google-cloud-speech-v1p1beta1 0.16.0 → 0.17.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +2 -2
- data/lib/google/cloud/speech/v1p1beta1/adaptation/client.rb +3 -3
- data/lib/google/cloud/speech/v1p1beta1/adaptation/rest/client.rb +3 -3
- data/lib/google/cloud/speech/v1p1beta1/cloud_speech_pb.rb +11 -0
- data/lib/google/cloud/speech/v1p1beta1/speech/client.rb +2 -2
- data/lib/google/cloud/speech/v1p1beta1/speech/operations.rb +2 -2
- data/lib/google/cloud/speech/v1p1beta1/speech/rest/client.rb +2 -2
- data/lib/google/cloud/speech/v1p1beta1/speech/rest/operations.rb +2 -2
- data/lib/google/cloud/speech/v1p1beta1/version.rb +1 -1
- data/proto_docs/google/api/client.rb +9 -3
- data/proto_docs/google/cloud/speech/v1p1beta1/cloud_speech.rb +62 -16
- data/proto_docs/google/cloud/speech/v1p1beta1/cloud_speech_adaptation.rb +1 -1
- metadata +5 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3a9a31ae4c03e0de70e4d30aff8741a132cfeec7a0477f7e24dfaa38ea686b99
|
4
|
+
data.tar.gz: eb7850c2b84633d7040034cc86b9bd87855856cf06e0bbd44194e8124afaee4a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 207dc537df35fca8abe841f31a1c92cefc60490f15024bbd85356778eacc4c8b01b80c9dbe3631b4474f6245ad00c386ec466bed161513dba8b26f469d895ade
|
7
|
+
data.tar.gz: 1bf1eeac4ebcccb17af7c6476223aab9218f182a0ab9b92983e305cd5f93aa94d8b9d521aa0dc3ff5ad11f34f8222219c68f639c26d65d2517a526e9c6fe3e54
|
data/README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
# Ruby Client for the Cloud Speech-to-Text V1p1beta1 API
|
2
2
|
|
3
|
-
|
3
|
+
Converts audio to text by applying powerful neural network models.
|
4
4
|
|
5
5
|
Google Speech-to-Text enables developers to convert audio to text by applying powerful neural network models in an easy-to-use API. The API recognizes more than 120 languages and variants to support your global user base. You can enable voice command-and-control, transcribe audio from call centers, and more. It can process real-time streaming or prerecorded audio, using Google's machine learning technology.
|
6
6
|
|
@@ -47,7 +47,7 @@ for general usage information.
|
|
47
47
|
|
48
48
|
To enable logging for this library, set the logger for the underlying [gRPC](https://github.com/grpc/grpc/tree/master/src/ruby) library.
|
49
49
|
The logger that you set may be a Ruby stdlib [`Logger`](https://ruby-doc.org/current/stdlibs/logger/Logger.html) as shown below,
|
50
|
-
or a [`Google::Cloud::Logging::Logger`](https://
|
50
|
+
or a [`Google::Cloud::Logging::Logger`](https://cloud.google.com/ruby/docs/reference/google-cloud-logging/latest)
|
51
51
|
that will write logs to [Cloud Logging](https://cloud.google.com/logging/). See [grpc/logconfig.rb](https://github.com/grpc/grpc/blob/master/src/ruby/lib/grpc/logconfig.rb)
|
52
52
|
and the gRPC [spec_helper.rb](https://github.com/grpc/grpc/blob/master/src/ruby/spec/spec_helper.rb) for additional information.
