ibm_watson 1.1.0 → 1.5.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (26) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +33 -5
  3. data/lib/ibm_watson/assistant_v1.rb +156 -65
  4. data/lib/ibm_watson/assistant_v2.rb +76 -13
  5. data/lib/ibm_watson/compare_comply_v1.rb +11 -5
  6. data/lib/ibm_watson/discovery_v1.rb +19 -9
  7. data/lib/ibm_watson/discovery_v2.rb +25 -9
  8. data/lib/ibm_watson/language_translator_v3.rb +27 -13
  9. data/lib/ibm_watson/natural_language_classifier_v1.rb +10 -4
  10. data/lib/ibm_watson/natural_language_understanding_v1.rb +20 -10
  11. data/lib/ibm_watson/personality_insights_v3.rb +17 -11
  12. data/lib/ibm_watson/speech_to_text_v1.rb +394 -168
  13. data/lib/ibm_watson/text_to_speech_v1.rb +57 -46
  14. data/lib/ibm_watson/tone_analyzer_v3.rb +11 -5
  15. data/lib/ibm_watson/version.rb +1 -1
  16. data/lib/ibm_watson/visual_recognition_v3.rb +15 -7
  17. data/lib/ibm_watson/visual_recognition_v4.rb +199 -4
  18. data/test/integration/test_assistant_v2.rb +7 -0
  19. data/test/integration/test_compare_comply_v1.rb +1 -12
  20. data/test/integration/test_speech_to_text_v1.rb +7 -2
  21. data/test/integration/test_visual_recognition_v4.rb +9 -0
  22. data/test/unit/test_assistant_v2.rb +66 -0
  23. data/test/unit/test_personality_insights_v3.rb +4 -0
  24. data/test/unit/test_visual_recognition_v4.rb +87 -0
  25. metadata +5 -6
  26. data/test/unit/test_vcap_using_personality_insights.rb +0 -161
data/lib/ibm_watson/natural_language_classifier_v1.rb CHANGED
@@ -1,6 +1,6 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- # (C) Copyright IBM Corp. 2019.
3
+ # (C) Copyright IBM Corp. 2018, 2020.
4
4
  #
5
5
  # Licensed under the Apache License, Version 2.0 (the "License");
6
6
  # you may not use this file except in compliance with the License.
@@ -31,6 +31,8 @@ module IBMWatson
31
31
  # The Natural Language Classifier V1 service.
32
32
  class NaturalLanguageClassifierV1 < IBMCloudSdkCore::BaseService
33
33
  include Concurrent::Async
34
+ DEFAULT_SERVICE_NAME = "natural_language_classifier"
35
+ DEFAULT_SERVICE_URL = "https://gateway.watsonplatform.net/natural-language-classifier/api"
34
36
  ##
35
37
  # @!method initialize(args)
36
38
  # Construct a new client for the Natural Language Classifier service.
@@ -39,15 +41,19 @@ module IBMWatson
39
41
  # @option args service_url [String] The base service URL to use when contacting the service.
40
42
  # The base service_url may differ between IBM Cloud regions.
41
43
  # @option args authenticator [Object] The Authenticator instance to be configured for this service.
44
+ # @option args service_name [String] The name of the service to configure. Will be used as the key to load
45
+ # any external configuration, if applicable.
42
46
  def initialize(args = {})
43
47
  @__async_initialized__ = false
44
48
  defaults = {}
45
- defaults[:service_url] = "https://gateway.watsonplatform.net/natural-language-classifier/api"
49
+ defaults[:service_url] = DEFAULT_SERVICE_URL
50
+ defaults[:service_name] = DEFAULT_SERVICE_NAME
46
51
  defaults[:authenticator] = nil
52
+ user_service_url = args[:service_url] unless args[:service_url].nil?
47
53
  args = defaults.merge(args)
48
- args[:service_name] = "natural_language_classifier"
49
54
  args[:authenticator] = IBMCloudSdkCore::ConfigBasedAuthenticatorFactory.new.get_authenticator(service_name: args[:service_name]) if args[:authenticator].nil?
50
55
  super
56
+ @service_url = user_service_url unless user_service_url.nil?
51
57
  end
52
58
 
53
59
  #########################
@@ -141,7 +147,7 @@ module IBMWatson
141
147
  # (`pt`), and Spanish (`es`).
142
148
  # @param training_data [File] Training data in CSV format. Each text value must have at least one class. The
143
149
  # data can include up to 3,000 classes and 20,000 records. For details, see [Data
144
- # preparation](https://cloud.ibm.com/docs/services/natural-language-classifier?topic=natural-language-classifier-using-your-data).
150
+ # preparation](https://cloud.ibm.com/docs/natural-language-classifier?topic=natural-language-classifier-using-your-data).
145
151
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
146
152
  def create_classifier(training_metadata:, training_data:)
147
153
  raise ArgumentError.new("training_metadata must be provided") if training_metadata.nil?
data/lib/ibm_watson/natural_language_understanding_v1.rb CHANGED
@@ -1,6 +1,6 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- # (C) Copyright IBM Corp. 2019.
3
+ # (C) Copyright IBM Corp. 2018, 2020.
4
4
  #
5
5
  # Licensed under the Apache License, Version 2.0 (the "License");
6
6
  # you may not use this file except in compliance with the License.
@@ -20,9 +20,9 @@
20
20
  # can ignore most advertisements and other unwanted content.
21
21
  #
22
22
  # You can create [custom
23
- # models](https://cloud.ibm.com/docs/services/natural-language-understanding?topic=natural-language-understanding-customizing)
24
- # with Watson Knowledge Studio to detect custom entities, relations, and categories in
25
- # Natural Language Understanding.
23
+ # models](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-customizing)
24
+ # with Watson Knowledge Studio to detect custom entities and relations in Natural Language
25
+ # Understanding.
26
26
 
27
27
  require "concurrent"
28
28
  require "erb"
@@ -36,6 +36,8 @@ module IBMWatson
36
36
  # The Natural Language Understanding V1 service.
37
37
  class NaturalLanguageUnderstandingV1 < IBMCloudSdkCore::BaseService
38
38
  include Concurrent::Async
39
+ DEFAULT_SERVICE_NAME = "natural_language_understanding"
40
+ DEFAULT_SERVICE_URL = "https://gateway.watsonplatform.net/natural-language-understanding/api"
39
41
  ##
40
42
  # @!method initialize(args)
41
43
  # Construct a new client for the Natural Language Understanding service.
@@ -54,19 +56,23 @@ module IBMWatson
54
56
  # @option args service_url [String] The base service URL to use when contacting the service.
55
57
  # The base service_url may differ between IBM Cloud regions.
56
58
  # @option args authenticator [Object] The Authenticator instance to be configured for this service.
59
+ # @option args service_name [String] The name of the service to configure. Will be used as the key to load
60
+ # any external configuration, if applicable.
