google-cloud-speech 0.31.1 → 0.32.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/google/cloud/speech/v1/speech_client_config.json +3 -3
- data/lib/google/cloud/speech/v1p1beta1/cloud_speech_pb.rb +2 -0
- data/lib/google/cloud/speech/v1p1beta1/cloud_speech_services_pb.rb +2 -1
- data/lib/google/cloud/speech/v1p1beta1/doc/google/cloud/speech/v1p1beta1/cloud_speech.rb +39 -26
- data/lib/google/cloud/speech/v1p1beta1/speech_client_config.json +3 -3
- metadata +4 -4
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 58d05dda613bbd299a497420c6041d87f24341b805c31b1adde99408e0039aeb
|
|
4
|
+
data.tar.gz: ab6f46d2a5013541196b60c3334aae34371a9a7cdeb2aa3e296a6dfb10fc64bb
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 7e90bf229e973607f17495decf94580dcf3bfd8775eba9dab950434a432a2533db93f847f6a48d1dff430d05d41f63a12461727a58f7acb7acb0963be2adbf4d
|
|
7
|
+
data.tar.gz: 696db8cf73a3ddf704e46e07bbf1108346a371784869d415f314887dd2938c3a9e8f06c9471e24a94d3f289d676deab4b0fe67033d1f00cc5547c9e3f2f4978d
|
|
@@ -21,17 +21,17 @@
|
|
|
21
21
|
},
|
|
22
22
|
"methods": {
|
|
23
23
|
"Recognize": {
|
|
24
|
-
"timeout_millis":
|
|
24
|
+
"timeout_millis": 200000,
|
|
25
25
|
"retry_codes_name": "idempotent",
|
|
26
26
|
"retry_params_name": "default"
|
|
27
27
|
},
|
|
28
28
|
"LongRunningRecognize": {
|
|
29
|
-
"timeout_millis":
|
|
29
|
+
"timeout_millis": 200000,
|
|
30
30
|
"retry_codes_name": "non_idempotent",
|
|
31
31
|
"retry_params_name": "default"
|
|
32
32
|
},
|
|
33
33
|
"StreamingRecognize": {
|
|
34
|
-
"timeout_millis":
|
|
34
|
+
"timeout_millis": 200000,
|
|
35
35
|
"retry_codes_name": "idempotent",
|
|
36
36
|
"retry_params_name": "default"
|
|
37
37
|
}
|
|
@@ -8,6 +8,7 @@ require 'google/api/annotations_pb'
|
|
|
8
8
|
require 'google/longrunning/operations_pb'
|
|
9
9
|
require 'google/protobuf/any_pb'
|
|
10
10
|
require 'google/protobuf/duration_pb'
|
|
11
|
+
require 'google/protobuf/empty_pb'
|
|
11
12
|
require 'google/protobuf/timestamp_pb'
|
|
12
13
|
require 'google/rpc/status_pb'
|
|
13
14
|
Google::Protobuf::DescriptorPool.generated_pool.build do
|
|
@@ -134,6 +135,7 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
|
|
|
134
135
|
repeated :alternatives, :message, 1, "google.cloud.speech.v1p1beta1.SpeechRecognitionAlternative"
|
|
135
136
|
optional :is_final, :bool, 2
|
|
136
137
|
optional :stability, :float, 3
|
|
138
|
+
optional :result_end_time, :message, 4, "google.protobuf.Duration"
