=true` and only
|
@@ -792,7 +792,7 @@ module Google
|
|
792
792
|
# This is an experimental feature and the accuracy of the time offset can
|
793
793
|
# vary.
|
794
794
|
# @!attribute [rw] end_time
|
795
|
-
# @return [Google::Protobuf::Duration]
|
795
|
+
# @return [::Google::Protobuf::Duration]
|
796
796
|
# Time offset relative to the beginning of the audio,
|
797
797
|
# and corresponding to the end of the spoken word.
|
798
798
|
# This field is only set if `enable_word_time_offsets=true` and only
|
@@ -800,10 +800,10 @@ module Google
|
|
800
800
|
# This is an experimental feature and the accuracy of the time offset can
|
801
801
|
# vary.
|
802
802
|
# @!attribute [rw] word
|
803
|
-
# @return [String]
|
803
|
+
# @return [::String]
|
804
804
|
# The word corresponding to this set of information.
|
805
805
|
# @!attribute [rw] confidence
|
806
|
-
# @return [Float]
|
806
|
+
# @return [::Float]
|
807
807
|
# The confidence estimate between 0.0 and 1.0. A higher number
|
808
808
|
# indicates an estimated greater likelihood that the recognized words are
|
809
809
|
# correct. This field is set only for the top alternative of a non-streaming
|
@@ -812,15 +812,15 @@ module Google
|
|
812
812
|
# to be always provided.
|
813
813
|
# The default of 0.0 is a sentinel value indicating `confidence` was not set.
|
814
814
|
# @!attribute [r] speaker_tag
|
815
|
-
# @return [Integer]
|
815
|
+
# @return [::Integer]
|
816
816
|
# Output only. A distinct integer value is assigned for every speaker within
|
817
817
|
# the audio. This field specifies which one of those speakers was detected to
|
818
818
|
# have spoken this word. Value ranges from '1' to diarization_speaker_count.
|
819
819
|
# speaker_tag is set if enable_speaker_diarization = 'true' and only in the
|
820
820
|
# top alternative.
|
821
821
|
class WordInfo
|
822
|
-
include Google::Protobuf::MessageExts
|
823
|
-
extend Google::Protobuf::MessageExts::ClassMethods
|
822
|
+
include ::Google::Protobuf::MessageExts
|
823
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
824
824
|
end
|
825
825
|
end
|
826
826
|
end
|