57
61
  def initialize(args = {})
58
62
  @__async_initialized__ = false
59
63
  defaults = {}
60
64
  defaults[:version] = nil
61
- defaults[:service_url] = "https://gateway.watsonplatform.net/natural-language-understanding/api"
65
+ defaults[:service_url] = DEFAULT_SERVICE_URL
66
+ defaults[:service_name] = DEFAULT_SERVICE_NAME
62
67
  defaults[:authenticator] = nil
68
+ user_service_url = args[:service_url] unless args[:service_url].nil?
63
69
  args = defaults.merge(args)
64
70
  @version = args[:version]
65
71
  raise ArgumentError.new("version must be provided") if @version.nil?
66
72
 
67
- args[:service_name] = "natural_language_understanding"
68
73
  args[:authenticator] = IBMCloudSdkCore::ConfigBasedAuthenticatorFactory.new.get_authenticator(service_name: args[:service_name]) if args[:authenticator].nil?
69
74
  super
75
+ @service_url = user_service_url unless user_service_url.nil?
70
76
  end
71
77
 
72
78
  #########################
@@ -87,6 +93,10 @@ module IBMWatson
87
93
  # - Semantic roles
88
94
  # - Sentiment
89
95
  # - Syntax (Experimental).
96
+ #
97
+ # If a language for the input text is not specified with the `language` parameter,
98
+ # the service [automatically detects the
99
+ # language](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-detectable-languages).
90
100
  # @param features [Features] Specific features to analyze the document for.
91
101
  # @param text [String] The plain text to analyze. One of the `text`, `html`, or `url` parameters is
92
102
  # required.
@@ -96,10 +106,10 @@ module IBMWatson
96
106
  # required.
97
107
  # @param clean [Boolean] Set this to `false` to disable webpage cleaning. To learn more about webpage
98
108
  # cleaning, see the [Analyzing
99
- # webpages](https://cloud.ibm.com/docs/services/natural-language-understanding?topic=natural-language-understanding-analyzing-webpages)
109
+ # webpages](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-analyzing-webpages)
100
110
  # documentation.
101
111
  # @param xpath [String] An [XPath
102
- # query](https://cloud.ibm.com/docs/services/natural-language-understanding?topic=natural-language-understanding-analyzing-webpages#xpath)
112
+ # query](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-analyzing-webpages#xpath)
103
113
  # to perform on `html` or `url` input. Results of the query will be appended to the
104
114
  # cleaned webpage text before it is analyzed. To analyze only the results of the
105
115
  # XPath query, set the `clean` parameter to `false`.
@@ -108,7 +118,7 @@ module IBMWatson
108
118
  # @param language [String] ISO 639-1 code that specifies the language of your text. This overrides automatic
109
119
  # language detection. Language support differs depending on the features you include
110
120
  # in your analysis. See [Language
111
- # support](https://cloud.ibm.com/docs/services/natural-language-understanding?topic=natural-language-understanding-language-support)
121
+ # support](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-language-support)
112
122
  # for more information.
113
123
  # @param limit_text_characters [Fixnum] Sets the maximum number of characters that are processed by the service.
114
124
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
@@ -157,7 +167,7 @@ module IBMWatson
157
167
  # @!method list_models
158
168
  # List models.
159
169
  # Lists Watson Knowledge Studio [custom entities and relations
160
- # models](https://cloud.ibm.com/docs/services/natural-language-understanding?topic=natural-language-understanding-customizing)
170
+ # models](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-customizing)
161
171
  # that are deployed to your Natural Language Understanding service.
162
172
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
163
173
  def list_models
data/lib/ibm_watson/personality_insights_v3.rb CHANGED
@@ -1,6 +1,6 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- # (C) Copyright IBM Corp. 2019.
3
+ # (C) Copyright IBM Corp. 2018, 2020.
4
4
  #
5
5
  # Licensed under the Apache License, Version 2.0 (the "License");
6
6
  # you may not use this file except in compliance with the License.
@@ -26,9 +26,9 @@
26
26
  # is timestamped, can report temporal behavior.
27
27
  # * For information about the meaning of the models that the service uses to describe
28
28
  # personality characteristics, see [Personality
29
- # models](https://cloud.ibm.com/docs/services/personality-insights?topic=personality-insights-models#models).
29
+ # models](https://cloud.ibm.com/docs/personality-insights?topic=personality-insights-models#models).
30
30
  # * For information about the meaning of the consumption preferences, see [Consumption
31
- # preferences](https://cloud.ibm.com/docs/services/personality-insights?topic=personality-insights-preferences#preferences).
31
+ # preferences](https://cloud.ibm.com/docs/personality-insights?topic=personality-insights-preferences#preferences).
32
32
  #
33
33
  #
34
34
  # **Note:** Request logging is disabled for the Personality Insights service. Regardless
@@ -47,6 +47,8 @@ module IBMWatson
47
47
  # The Personality Insights V3 service.
48
48
  class PersonalityInsightsV3 < IBMCloudSdkCore::BaseService
49
49
  include Concurrent::Async
50
+ DEFAULT_SERVICE_NAME = "personality_insights"
51
+ DEFAULT_SERVICE_URL = "https://gateway.watsonplatform.net/personality-insights/api"
50
52
  ##
51
53
  # @!method initialize(args)
52
54
  # Construct a new client for the Personality Insights service.
@@ -65,19 +67,23 @@ module IBMWatson
65
67
  # @option args service_url [String] The base service URL to use when contacting the service.
66
68
  # The base service_url may differ between IBM Cloud regions.
67
69
  # @option args authenticator [Object] The Authenticator instance to be configured for this service.
70
+ # @option args service_name [String] The name of the service to configure. Will be used as the key to load
71
+ # any external configuration, if applicable.
68
72
  def initialize(args = {})
69
73
  @__async_initialized__ = false
70
74
  defaults = {}
71
75
  defaults[:version] = nil
72
- defaults[:service_url] = "https://gateway.watsonplatform.net/personality-insights/api"
76
+ defaults[:service_url] = DEFAULT_SERVICE_URL
77
+ defaults[:service_name] = DEFAULT_SERVICE_NAME
73
78
  defaults[:authenticator] = nil
79
+ user_service_url = args[:service_url] unless args[:service_url].nil?