|
|
137
139
|
optional :channel_tag, :int32, 5
|
|
138
140
|
optional :language_code, :string, 6
|
|
139
141
|
end
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
# Generated by the protocol buffer compiler. DO NOT EDIT!
|
|
2
2
|
# Source: google/cloud/speech/v1p1beta1/cloud_speech.proto for package 'google.cloud.speech.v1p1beta1'
|
|
3
3
|
# Original file comments:
|
|
4
|
-
# Copyright 2018 Google
|
|
4
|
+
# Copyright 2018 Google LLC.
|
|
5
5
|
#
|
|
6
6
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
7
7
|
# you may not use this file except in compliance with the License.
|
|
@@ -15,6 +15,7 @@
|
|
|
15
15
|
# See the License for the specific language governing permissions and
|
|
16
16
|
# limitations under the License.
|
|
17
17
|
#
|
|
18
|
+
#
|
|
18
19
|
|
|
19
20
|
|
|
20
21
|
require 'grpc'
|
|
@@ -57,7 +57,7 @@ module Google
|
|
|
57
57
|
# `audio_content` data. The audio bytes must be encoded as specified in
|
|
58
58
|
# `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
|
|
59
59
|
# pure binary representation (not base64). See
|
|
60
|
-
# [
|
|
60
|
+
# [content limits](https://cloud.google.com/speech-to-text/quotas#content).
|
|
61
61
|
class StreamingRecognizeRequest; end
|
|
62
62
|
|
|
63
63
|
# Provides information to the recognizer that specifies how to process the
|
|
@@ -111,36 +111,36 @@ module Google
|
|
|
111
111
|
# Valid values for OGG_OPUS are '1'-'254'.
|
|
112
112
|
# Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
|
|
113
113
|
# If `0` or omitted, defaults to one channel (mono).
|
|
114
|
-
#
|
|
114
|
+
# Note: We only recognize the first channel by default.
|
|
115
115
|
# To perform independent recognition on each channel set
|
|
116
|
-
# enable_separate_recognition_per_channel to 'true'.
|
|
116
|
+
# `enable_separate_recognition_per_channel` to 'true'.
|
|
117
117
|
# @!attribute [rw] enable_separate_recognition_per_channel
|
|
118
118
|
# @return [true, false]
|
|
119
|
-
# This needs to be set to ‘true’ explicitly and audio_channel_count > 1
|
|
119
|
+
# This needs to be set to ‘true’ explicitly and `audio_channel_count` > 1
|
|
120
120
|
# to get each channel recognized separately. The recognition result will
|
|
121
|
-
# contain a channel_tag field to state which channel that result belongs
|
|
122
|
-
# If this is not
|
|
123
|
-
#
|
|
124
|
-
#
|
|
121
|
+
# contain a `channel_tag` field to state which channel that result belongs
|
|
122
|
+
# to. If this is not true, we will only recognize the first channel. The
|
|
123
|
+
# request is billed cumulatively for all channels recognized:
|
|
124
|
+
# `audio_channel_count` multiplied by the length of the audio.
|
|
125
125
|
# @!attribute [rw] language_code
|
|
126
126
|
# @return [String]
|
|
127
127
|
# *Required* The language of the supplied audio as a
|
|
128
128
|
# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
|
|
129
129
|
# Example: "en-US".
|
|
130
|
-
# See [Language Support](https://cloud.google.com/speech/docs/languages)
|
|
130
|
+
# See [Language Support](https://cloud.google.com/speech-to-text/docs/languages)
|
|
131
131
|
# for a list of the currently supported language codes.
|
|
132
132
|
# @!attribute [rw] alternative_language_codes
|
|
133
133
|
# @return [Array<String>]
|
|
134
134
|
# *Optional* A list of up to 3 additional
|
|
135
135
|
# [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
|
|
136
136
|
# listing possible alternative languages of the supplied audio.
|
|
137
|
-
# See [Language Support](https://cloud.google.com/speech/docs/languages)
|
|
137
|
+
# See [Language Support](https://cloud.google.com/speech-to-text/docs/languages)
|
|
138
138
|
# for a list of the currently supported language codes.
|
|
139
139
|
# If alternative languages are listed, recognition result will contain
|
|
140
140
|
# recognition in the most likely language detected including the main
|
|
141
141
|
# language_code. The recognition result will include the language tag
|
|
142
142
|
# of the language detected in the audio.
|
|
143
|
-
#
|
|
143
|
+