|
53
53
|
|
@@ -168,7 +168,7 @@ module Google
|
|
168
168
|
# Required. The parent resource where this phrase set will be created.
|
169
169
|
# Format:
|
170
170
|
#
|
171
|
-
# `projects/{project}/locations/{location}
|
171
|
+
# `projects/{project}/locations/{location}`
|
172
172
|
#
|
173
173
|
# Speech-to-Text supports three locations: `global`, `us` (US North America),
|
174
174
|
# and `eu` (Europe). If you are calling the `speech.googleapis.com`
|
@@ -1162,9 +1162,9 @@ module Google
|
|
1162
1162
|
# * (`String`) The path to a service account key file in JSON format
|
1163
1163
|
# * (`Hash`) A service account key as a Hash
|
1164
1164
|
# * (`Google::Auth::Credentials`) A googleauth credentials object
|
1165
|
-
# (see the [googleauth docs](https://
|
1165
|
+
# (see the [googleauth docs](https://rubydoc.info/gems/googleauth/Google/Auth/Credentials))
|
1166
1166
|
# * (`Signet::OAuth2::Client`) A signet oauth2 client object
|
1167
|
-
# (see the [signet docs](https://
|
1167
|
+
# (see the [signet docs](https://rubydoc.info/gems/signet/Signet/OAuth2/Client))
|
1168
1168
|
# * (`GRPC::Core::Channel`) a gRPC channel with included credentials
|
1169
1169
|
# * (`GRPC::Core::ChannelCredentials`) a gRPC credentails object
|
1170
1170
|
# * (`nil`) indicating no credentials
|
@@ -159,7 +159,7 @@ module Google
|
|
159
159
|
# Required. The parent resource where this phrase set will be created.
|
160
160
|
# Format:
|
161
161
|
#
|
162
|
-
# `projects/{project}/locations/{location}
|
162
|
+
# `projects/{project}/locations/{location}`
|
163
163
|
#
|
164
164
|
# Speech-to-Text supports three locations: `global`, `us` (US North America),
|
165
165
|
# and `eu` (Europe). If you are calling the `speech.googleapis.com`
|
@@ -915,9 +915,9 @@ module Google
|
|
915
915
|
# * (`String`) The path to a service account key file in JSON format
|
916
916
|
# * (`Hash`) A service account key as a Hash
|
917
917
|
# * (`Google::Auth::Credentials`) A googleauth credentials object
|
918
|
-
# (see the [googleauth docs](https://
|
918
|
+
# (see the [googleauth docs](https://rubydoc.info/gems/googleauth/Google/Auth/Credentials))
|
919
919
|
# * (`Signet::OAuth2::Client`) A signet oauth2 client object
|
920
|
-
# (see the [signet docs](https://
|
920
|
+
# (see the [signet docs](https://rubydoc.info/gems/signet/Signet/OAuth2/Client))
|
921
921
|
# * (`nil`) indicating no credentials
|
922
922
|
# @return [::Object]
|
923
923
|
# @!attribute [rw] scope
|
@@ -39,6 +39,12 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
|
|
39
39
|
optional :config, :message, 1, "google.cloud.speech.v1p1beta1.RecognitionConfig"
|
40
40
|
optional :single_utterance, :bool, 2
|
41
41
|
optional :interim_results, :bool, 3
|
42
|
+
optional :enable_voice_activity_events, :bool, 5
|
43
|
+
optional :voice_activity_timeout, :message, 6, "google.cloud.speech.v1p1beta1.StreamingRecognitionConfig.VoiceActivityTimeout"
|
44
|
+
end
|
45
|
+
add_message "google.cloud.speech.v1p1beta1.StreamingRecognitionConfig.VoiceActivityTimeout" do
|
46
|
+
optional :speech_start_timeout, :message, 1, "google.protobuf.Duration"
|
47
|
+
optional :speech_end_timeout, :message, 2, "google.protobuf.Duration"
|
42
48
|
end
|
43
49
|
add_message "google.cloud.speech.v1p1beta1.RecognitionConfig" do
|
44
50
|
optional :encoding, :enum, 1, "google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding"
|
@@ -159,6 +165,7 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
|
|
159
165
|
optional :error, :message, 1, "google.rpc.Status"
|
160
166
|
repeated :results, :message, 2, "google.cloud.speech.v1p1beta1.StreamingRecognitionResult"
|
161
167
|
optional :speech_event_type, :enum, 4, "google.cloud.speech.v1p1beta1.StreamingRecognizeResponse.SpeechEventType"
|
168
|
+
optional :speech_event_time, :message, 8, "google.protobuf.Duration"
|
162
169
|
optional :total_billed_time, :message, 5, "google.protobuf.Duration"
|
163
170
|
optional :speech_adaptation_info, :message, 9, "google.cloud.speech.v1p1beta1.SpeechAdaptationInfo"
|
164
171
|
optional :request_id, :int64, 10
|
@@ -166,6 +173,9 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
|
|
166
173
|
add_enum "google.cloud.speech.v1p1beta1.StreamingRecognizeResponse.SpeechEventType" do
|
167
174
|
value :SPEECH_EVENT_UNSPECIFIED, 0
|
168
175
|
value :END_OF_SINGLE_UTTERANCE, 1
|
176
|
+
value :SPEECH_ACTIVITY_BEGIN, 2
|
177
|
+
value :SPEECH_ACTIVITY_END, 3
|
178
|
+
value :SPEECH_ACTIVITY_TIMEOUT, 4
|
169
179
|
end
|
170
180
|
add_message "google.cloud.speech.v1p1beta1.StreamingRecognitionResult" do
|
171
181
|
repeated :alternatives, :message, 1, "google.cloud.speech.v1p1beta1.SpeechRecognitionAlternative"
|
@@ -209,6 +219,7 @@ module Google
|
|
209
219
|
TranscriptOutputConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.TranscriptOutputConfig").msgclass
|
210
220
|
StreamingRecognizeRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.StreamingRecognizeRequest").msgclass
|
211
221
|
StreamingRecognitionConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.StreamingRecognitionConfig").msgclass
|
222
|
+
StreamingRecognitionConfig::VoiceActivityTimeout = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.StreamingRecognitionConfig.VoiceActivityTimeout").msgclass
|
212
223
|
RecognitionConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.RecognitionConfig").msgclass
|
213
224
|
RecognitionConfig::AudioEncoding = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding").enummodule
|
214
225
|
SpeakerDiarizationConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.SpeakerDiarizationConfig").msgclass