74
80
  args = defaults.merge(args)
75
81
  @version = args[:version]
76
82
  raise ArgumentError.new("version must be provided") if @version.nil?
77
83
 
78
- args[:service_name] = "personality_insights"
79
84
  args[:authenticator] = IBMCloudSdkCore::ConfigBasedAuthenticatorFactory.new.get_authenticator(service_name: args[:service_name]) if args[:authenticator].nil?
80
85
  super
86
+ @service_url = user_service_url unless user_service_url.nil?
81
87
  end
82
88
 
83
89
  #########################
@@ -95,9 +101,9 @@ module IBMWatson
95
101
  #
96
102
  # **See also:**
97
103
  # * [Requesting a
98
- # profile](https://cloud.ibm.com/docs/services/personality-insights?topic=personality-insights-input#input)
104
+ # profile](https://cloud.ibm.com/docs/personality-insights?topic=personality-insights-input#input)
99
105
  # * [Providing sufficient
100
- # input](https://cloud.ibm.com/docs/services/personality-insights?topic=personality-insights-input#sufficient)
106
+ # input](https://cloud.ibm.com/docs/personality-insights?topic=personality-insights-input#sufficient)
101
107
  #
102
108
  #
103
109
  # ### Content types
@@ -115,7 +121,7 @@ module IBMWatson
115
121
  # `Content-Type: text/plain;charset=utf-8`.
116
122
  #
117
123
  # **See also:** [Specifying request and response
118
- # formats](https://cloud.ibm.com/docs/services/personality-insights?topic=personality-insights-input#formats)
124
+ # formats](https://cloud.ibm.com/docs/personality-insights?topic=personality-insights-input#formats)
119
125
  #
120
126
  #
121
127
  # ### Accept types
@@ -127,12 +133,12 @@ module IBMWatson
127
133
  #
128
134
  # **See also:**
129
135
  # * [Understanding a JSON
130
- # profile](https://cloud.ibm.com/docs/services/personality-insights?topic=personality-insights-output#output)
136
+ # profile](https://cloud.ibm.com/docs/personality-insights?topic=personality-insights-output#output)
131
137
  # * [Understanding a CSV
132
- # profile](https://cloud.ibm.com/docs/services/personality-insights?topic=personality-insights-outputCSV#outputCSV).
138
+ # profile](https://cloud.ibm.com/docs/personality-insights?topic=personality-insights-outputCSV#outputCSV).
133
139
  # @param content [Content] A maximum of 20 MB of content to analyze, though the service requires much less
134
140
  # text; for more information, see [Providing sufficient
135
- # input](https://cloud.ibm.com/docs/services/personality-insights?topic=personality-insights-input#sufficient).
141
+ # input](https://cloud.ibm.com/docs/personality-insights?topic=personality-insights-input#sufficient).
136
142
  # For JSON input, provide an object of type `Content`.
137
143
  # @param accept [String] The type of the response. For more information, see **Accept types** in the method
138
144
  # description.
data/lib/ibm_watson/speech_to_text_v1.rb CHANGED
@@ -1,6 +1,6 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- # (C) Copyright IBM Corp. 2019.
3
+ # (C) Copyright IBM Corp. 2018, 2020.
4
4
  #
5
5
  # Licensed under the Apache License, Version 2.0 (the "License");
6
6
  # you may not use this file except in compliance with the License.
@@ -34,9 +34,9 @@
34
34
  # is a formal language specification that lets you restrict the phrases that the service
35
35
  # can recognize.
36
36
  #
37
- # Language model customization is generally available for production use with most
38
- # supported languages. Acoustic model customization is beta functionality that is
39
- # available for all supported languages.
37
+ # Language model customization and acoustic model customization are generally available
38
+ # for production use with all language models that are generally available. Grammars are
39
+ # beta functionality for all language models that support language model customization.
40
40
 
41
41
  require "concurrent"
42
42
  require "erb"
@@ -50,6 +50,8 @@ module IBMWatson
50
50
  # The Speech to Text V1 service.
51
51
  class SpeechToTextV1 < IBMCloudSdkCore::BaseService
52
52
  include Concurrent::Async
53
+ DEFAULT_SERVICE_NAME = "speech_to_text"
54
+ DEFAULT_SERVICE_URL = "https://stream.watsonplatform.net/speech-to-text/api"
53
55
  ##
54
56
  # @!method initialize(args)
55
57
  # Construct a new client for the Speech to Text service.
@@ -58,15 +60,19 @@ module IBMWatson
58
60
  # @option args service_url [String] The base service URL to use when contacting the service.
59
61
  # The base service_url may differ between IBM Cloud regions.
60
62
  # @option args authenticator [Object] The Authenticator instance to be configured for this service.
63
+ # @option args service_name [String] The name of the service to configure. Will be used as the key to load
64
+ # any external configuration, if applicable.
61
65
  def initialize(args = {})
62
66
  @__async_initialized__ = false
63
67
  defaults = {}
64
- defaults[:service_url] = "https://stream.watsonplatform.net/speech-to-text/api"
68
+ defaults[:service_url] = DEFAULT_SERVICE_URL
69
+ defaults[:service_name] = DEFAULT_SERVICE_NAME
65
70
  defaults[:authenticator] = nil
71
+ user_service_url = args[:service_url] unless args[:service_url].nil?
66
72
  args = defaults.merge(args)
67
- args[:service_name] = "speech_to_text"
68
73
  args[:authenticator] = IBMCloudSdkCore::ConfigBasedAuthenticatorFactory.new.get_authenticator(service_name: args[:service_name]) if args[:authenticator].nil?
69
74
  super
75
+ @service_url = user_service_url unless user_service_url.nil?
70
76
  end
71
77
 
72
78
  #########################
@@ -81,7 +87,7 @@ module IBMWatson
81
87
  # among other things.
82
88
  #
83
89
  # **See also:** [Languages and
84
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-models#models).
90
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-models#models).
85
91
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
86
92
  def list_models
87
93
  headers = {
@@ -108,7 +114,7 @@ module IBMWatson
108
114
  # sampling rate in Hertz, among other things.
109
115
  #
110
116
  # **See also:** [Languages and
111
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-models#models).
117
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-models#models).