# Note: This feature is only supported for Voice Command and Voice Search
|
|
144
144
|
# use cases and performance may vary for other use cases (e.g., phone call
|
|
145
145
|
# transcription).
|
|
146
146
|
# @!attribute [rw] max_alternatives
|
|
@@ -159,7 +159,9 @@ module Google
|
|
|
159
159
|
# won't be filtered out.
|
|
160
160
|
# @!attribute [rw] speech_contexts
|
|
161
161
|
# @return [Array<Google::Cloud::Speech::V1p1beta1::SpeechContext>]
|
|
162
|
-
# *Optional*
|
|
162
|
+
# *Optional* array of {Google::Cloud::Speech::V1p1beta1::SpeechContext SpeechContext}.
|
|
163
|
+
# A means to provide context to assist the speech recognition. For more
|
|
164
|
+
# information, see [Phrase Hints](https://cloud.google.com/speech-to-text/docs/basics#phrase-hints).
|
|
163
165
|
# @!attribute [rw] enable_word_time_offsets
|
|
164
166
|
# @return [true, false]
|
|
165
167
|
# *Optional* If `true`, the top result includes a list of words and
|
|
@@ -177,18 +179,20 @@ module Google
|
|
|
177
179
|
# This feature is only available in select languages. Setting this for
|
|
178
180
|
# requests in other languages has no effect at all.
|
|
179
181
|
# The default 'false' value does not add punctuation to result hypotheses.
|
|
180
|
-
#
|
|
182
|
+
# Note: This is currently offered as an experimental service, complimentary
|
|
181
183
|
# to all users. In the future this may be exclusively available as a
|
|
182
|
-
# premium feature.
|
|
184
|
+
# premium feature.
|
|
183
185
|
# @!attribute [rw] enable_speaker_diarization
|
|
184
186
|
# @return [true, false]
|
|
185
187
|
# *Optional* If 'true', enables speaker detection for each recognized word in
|
|
186
188
|
# the top alternative of the recognition result using a speaker_tag provided
|
|
187
189
|
# in the WordInfo.
|
|
188
190
|
# Note: When this is true, we send all the words from the beginning of the
|
|
189
|
-
# audio for the top alternative in every consecutive responses.
|
|
191
|
+
# audio for the top alternative in every consecutive STREAMING responses.
|
|
190
192
|
# This is done in order to improve our speaker tags as our models learn to
|
|
191
193
|
# identify the speakers in the conversation over time.
|
|
194
|
+
# For non-streaming requests, the diarization results will be provided only
|
|
195
|
+
# in the top alternative of the FINAL SpeechRecognitionResult.
|
|
192
196
|
# @!attribute [rw] diarization_speaker_count
|
|
193
197
|
# @return [Integer]
|
|
194
198
|
# *Optional*
|
|
@@ -235,14 +239,18 @@ module Google
|
|
|
235
239
|
# @!attribute [rw] use_enhanced
|
|
236
240
|
# @return [true, false]
|
|
237
241
|
# *Optional* Set to true to use an enhanced model for speech recognition.
|
|
238
|
-
#
|
|
239
|
-
#
|
|
240
|
-
#
|
|
241
|
-
#
|
|
242
|
-
# recognized using the standard version of the specified model.
|
|
242
|
+
# If `use_enhanced` is set to true and the `model` field is not set, then
|
|
243
|
+
# an appropriate enhanced model is chosen if:
|
|
244
|
+
# 1. project is eligible for requesting enhanced models
|
|
245
|
+
# 2. an enhanced model exists for the audio
|
|
243
246
|
#
|
|
244
|
-
#
|
|
245
|
-
#
|
|
247
|
+
# If `use_enhanced` is true and an enhanced version of the specified model
|
|
248
|
+
# does not exist, then the speech is recognized using the standard version
|
|
249
|
+
# of the specified model.
|
|
250
|
+
#
|
|
251
|
+
# Enhanced speech models require that you opt-in to data logging using
|
|
252
|
+
# instructions in the
|
|
253
|
+
# [documentation](https://cloud.google.com/speech-to-text/docs/enable-data-logging). If you set
|
|
246
254
|
# `use_enhanced` to true and you have not enabled audio logging, then you
|
|
247
255
|
# will receive an error.
|
|
248
256
|
class RecognitionConfig
|
|
@@ -452,13 +460,13 @@ module Google
|
|
|
452
460
|
# to improve the accuracy for specific words and phrases, for example, if
|
|
453
461
|
# specific commands are typically spoken by the user. This can also be used
|
|
454
462
|
# to add additional words to the vocabulary of the recognizer. See
|
|
455
|
-