|
@@ -462,9 +462,9 @@ module Google
|
|
462
462
|
# * (`String`) The path to a service account key file in JSON format
|
463
463
|
# * (`Hash`) A service account key as a Hash
|
464
464
|
# * (`Google::Auth::Credentials`) A googleauth credentials object
|
465
|
-
# (see the [googleauth docs](https://
|
465
|
+
# (see the [googleauth docs](https://rubydoc.info/gems/googleauth/Google/Auth/Credentials))
|
466
466
|
# * (`Signet::OAuth2::Client`) A signet oauth2 client object
|
467
|
-
# (see the [signet docs](https://
|
467
|
+
# (see the [signet docs](https://rubydoc.info/gems/signet/Signet/OAuth2/Client))
|
468
468
|
# * (`GRPC::Core::Channel`) a gRPC channel with included credentials
|
469
469
|
# * (`GRPC::Core::ChannelCredentials`) a gRPC credentails object
|
470
470
|
# * (`nil`) indicating no credentials
|
@@ -612,9 +612,9 @@ module Google
|
|
612
612
|
# * (`String`) The path to a service account key file in JSON format
|
613
613
|
# * (`Hash`) A service account key as a Hash
|
614
614
|
# * (`Google::Auth::Credentials`) A googleauth credentials object
|
615
|
-
# (see the [googleauth docs](https://
|
615
|
+
# (see the [googleauth docs](https://rubydoc.info/gems/googleauth/Google/Auth/Credentials))
|
616
616
|
# * (`Signet::OAuth2::Client`) A signet oauth2 client object
|
617
|
-
# (see the [signet docs](https://
|
617
|
+
# (see the [signet docs](https://rubydoc.info/gems/signet/Signet/OAuth2/Client))
|
618
618
|
# * (`GRPC::Core::Channel`) a gRPC channel with included credentials
|
619
619
|
# * (`GRPC::Core::ChannelCredentials`) a gRPC credentails object
|
620
620
|
# * (`nil`) indicating no credentials
|
@@ -332,9 +332,9 @@ module Google
|
|
332
332
|
# * (`String`) The path to a service account key file in JSON format
|
333
333
|
# * (`Hash`) A service account key as a Hash
|
334
334
|
# * (`Google::Auth::Credentials`) A googleauth credentials object
|
335
|
-
# (see the [googleauth docs](https://
|
335
|
+
# (see the [googleauth docs](https://rubydoc.info/gems/googleauth/Google/Auth/Credentials))
|
336
336
|
# * (`Signet::OAuth2::Client`) A signet oauth2 client object
|
337
|
-
# (see the [signet docs](https://
|
337
|
+
# (see the [signet docs](https://rubydoc.info/gems/signet/Signet/OAuth2/Client))
|
338
338
|
# * (`nil`) indicating no credentials
|
339
339
|
# @return [::Object]
|
340
340
|
# @!attribute [rw] scope
|
@@ -411,9 +411,9 @@ module Google
|
|
411
411
|
# * (`String`) The path to a service account key file in JSON format
|
412
412
|
# * (`Hash`) A service account key as a Hash
|
413
413
|
# * (`Google::Auth::Credentials`) A googleauth credentials object
|
414
|
-
# (see the [googleauth docs](https://
|
414
|
+
# (see the [googleauth docs](https://rubydoc.info/gems/googleauth/Google/Auth/Credentials))
|
415
415
|
# * (`Signet::OAuth2::Client`) A signet oauth2 client object
|
416
|
-
# (see the [signet docs](https://
|
416
|
+
# (see the [signet docs](https://rubydoc.info/gems/signet/Signet/OAuth2/Client))
|
417
417
|
# * (`nil`) indicating no credentials
|
418
418
|
# @return [::Object]
|
419
419
|
# @!attribute [rw] scope
|
@@ -35,7 +35,9 @@ module Google
|
|
35
35
|
# Details about how and where to publish client libraries.
|
36
36
|
# @!attribute [rw] version
|
37
37
|
# @return [::String]
|
38
|
-
# Version of the API to apply these settings to.
|
38
|
+
# Version of the API to apply these settings to. This is the full protobuf
|
39
|
+
# package for the API, ending in the version element.
|
40
|
+
# Examples: "google.cloud.speech.v1" and "google.spanner.admin.database.v1".
|
39
41
|
# @!attribute [rw] launch_stage
|
40
42
|
# @return [::Google::Api::LaunchStage]
|
41
43
|
# Launch stage of this version of the API.
|
@@ -111,6 +113,10 @@ module Google
|
|
111
113
|
# Client library settings. If the same version string appears multiple
|