112
118
  # @param model_id [String] The identifier of the model in the form of its name from the output of the **Get a
113
119
  # model** method.
114
120
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
@@ -135,7 +141,7 @@ module IBMWatson
135
141
  #########################
136
142
 
137
143
  ##
138
- # @!method recognize(audio:, content_type: nil, model: nil, language_customization_id: nil, acoustic_customization_id: nil, base_model_version: nil, customization_weight: nil, inactivity_timeout: nil, keywords: nil, keywords_threshold: nil, max_alternatives: nil, word_alternatives_threshold: nil, word_confidence: nil, timestamps: nil, profanity_filter: nil, smart_formatting: nil, speaker_labels: nil, customization_id: nil, grammar_name: nil, redaction: nil, audio_metrics: nil)
144
+ # @!method recognize(audio:, content_type: nil, model: nil, language_customization_id: nil, acoustic_customization_id: nil, base_model_version: nil, customization_weight: nil, inactivity_timeout: nil, keywords: nil, keywords_threshold: nil, max_alternatives: nil, word_alternatives_threshold: nil, word_confidence: nil, timestamps: nil, profanity_filter: nil, smart_formatting: nil, speaker_labels: nil, customization_id: nil, grammar_name: nil, redaction: nil, audio_metrics: nil, end_of_phrase_silence_time: nil, split_transcript_at_phrase_end: nil, speech_detector_sensitivity: nil, background_audio_suppression: nil)
139
145
  # Recognize audio.
140
146
  # Sends audio and returns transcription results for a recognition request. You can
141
147
  # pass a maximum of 100 MB and a minimum of 100 bytes of audio with a request. The
@@ -146,7 +152,7 @@ module IBMWatson
146
152
  # upload the file for the request.)
147
153
  #
148
154
  # **See also:** [Making a basic HTTP
149
- # request](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-http#HTTP-basic).
155
+ # request](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-http#HTTP-basic).
150
156
  #
151
157
  #
152
158
  # ### Streaming mode
@@ -161,9 +167,9 @@ module IBMWatson
161
167
  #
162
168
  # **See also:**
163
169
  # * [Audio
164
- # transmission](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#transmission)
170
+ # transmission](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#transmission)
165
171
  # *
166
- # [Timeouts](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#timeouts)
172
+ # [Timeouts](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#timeouts)
167
173
  #
168
174
  #
169
175
  # ### Audio formats (content types)
@@ -203,7 +209,7 @@ module IBMWatson
203
209
  # fails.
204
210
  #
205
211
  # **See also:** [Audio
206
- # formats](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-audio-formats#audio-formats).
212
+ # formats](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-audio-formats#audio-formats).
207
213
  #
208
214
  #
209
215
  # ### Multipart speech recognition
@@ -222,19 +228,19 @@ module IBMWatson
222
228
  # want to spot a very large number of keywords.
223
229
  #
224
230
  # **See also:** [Making a multipart HTTP
225
- # request](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-http#HTTP-multi).
231
+ # request](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-http#HTTP-multi).
226
232
  # @param audio [String] The audio to transcribe.
227
233
  # @param content_type [String] The format (MIME type) of the audio. For more information about specifying an
228
234
  # audio format, see **Audio formats (content types)** in the method description.
229
235
  # @param model [String] The identifier of the model that is to be used for the recognition request. See
230
236
  # [Languages and
231
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-models#models).
237
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-models#models).
232
238
  # @param language_customization_id [String] The customization ID (GUID) of a custom language model that is to be used with the
233
239
  # recognition request. The base model of the specified custom language model must
234
240
  # match the model specified with the `model` parameter. You must make the request
235
241
  # with credentials for the instance of the service that owns the custom model. By
236
242
  # default, no custom language model is used. See [Custom
237
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#custom-input).
243
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#custom-input).
238
244
  #
239
245
  #
240
246
  # **Note:** Use this parameter instead of the deprecated `customization_id`
@@ -244,13 +250,13 @@ module IBMWatson
244
250
  # match the model specified with the `model` parameter. You must make the request
245
251
  # with credentials for the instance of the service that owns the custom model. By
246
252
  # default, no custom acoustic model is used. See [Custom
247
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#custom-input).
253
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#custom-input).
248
254
  # @param base_model_version [String] The version of the specified base model that is to be used with the recognition
249
255
  # request. Multiple versions of a base model can exist when a model is updated for
250
256
  # internal improvements. The parameter is intended primarily for use with custom
251
257
  # models that have been upgraded for a new base model. The default value depends on
252
258
  # whether the parameter is used with or without a custom model. See [Base model
253
- # version](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#version).
259
+ # version](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#version).
254
260
  # @param customization_weight [Float] If you specify the customization ID (GUID) of a custom language model with the
255
261
  # recognition request, the customization weight tells the service how much weight to
256
262
  # give to words from the custom language model compared to those from the base model
@@ -268,45 +274,51 @@ module IBMWatson
268
274
  # phrases.
269
275
  #
270
276
  # See [Custom
271
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#custom-input).
277
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#custom-input).
272
278
  # @param inactivity_timeout [Fixnum] The time in seconds after which, if only silence (no speech) is detected in
273
279
  # streaming audio, the connection is closed with a 400 error. The parameter is
274
280
  # useful for stopping audio submission from a live microphone when a user simply
275
281
  # walks away. Use `-1` for infinity. See [Inactivity
276
- # timeout](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#timeouts-inactivity).
282
+ # timeout](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#timeouts-inactivity).
277
283
  # @param keywords [Array[String]] An array of keyword strings to spot in the audio. Each keyword string can include
278
284
  # one or more string tokens. Keywords are spotted only in the final results, not in
279
285
  # interim hypotheses. If you specify any keywords, you must also specify a keywords
280
- # threshold. You can spot a maximum of 1000 keywords. Omit the parameter or specify
281
- # an empty array if you do not need to spot keywords. See [Keyword
282
- # spotting](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#keyword_spotting).
286
+ # threshold. Omit the parameter or specify an empty array if you do not need to spot
287
+ # keywords.
288
+ #
289
+ # You can spot a maximum of 1000 keywords with a single request. A single keyword
290
+ # can have a maximum length of 1024 characters, though the maximum effective length
291
+ # for double-byte languages might be shorter. Keywords are case-insensitive.
292
+ #
293
+ # See [Keyword
294
+ # spotting](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#keyword_spotting).