# [usage limits](https://cloud.google.com/speech/
|
|
463
|
+
# [usage limits](https://cloud.google.com/speech-to-text/quotas#content).
|
|
456
464
|
class SpeechContext; end
|
|
457
465
|
|
|
458
466
|
# Contains audio data in the encoding specified in the `RecognitionConfig`.
|
|
459
467
|
# Either `content` or `uri` must be supplied. Supplying both or neither
|
|
460
468
|
# returns {Google::Rpc::Code::INVALID_ARGUMENT}. See
|
|
461
|
-
# [
|
|
469
|
+
# [content limits](https://cloud.google.com/speech-to-text/quotas#content).
|
|
462
470
|
# @!attribute [rw] content
|
|
463
471
|
# @return [String]
|
|
464
472
|
# The audio data bytes encoded as specified in
|
|
@@ -467,7 +475,8 @@ module Google
|
|
|
467
475
|
# @!attribute [rw] uri
|
|
468
476
|
# @return [String]
|
|
469
477
|
# URI that points to a file that contains audio data bytes as specified in
|
|
470
|
-
# `RecognitionConfig`.
|
|
478
|
+
# `RecognitionConfig`. The file must not be compressed (for example, gzip).
|
|
479
|
+
# Currently, only Google Cloud Storage URIs are
|
|
471
480
|
# supported, which must be specified in the following format:
|
|
472
481
|
# `gs://bucket_name/object_name` (other URI formats return
|
|
473
482
|
# {Google::Rpc::Code::INVALID_ARGUMENT}). For more information, see
|
|
@@ -610,6 +619,10 @@ module Google
|
|
|
610
619
|
# (completely unstable) to 1.0 (completely stable).
|
|
611
620
|
# This field is only provided for interim results (`is_final=false`).
|
|
612
621
|
# The default of 0.0 is a sentinel value indicating `stability` was not set.
|
|
622
|
+
# @!attribute [rw] result_end_time
|
|
623
|
+
# @return [Google::Protobuf::Duration]
|
|
624
|
+
# Output only. Time offset of the end of this result relative to the
|
|
625
|
+
# beginning of the audio.
|
|
613
626
|
# @!attribute [rw] channel_tag
|
|
614
627
|
# @return [Integer]
|
|
615
628
|
# For multi-channel audio, this is the channel number corresponding to the
|
|
@@ -659,7 +672,7 @@ module Google
|
|
|
659
672
|
# @!attribute [rw] words
|
|
660
673
|
# @return [Array<Google::Cloud::Speech::V1p1beta1::WordInfo>]
|
|
661
674
|
# Output only. A list of word-specific information for each recognized word.
|
|
662
|
-
# Note: When enable_speaker_diarization is true, you will see all the words
|
|
675
|
+
# Note: When `enable_speaker_diarization` is true, you will see all the words
|
|
663
676
|
# from the beginning of the audio.
|
|
664
677
|
class SpeechRecognitionAlternative; end
|
|
665
678
|
|
|
@@ -21,17 +21,17 @@
|
|
|
21
21
|
},
|
|
22
22
|
"methods": {
|
|
23
23
|
"Recognize": {
|
|
24
|
-
"timeout_millis":
|
|
24
|
+
"timeout_millis": 200000,
|
|
25
25
|
"retry_codes_name": "idempotent",
|
|
26
26
|
"retry_params_name": "default"
|
|
27
27
|
},
|
|
28
28
|
"LongRunningRecognize": {
|
|
29
|
-
"timeout_millis":
|
|
29
|
+
"timeout_millis": 200000,
|
|
30
30
|
"retry_codes_name": "non_idempotent",
|
|
31
31
|
"retry_params_name": "default"
|
|
32
32
|
},
|
|
33
33
|
"StreamingRecognize": {
|
|
34
|
-
"timeout_millis":
|
|
34
|
+
"timeout_millis": 905000,
|
|
35
35
|
"retry_codes_name": "idempotent",
|
|
36
36
|
"retry_params_name": "default"
|
|
37
37
|
}
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: google-cloud-speech
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.32.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Google LLC
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2018-
|
|
11
|
+
date: 2018-11-15 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: google-gax
|
|
@@ -58,14 +58,14 @@ dependencies:
|
|
|
58
58
|
requirements:
|
|
59
59
|
- - "~>"
|
|
60
60
|
- !ruby/object:Gem::Version
|
|
61
|
-
version: 0.
|
|
61
|
+
version: 0.59.2
|
|
62
62
|
type: :development
|
|
63
63
|
prerelease: false
|
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
|
65
65
|
requirements:
|
|
66
66
|
- - "~>"
|
|
67
67
|
- !ruby/object:Gem::Version
|
|
68
|
-
version: 0.
|
|
68
|
+
version: 0.59.2
|
|
69
69
|
- !ruby/object:Gem::Dependency
|
|
70
70
|
name: simplecov
|
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|