112
114
|
# times in this list, then the last one wins. Settings from earlier
|
113
115
|
# settings with the same version string are discarded.
|
116
|
+
# @!attribute [rw] proto_reference_documentation_uri
|
117
|
+
# @return [::String]
|
118
|
+
# Optional link to proto reference documentation. Example:
|
119
|
+
# https://cloud.google.com/pubsub/lite/docs/reference/rpc
|
114
120
|
class Publishing
|
115
121
|
include ::Google::Protobuf::MessageExts
|
116
122
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
@@ -240,8 +246,8 @@ module Google
|
|
240
246
|
# Example of a YAML configuration::
|
241
247
|
#
|
242
248
|
# publishing:
|
243
|
-
#
|
244
|
-
# - selector:
|
249
|
+
# method_settings:
|
250
|
+
# - selector: google.cloud.speech.v2.Speech.BatchRecognize
|
245
251
|
# long_running:
|
246
252
|
# initial_poll_delay:
|
247
253
|
# seconds: 60 # 1 minute
|
@@ -122,9 +122,30 @@ module Google
|
|
122
122
|
# returned as they become available (these interim results are indicated with
|
123
123
|
# the `is_final=false` flag).
|
124
124
|
# If `false` or omitted, only `is_final=true` result(s) are returned.
|
125
|
+
# @!attribute [rw] enable_voice_activity_events
|
126
|
+
# @return [::Boolean]
|
127
|
+
# If `true`, responses with voice activity speech events will be returned as
|
128
|
+
# they are detected.
|
129
|
+
# @!attribute [rw] voice_activity_timeout
|
130
|
+
# @return [::Google::Cloud::Speech::V1p1beta1::StreamingRecognitionConfig::VoiceActivityTimeout]
|
131
|
+
# If set, the server will automatically close the stream after the specified
|
132
|
+
# duration has elapsed after the last VOICE_ACTIVITY speech event has been
|
133
|
+
# sent. The field `voice_activity_events` must also be set to true.
|
125
134
|
class StreamingRecognitionConfig
|
126
135
|
include ::Google::Protobuf::MessageExts
|
127
136
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
137
|
+
|
138
|
+
# Events that a timeout can be set on for voice activity.
|
139
|
+
# @!attribute [rw] speech_start_timeout
|
140
|
+
# @return [::Google::Protobuf::Duration]
|
141
|
+
# Duration to timeout the stream if no speech begins.
|
142
|
+
# @!attribute [rw] speech_end_timeout
|
143
|
+
# @return [::Google::Protobuf::Duration]
|
144
|
+
# Duration to timeout the stream after speech ends.
|
145
|
+
class VoiceActivityTimeout
|
146
|
+
include ::Google::Protobuf::MessageExts
|
147
|
+
extend ::Google::Protobuf::MessageExts::ClassMethods
|
148
|
+
end
|
128
149
|
end
|
129
150
|
|
130
151
|
# Provides information to the recognizer that specifies how to process the
|
@@ -133,7 +154,8 @@ module Google
|
|
133
154
|
# @return [::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding]
|
134
155
|
# Encoding of audio data sent in all `RecognitionAudio` messages.
|
135
156
|
# This field is optional for `FLAC` and `WAV` audio files and required
|
136
|
-
# for all other audio formats. For details, see
|
157
|
+
# for all other audio formats. For details, see
|
158
|
+
# {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
|
137
159
|
# @!attribute [rw] sample_rate_hertz
|
138
160
|
# @return [::Integer]
|
139
161
|
# Sample rate in Hertz of the audio data sent in all
|
@@ -142,7 +164,8 @@ module Google
|
|
142
164
|
# source to 16000 Hz. If that's not possible, use the native sample rate of
|
143
165
|
# the audio source (instead of re-sampling).
|
144
166
|
# This field is optional for FLAC and WAV audio files, but is
|
145
|
-
# required for all other audio formats. For details, see
|
167
|
+
# required for all other audio formats. For details, see
|
168
|
+
# {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
|
146
169
|
# @!attribute [rw] audio_channel_count
|
147
170
|
# @return [::Integer]
|
148
171
|