283
295
  # @param keywords_threshold [Float] A confidence value that is the lower bound for spotting a keyword. A word is
284
296
  # considered to match a keyword if its confidence is greater than or equal to the
285
297
  # threshold. Specify a probability between 0.0 and 1.0. If you specify a threshold,
286
298
  # you must also specify one or more keywords. The service performs no keyword
287
299
  # spotting if you omit either parameter. See [Keyword
288
- # spotting](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#keyword_spotting).
300
+ # spotting](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#keyword_spotting).
289
301
  # @param max_alternatives [Fixnum] The maximum number of alternative transcripts that the service is to return. By
290
302
  # default, the service returns a single transcript. If you specify a value of `0`,
291
303
  # the service uses the default value, `1`. See [Maximum
292
- # alternatives](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#max_alternatives).
304
+ # alternatives](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#max_alternatives).
293
305
  # @param word_alternatives_threshold [Float] A confidence value that is the lower bound for identifying a hypothesis as a
294
306
  # possible word alternative (also known as "Confusion Networks"). An alternative
295
307
  # word is considered if its confidence is greater than or equal to the threshold.
296
308
  # Specify a probability between 0.0 and 1.0. By default, the service computes no
297
309
  # alternative words. See [Word
298
- # alternatives](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#word_alternatives).
310
+ # alternatives](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#word_alternatives).
299
311
  # @param word_confidence [Boolean] If `true`, the service returns a confidence measure in the range of 0.0 to 1.0 for
300
312
  # each word. By default, the service returns no word confidence scores. See [Word
301
- # confidence](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#word_confidence).
313
+ # confidence](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#word_confidence).
302
314
  # @param timestamps [Boolean] If `true`, the service returns time alignment for each word. By default, no
303
315
  # timestamps are returned. See [Word
304
- # timestamps](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#word_timestamps).
316
+ # timestamps](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#word_timestamps).
305
317
  # @param profanity_filter [Boolean] If `true`, the service filters profanity from all output except for keyword
306
318
  # results by replacing inappropriate words with a series of asterisks. Set the
307
319
  # parameter to `false` to return results with no censoring. Applies to US English
308
320
  # transcription only. See [Profanity
309
- # filtering](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#profanity_filter).
321
+ # filtering](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#profanity_filter).
310
322
  # @param smart_formatting [Boolean] If `true`, the service converts dates, times, series of digits and numbers, phone
311
323
  # numbers, currency values, and internet addresses into more readable, conventional
312
324
  # representations in the final transcript of a recognition request. For US English,
@@ -316,21 +328,21 @@ module IBMWatson
316
328
  # **Note:** Applies to US English, Japanese, and Spanish transcription only.
317
329
  #
318
330
  # See [Smart
319
- # formatting](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#smart_formatting).
331
+ # formatting](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#smart_formatting).
320
332
  # @param speaker_labels [Boolean] If `true`, the response includes labels that identify which words were spoken by
321
333
  # which participants in a multi-person exchange. By default, the service returns no
322
334
  # speaker labels. Setting `speaker_labels` to `true` forces the `timestamps`
323
335
  # parameter to be `true`, regardless of whether you specify `false` for the
324
336
  # parameter.
325
337
  #
326
- # **Note:** Applies to US English, Japanese, and Spanish (both broadband and
327
- # narrowband models) and UK English (narrowband model) transcription only. To
328
- # determine whether a language model supports speaker labels, you can also use the
329
- # **Get a model** method and check that the attribute `speaker_labels` is set to
330
- # `true`.
338
+ # **Note:** Applies to US English, German, Japanese, Korean, and Spanish (both
339
+ # broadband and narrowband models) and UK English (narrowband model) transcription
340
+ # only. To determine whether a language model supports speaker labels, you can also
341
+ # use the **Get a model** method and check that the attribute `speaker_labels` is
342
+ # set to `true`.
331
343
  #
332
344
  # See [Speaker
333
- # labels](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#speaker_labels).
345
+ # labels](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#speaker_labels).
334
346
  # @param customization_id [String] **Deprecated.** Use the `language_customization_id` parameter to specify the
335
347
  # customization ID (GUID) of a custom language model that is to be used with the
336
348
  # recognition request. Do not specify both parameters with a request.
@@ -339,7 +351,7 @@ module IBMWatson
339
351
  # specify the name of the custom language model for which the grammar is defined.
340
352
  # The service recognizes only strings that are recognized by the specified grammar;
341
353
  # it does not recognize other custom words from the model's words resource. See
342
- # [Grammars](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#grammars-input).
354
+ # [Grammars](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#grammars-input).
343
355
  # @param redaction [Boolean] If `true`, the service redacts, or masks, numeric data from final transcripts. The
344
356
  # feature redacts any number that has three or more consecutive digits by replacing
345
357
  # each digit with an `X` character. It is intended to redact sensitive numeric data,
@@ -354,12 +366,67 @@ module IBMWatson
354
366
  # **Note:** Applies to US English, Japanese, and Korean transcription only.
355
367
  #
356
368
  # See [Numeric
357
- # redaction](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#redaction).
369
+ # redaction](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#redaction).
358
370
  # @param audio_metrics [Boolean] If `true`, requests detailed information about the signal characteristics of the
359
371
  # input audio. The service returns audio metrics with the final transcription
360
372
  # results. By default, the service returns no audio metrics.
373
+ #
374
+ # See [Audio
375
+ # metrics](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-metrics#audio_metrics).
376
+ # @param end_of_phrase_silence_time [Float] If `true`, specifies the duration of the pause interval at which the service
377
+ # splits a transcript into multiple final results. If the service detects pauses or
378
+ # extended silence before it reaches the end of the audio stream, its response can
379
+ # include multiple final results. Silence indicates a point at which the speaker
380
+ # pauses between spoken words or phrases.
381
+ #
382
+ # Specify a value for the pause interval in the range of 0.0 to 120.0.
383
+ # * A value greater than 0 specifies the interval that the service is to use for
384
+ # speech recognition.
385
+ # * A value of 0 indicates that the service is to use the default interval. It is
386
+ # equivalent to omitting the parameter.
387
+ #
388
+ # The default pause interval for most languages is 0.8 seconds; the default for
389
+ # Chinese is 0.6 seconds.
390
+ #
391
+ # See [End of phrase silence
392
+ # time](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#silence_time).