# The number of channels in the input audio data.
|
@@ -363,7 +386,8 @@ module Google
|
|
363
386
|
# an `AudioEncoding` when you send send `FLAC` or `WAV` audio, the
|
364
387
|
# encoding configuration must match the encoding described in the audio
|
365
388
|
# header; otherwise the request returns an
|
366
|
-
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
|
389
|
+
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
|
390
|
+
# code.
|
367
391
|
module AudioEncoding
|
368
392
|
# Not specified.
|
369
393
|
ENCODING_UNSPECIFIED = 0
|
@@ -612,8 +636,8 @@ module Google
|
|
612
636
|
|
613
637
|
# Contains audio data in the encoding specified in the `RecognitionConfig`.
|
614
638
|
# Either `content` or `uri` must be supplied. Supplying both or neither
|
615
|
-
# returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
|
616
|
-
# [content limits](https://cloud.google.com/speech-to-text/quotas#content).
|
639
|
+
# returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
|
640
|
+
# See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
|
617
641
|
# @!attribute [rw] content
|
618
642
|
# @return [::String]
|
619
643
|
# The audio data bytes encoded as specified in
|
@@ -626,8 +650,9 @@ module Google
|
|
626
650
|
# Currently, only Google Cloud Storage URIs are
|
627
651
|
# supported, which must be specified in the following format:
|
628
652
|
# `gs://bucket_name/object_name` (other URI formats return
|
629
|
-
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
|
630
|
-
# [Request
|
653
|
+
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
|
654
|
+
# For more information, see [Request
|
655
|
+
# URIs](https://cloud.google.com/storage/docs/reference-uris).
|
631
656
|
class RecognitionAudio
|
632
657
|
include ::Google::Protobuf::MessageExts
|
633
658
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
@@ -700,11 +725,12 @@ module Google
|
|
700
725
|
# Time of the most recent processing update.
|
701
726
|
# @!attribute [r] uri
|
702
727
|
# @return [::String]
|
703
|
-
# Output only. The URI of the audio file being transcribed. Empty if the
|
704
|
-
# as byte content.
|
728
|
+
# Output only. The URI of the audio file being transcribed. Empty if the
|
729
|
+
# audio was sent as byte content.
|
705
730
|
# @!attribute [r] output_config
|
706
731
|
# @return [::Google::Cloud::Speech::V1p1beta1::TranscriptOutputConfig]
|
707
|
-
# Output only. A copy of the TranscriptOutputConfig if it was set in the
|
732
|
+
# Output only. A copy of the TranscriptOutputConfig if it was set in the
|
733
|
+
# request.
|
708
734
|
class LongRunningRecognizeMetadata
|
709
735
|
include ::Google::Protobuf::MessageExts
|
710
736
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
@@ -772,6 +798,9 @@ module Google
|
|
772
798
|
# @!attribute [rw] speech_event_type
|
773
799
|
# @return [::Google::Cloud::Speech::V1p1beta1::StreamingRecognizeResponse::SpeechEventType]
|
774
800
|
# Indicates the type of speech event.
|
801
|
+
# @!attribute [rw] speech_event_time
|
802
|
+
# @return [::Google::Protobuf::Duration]
|
803
|
+
# Time offset between the beginning of the audio and event emission.
|
775
804
|
# @!attribute [rw] total_billed_time
|
776
805
|
# @return [::Google::Protobuf::Duration]
|
777
806
|
# When available, billed audio seconds for the stream.
|
@@ -800,6 +829,23 @@ module Google
|
|
800
829
|
# until the server closes the gRPC connection. This event is only sent if
|
801
830
|
# `single_utterance` was set to `true`, and is not used otherwise.
|
802
831
|
END_OF_SINGLE_UTTERANCE = 1
|
832
|
+
|
833
|
+
# This event indicates that the server has detected the beginning of human
|
834
|
+
# voice activity in the stream. This event can be returned multiple times
|
835
|
+
# if speech starts and stops repeatedly throughout the stream. This event
|
836
|
+
# is only sent if `voice_activity_events` is set to true.
|
837
|
+
SPEECH_ACTIVITY_BEGIN = 2
|
838
|
+
|
839
|
+
# This event indicates that the server has detected the end of human voice
|
840
|
+
# activity in the stream. This event can be returned multiple times if
|
841
|
+
# speech starts and stops repeatedly throughout the stream. This event is
|
842
|
+
# only sent if `voice_activity_events` is set to true.
|
843
|
+
SPEECH_ACTIVITY_END = 3
|
844
|
+
|
845
|
+
# This event indicates that the user-set timeout for speech activity begin
|
846
|
+
# or end has exceeded. Upon receiving this event, the client is expected to
|
847
|
+
# send a half close. Further audio will not be processed.
|
848
|
+
SPEECH_ACTIVITY_TIMEOUT = 4
|
803
849
|
end
|
804
850
|
end
|
805
851
|
|
@@ -836,9 +882,9 @@ module Google
|
|
836
882
|
# For audio_channel_count = N, its output values can range from '1' to 'N'.
|
837
883
|
# @!attribute [r] language_code
|
838
884
|
# @return [::String]
|
839
|
-
# Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
840
|
-
# of the language in this result. This language code was
|
841
|
-
# the most likelihood of being spoken in the audio.
|
885
|
+
# Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
886
|
+
# language tag of the language in this result. This language code was
|
887
|
+
# detected to have the most likelihood of being spoken in the audio.
|
842
888
|
class StreamingRecognitionResult
|
843
889
|
include ::Google::Protobuf::MessageExts
|
844
890
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
@@ -862,9 +908,9 @@ module Google
|
|
862
908
|
# beginning of the audio.
|
863
909
|
# @!attribute [r] language_code
|
864
910
|
# @return [::String]
|
865
|
-
# Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
866
|
-
# of the language in this result. This language code was
|
867
|
-
# the most likelihood of being spoken in the audio.
|
911
|
+
# Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
|
912
|
+
# language tag of the language in this result. This language code was
|
913
|
+
# detected to have the most likelihood of being spoken in the audio.
|
868
914
|
class SpeechRecognitionResult
|
869
915
|
include ::Google::Protobuf::MessageExts
|
870
916
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
@@ -27,7 +27,7 @@ module Google
|
|
27
27
|
# Required. The parent resource where this phrase set will be created.
|
28
28
|
# Format:
|
29
29
|
#
|
30
|
-
# `projects/{project}/locations/{location}
|
30
|
+
# `projects/{project}/locations/{location}`
|
31
31
|
#
|
32
32
|
# Speech-to-Text supports three locations: `global`, `us` (US North America),
|
33
33
|
# and `eu` (Europe). If you are calling the `speech.googleapis.com`
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: google-cloud-speech-v1p1beta1
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.17.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Google LLC
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-
|
11
|
+
date: 2023-03-23 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: gapic-common
|
@@ -16,7 +16,7 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: 0.
|
19
|
+
version: 0.18.0
|
20
20
|
- - "<"
|
21
21
|
- !ruby/object:Gem::Version
|
22
22
|
version: 2.a
|
@@ -26,7 +26,7 @@ dependencies:
|
|
26
26
|
requirements:
|
27
27
|
- - ">="
|
28
28
|
- !ruby/object:Gem::Version
|
29
|
-
version: 0.
|
29
|
+
version: 0.18.0
|
30
30
|
- - "<"
|
31
31
|
- !ruby/object:Gem::Version
|
32
32
|
version: 2.a
|
@@ -236,5 +236,5 @@ requirements: []
|
|
236
236
|
rubygems_version: 3.4.2
|
237
237
|
signing_key:
|
238
238
|
specification_version: 4
|
239
|
-
summary:
|
239
|
+
summary: Converts audio to text by applying powerful neural network models.
|
240
240
|
test_files: []
|