393
+ # @param split_transcript_at_phrase_end [Boolean] If `true`, directs the service to split the transcript into multiple final results
394
+ # based on semantic features of the input, for example, at the conclusion of
395
+ # meaningful phrases such as sentences. The service bases its understanding of
396
+ # semantic features on the base language model that you use with a request. Custom
397
+ # language models and grammars can also influence how and where the service splits a
398
+ # transcript. By default, the service splits transcripts based solely on the pause
399
+ # interval.
400
+ #
401
+ # See [Split transcript at phrase
402
+ # end](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#split_transcript).
403
+ # @param speech_detector_sensitivity [Float] The sensitivity of speech activity detection that the service is to perform. Use
404
+ # the parameter to suppress word insertions from music, coughing, and other
405
+ # non-speech events. The service biases the audio it passes for speech recognition
406
+ # by evaluating the input audio against prior models of speech and non-speech
407
+ # activity.
408
+ #
409
+ # Specify a value between 0.0 and 1.0:
410
+ # * 0.0 suppresses all audio (no speech is transcribed).
411
+ # * 0.5 (the default) provides a reasonable compromise for the level of sensitivity.
412
+ # * 1.0 suppresses no audio (speech detection sensitivity is disabled).
413
+ #
414
+ # The values increase on a monotonic curve. See [Speech Activity
415
+ # Detection](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#detection).
416
+ # @param background_audio_suppression [Float] The level to which the service is to suppress background audio based on its volume
417
+ # to prevent it from being transcribed as speech. Use the parameter to suppress side
418
+ # conversations or background noise.
419
+ #
420
+ # Specify a value in the range of 0.0 to 1.0:
421
+ # * 0.0 (the default) provides no suppression (background audio suppression is
422
+ # disabled).
423
+ # * 0.5 provides a reasonable level of audio suppression for general usage.
424
+ # * 1.0 suppresses all audio (no audio is transcribed).
425
+ #
426
+ # The values increase on a monotonic curve. See [Speech Activity
427
+ # Detection](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#detection).
361
428
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
362
- def recognize(audio:, content_type: nil, model: nil, language_customization_id: nil, acoustic_customization_id: nil, base_model_version: nil, customization_weight: nil, inactivity_timeout: nil, keywords: nil, keywords_threshold: nil, max_alternatives: nil, word_alternatives_threshold: nil, word_confidence: nil, timestamps: nil, profanity_filter: nil, smart_formatting: nil, speaker_labels: nil, customization_id: nil, grammar_name: nil, redaction: nil, audio_metrics: nil)
429
+ def recognize(audio:, content_type: nil, model: nil, language_customization_id: nil, acoustic_customization_id: nil, base_model_version: nil, customization_weight: nil, inactivity_timeout: nil, keywords: nil, keywords_threshold: nil, max_alternatives: nil, word_alternatives_threshold: nil, word_confidence: nil, timestamps: nil, profanity_filter: nil, smart_formatting: nil, speaker_labels: nil, customization_id: nil, grammar_name: nil, redaction: nil, audio_metrics: nil, end_of_phrase_silence_time: nil, split_transcript_at_phrase_end: nil, speech_detector_sensitivity: nil, background_audio_suppression: nil)
363
430
  raise ArgumentError.new("audio must be provided") if audio.nil?
364
431
 
365
432
  headers = {
@@ -388,7 +455,11 @@ module IBMWatson
388
455
  "customization_id" => customization_id,
389
456
  "grammar_name" => grammar_name,
390
457
  "redaction" => redaction,
391
- "audio_metrics" => audio_metrics
458
+ "audio_metrics" => audio_metrics,
459
+ "end_of_phrase_silence_time" => end_of_phrase_silence_time,
460
+ "split_transcript_at_phrase_end" => split_transcript_at_phrase_end,
461
+ "speech_detector_sensitivity" => speech_detector_sensitivity,
462
+ "background_audio_suppression" => background_audio_suppression
392
463
  }
393
464
 
394
465
  data = audio
@@ -407,7 +478,7 @@ module IBMWatson
407
478
  end
408
479
 
409
480
  ##
410
- # @!method recognize_using_websocket(content_type: nil,recognize_callback:,audio: nil,chunk_data: false,model: nil,customization_id: nil,acoustic_customization_id: nil,customization_weight: nil,base_model_version: nil,inactivity_timeout: nil,interim_results: nil,keywords: nil,keywords_threshold: nil,max_alternatives: nil,word_alternatives_threshold: nil,word_confidence: nil,timestamps: nil,profanity_filter: nil,smart_formatting: nil,speaker_labels: nil)
481
+ # @!method recognize_using_websocket(content_type: nil,recognize_callback:,audio: nil,chunk_data: false,model: nil,customization_id: nil,acoustic_customization_id: nil,customization_weight: nil,base_model_version: nil,inactivity_timeout: nil,interim_results: nil,keywords: nil,keywords_threshold: nil,max_alternatives: nil,word_alternatives_threshold: nil,word_confidence: nil,timestamps: nil,profanity_filter: nil,smart_formatting: nil,speaker_labels: nil, end_of_phrase_silence_time: nil, split_transcript_at_phrase_end: nil, speech_detector_sensitivity: nil, background_audio_suppression: nil)
411
482
  # Sends audio for speech recognition using web sockets.
412
483
  # @param content_type [String] The type of the input: audio/basic, audio/flac, audio/l16, audio/mp3, audio/mpeg, audio/mulaw, audio/ogg, audio/ogg;codecs=opus, audio/ogg;codecs=vorbis, audio/wav, audio/webm, audio/webm;codecs=opus, audio/webm;codecs=vorbis, or multipart/form-data.
413
484
  # @param recognize_callback [RecognizeCallback] The instance handling events returned from the service.
@@ -417,7 +488,7 @@ module IBMWatson
417
488
  # @param customization_id [String] The GUID of a custom language model that is to be used with the request. The base model of the specified custom language model must match the model specified with the `model` parameter. You must make the request with service credentials created for the instance of the service that owns the custom model. By default, no custom language model is used.
418
489
  # @param acoustic_customization_id [String] The GUID of a custom acoustic model that is to be used with the request. The base model of the specified custom acoustic model must match the model specified with the `model` parameter. You must make the request with service credentials created for the instance of the service that owns the custom model. By default, no custom acoustic model is used.
419
490
  # @param language_customization_id [String] The GUID of a custom language model that is to be used with the request. The base model of the specified custom language model must match the model specified with the `model` parameter. You must make the request with service credentials created for the instance of the service that owns the custom model. By default, no custom language model is used.
420
- # @param base_model_version [String] The version of the specified base `model` that is to be used for speech recognition. Multiple versions of a base model can exist when a model is updated for internal improvements. The parameter is intended primarily for use with custom models that have been upgraded for a new base model. The default value depends on whether the parameter is used with or without a custom model. For more information, see [Base model version](https://console.bluemix.net/docs/services/speech-to-text/input.html#version).
491
+ # @param base_model_version [String] The version of the specified base `model` that is to be used for speech recognition. Multiple versions of a base model can exist when a model is updated for internal improvements. The parameter is intended primarily for use with custom models that have been upgraded for a new base model. The default value depends on whether the parameter is used with or without a custom model. For more information, see [Base model version](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#version).
421
492
  # @param inactivity_timeout [Integer] The time in seconds after which, if only silence (no speech) is detected in submitted audio, the connection is closed with a 400 error. Useful for stopping audio submission from a live microphone when a user simply walks away. Use `-1` for infinity.
422
493
  # @param interim_results [Boolean] Send back non-final previews of each "sentence" as it is being processed. These results are ignored in text mode.
423
494
  # @param keywords [Array<String>] Array of keyword strings to spot in the audio. Each keyword string can include one or more tokens. Keywords are spotted only in the final hypothesis, not in interim results. If you specify any keywords, you must also specify a keywords threshold. Omit the parameter or specify an empty array if you do not need to spot keywords.
@@ -428,13 +499,13 @@ module IBMWatson
428
499
  # @param timestamps [Boolean] If `true`, time alignment for each word is returned.
429
500
  # @param profanity_filter [Boolean] If `true` (the default), filters profanity from all output except for keyword results by replacing inappropriate words with a series of asterisks. Set the parameter to `false` to return results with no censoring. Applies to US English transcription only.
430
501
  # @param smart_formatting [Boolean] If `true`, converts dates, times, series of digits and numbers, phone numbers, currency values, and Internet addresses into more readable, conventional representations in the final transcript of a recognition request. If `false` (the default), no formatting is performed. Applies to US English transcription only.
431
- # @param speaker_labels [Boolean] Indicates whether labels that identify which words were spoken by which participants in a multi-person exchange are to be included in the response. The default is `false`; no speaker labels are returned. Setting `speaker_labels` to `true` forces the `timestamps` parameter to be `true`, regardless of whether you specify `false` for the parameter. To determine whether a language model supports speaker labels, use the `GET /v1/models` method and check that the attribute `speaker_labels` is set to `true`. You can also refer to [Speaker labels](https://console.bluemix.net/docs/services/speech-to-text/output.html#speaker_labels).
502
+ # @param speaker_labels [Boolean] Indicates whether labels that identify which words were spoken by which participants in a multi-person exchange are to be included in the response. The default is `false`; no speaker labels are returned. Setting `speaker_labels` to `true` forces the `timestamps` parameter to be `true`, regardless of whether you specify `false` for the parameter. To determine whether a language model supports speaker labels, use the `GET /v1/models` method and check that the attribute `speaker_labels` is set to `true`. You can also refer to [Speaker labels](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#speaker_labels).
432
503
  # @param grammar_name [String] The name of a grammar that is to be used with the recognition request. If you
433
504
  # specify a grammar, you must also use the `language_customization_id` parameter to
434
505
  # specify the name of the custom language model for which the grammar is defined.
435
506
  # The service recognizes only strings that are recognized by the specified grammar;
436
507
  # it does not recognize other custom words from the model's words resource. See
437
- # [Grammars](https://cloud.ibm.com/docs/services/speech-to-text/output.html).
508
+ # [Grammars](https://cloud.ibm.com/docs/speech-to-text/output.html).
438
509
  # @param redaction [Boolean] If `true`, the service redacts, or masks, numeric data from final transcripts. The
439
510
  # feature redacts any number that has three or more consecutive digits by replacing
440
511
  # each digit with an `X` character. It is intended to redact sensitive numeric data,
@@ -449,7 +520,7 @@ module IBMWatson
449
520
  # **Note:** Applies to US English, Japanese, and Korean transcription only.
450
521
  #
451
522
  # See [Numeric
452
- # redaction](https://cloud.ibm.com/docs/services/speech-to-text/output.html#redaction).
523
+ # redaction](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#redaction).
453
524
  #
454
525
  # @param processing_metrics [Boolean] If `true`, requests processing metrics about the service's transcription of the
455
526
  # input audio. The service returns processing metrics at the interval specified by
@@ -469,6 +540,62 @@ module IBMWatson
469
540
  # input audio. The service returns audio metrics with the final transcription
470
541
  # results. By default, the service returns no audio metrics.
471
542
  # @return [WebSocketClient] Returns a new WebSocketClient object
543
+ #
544
+ # See [Audio
545
+ # metrics](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-metrics#audio_metrics).
546
+ # @param end_of_phrase_silence_time [Float] If `true`, specifies the duration of the pause interval at which the service
547
+ # splits a transcript into multiple final results. If the service detects pauses or
548
+ # extended silence before it reaches the end of the audio stream, its response can
549
+ # include multiple final results. Silence indicates a point at which the speaker
550
+ # pauses between spoken words or phrases.
551
+ #
552
+ # Specify a value for the pause interval in the range of 0.0 to 120.0.
553
+ # * A value greater than 0 specifies the interval that the service is to use for
554
+ # speech recognition.
555
+ # * A value of 0 indicates that the service is to use the default interval. It is
556
+ # equivalent to omitting the parameter.
557
+ #
558
+ # The default pause interval for most languages is 0.8 seconds; the default for
559
+ # Chinese is 0.6 seconds.
560
+ #
561
+ # See [End of phrase silence
562
+ # time](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#silence_time).
563
+ # @param split_transcript_at_phrase_end [Boolean] If `true`, directs the service to split the transcript into multiple final results
564
+ # based on semantic features of the input, for example, at the conclusion of
565
+ # meaningful phrases such as sentences. The service bases its understanding of
566
+ # semantic features on the base language model that you use with a request. Custom
567
+ # language models and grammars can also influence how and where the service splits a
568
+ # transcript. By default, the service splits transcripts based solely on the pause
569
+ # interval.
570
+ #
571
+ # See [Split transcript at phrase
572
+ # end](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#split_transcript).
573
+ # @param speech_detector_sensitivity [Float] The sensitivity of speech activity detection that the service is to perform. Use
574
+ # the parameter to suppress word insertions from music, coughing, and other
575
+ # non-speech events. The service biases the audio it passes for speech recognition
576
+ # by evaluating the input audio against prior models of speech and non-speech
577
+ # activity.
578
+ #
579
+ # Specify a value between 0.0 and 1.0:
580
+ # * 0.0 suppresses all audio (no speech is transcribed).
581
+ # * 0.5 (the default) provides a reasonable compromise for the level of sensitivity.
582
+ # * 1.0 suppresses no audio (speech detection sensitivity is disabled).
583
+ #
584
+ # The values increase on a monotonic curve. See [Speech Activity
585
+ # Detection](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#detection).
586
+ # @param background_audio_suppression [Float] The level to which the service is to suppress background audio based on its volume
587
+ # to prevent it from being transcribed as speech. Use the parameter to suppress side
588
+ # conversations or background noise.
589
+ #
590
+ # Specify a value in the range of 0.0 to 1.0:
591
+ # * 0.0 (the default) provides no suppression (background audio suppression is
592
+ # disabled).
593
+ # * 0.5 provides a reasonable level of audio suppression for general usage.
594
+ # * 1.0 suppresses all audio (no audio is transcribed).
595
+ #
596
+ # The values increase on a monotonic curve. See [Speech Activity
597
+ # Detection](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#detection).
598
+ # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
472
599
  def recognize_using_websocket(
473
600
  content_type: nil,
474
601
  recognize_callback:,
@@ -495,7 +622,11 @@ module IBMWatson
495
622
  redaction: nil,
496
623
  processing_metrics: nil,
497
624
  processing_metrics_interval: nil,
498
- audio_metrics: nil
625
+ audio_metrics: nil,
626
+ end_of_phrase_silence_time: nil,
627
+ split_transcript_at_phrase_end: nil,
628
+ speech_detector_sensitivity: nil,
629
+ background_audio_suppression: nil
499
630
  )
500
631
  raise ArgumentError("Audio must be provided") if audio.nil? && !chunk_data
501
632
  raise ArgumentError("Recognize callback must be provided") if recognize_callback.nil?
@@ -504,6 +635,7 @@ module IBMWatson
504
635
  require_relative("./websocket/speech_to_text_websocket_listener.rb")
505
636
  headers = {}
506
637
  headers = conn.default_options.headers.to_hash unless conn.default_options.headers.to_hash.empty?
638
+ @authenticator.authenticate(headers)
507
639
  service_url = @service_url.gsub("https:", "wss:")
508
640
  params = {
509
641
  "model" => model,
@@ -532,7 +664,11 @@ module IBMWatson
532
664
  "redaction" => redaction,
533
665
  "processing_metrics" => processing_metrics,
534
666
  "processing_metrics_interval" => processing_metrics_interval,
535
- "audio_metrics" => audio_metrics
667
+ "audio_metrics" => audio_metrics,
668
+ "end_of_phrase_silence_time" => end_of_phrase_silence_time,
669
+ "split_transcript_at_phrase_end" => split_transcript_at_phrase_end,
670
+ "speech_detector_sensitivity" => speech_detector_sensitivity,
671
+ "background_audio_suppression" => background_audio_suppression
536
672
  }
537
673
  options.delete_if { |_, v| v.nil? }
538
674
  WebSocketClient.new(audio: audio, chunk_data: chunk_data, options: options, recognize_callback: recognize_callback, service_url: service_url, headers: headers, disable_ssl_verification: @disable_ssl_verification)
@@ -577,7 +713,7 @@ module IBMWatson
577
713
  # a one-hour span of time.
578
714
  #
579
715
  # **See also:** [Registering a callback
580
- # URL](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-async#register).
716
+ # URL](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-async#register).
581
717
  # @param callback_url [String] An HTTP or HTTPS URL to which callback notifications are to be sent. To be
582
718
  # white-listed, the URL must successfully echo the challenge string during URL
583
719
  # verification. During verification, the client can also check the signature that
@@ -622,7 +758,7 @@ module IBMWatson
622
758
  # URL can no longer be used with asynchronous recognition requests.
623
759
  #
624
760
  # **See also:** [Unregistering a callback
625
- # URL](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-async#unregister).
761
+ # URL](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-async#unregister).
626
762
  # @param callback_url [String] The callback URL that is to be unregistered.
627
763
  # @return [nil]
628
764
  def unregister_callback(callback_url:)
@@ -650,7 +786,7 @@ module IBMWatson
650
786
  end
651
787
 
652
788
  ##
653
- # @!method create_job(audio:, content_type: nil, model: nil, callback_url: nil, events: nil, user_token: nil, results_ttl: nil, language_customization_id: nil, acoustic_customization_id: nil, base_model_version: nil, customization_weight: nil, inactivity_timeout: nil, keywords: nil, keywords_threshold: nil, max_alternatives: nil, word_alternatives_threshold: nil, word_confidence: nil, timestamps: nil, profanity_filter: nil, smart_formatting: nil, speaker_labels: nil, customization_id: nil, grammar_name: nil, redaction: nil, processing_metrics: nil, processing_metrics_interval: nil, audio_metrics: nil)
789
+ # @!method create_job(audio:, content_type: nil, model: nil, callback_url: nil, events: nil, user_token: nil, results_ttl: nil, language_customization_id: nil, acoustic_customization_id: nil, base_model_version: nil, customization_weight: nil, inactivity_timeout: nil, keywords: nil, keywords_threshold: nil, max_alternatives: nil, word_alternatives_threshold: nil, word_confidence: nil, timestamps: nil, profanity_filter: nil, smart_formatting: nil, speaker_labels: nil, customization_id: nil, grammar_name: nil, redaction: nil, processing_metrics: nil, processing_metrics_interval: nil, audio_metrics: nil, end_of_phrase_silence_time: nil, split_transcript_at_phrase_end: nil, speech_detector_sensitivity: nil, background_audio_suppression: nil)
654
790
  # Create a job.
655
791
  # Creates a job for a new asynchronous recognition request. The job is owned by the
656
792
  # instance of the service whose credentials are used to create it. How you learn the
@@ -690,7 +826,7 @@ module IBMWatson
690
826
  # option to upload the file for the request.)
691
827
  #
692
828
  # **See also:** [Creating a
693
- # job](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-async#create).
829
+ # job](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-async#create).
694
830
  #
695
831
  #
696
832
  # ### Streaming mode
@@ -705,9 +841,9 @@ module IBMWatson
705
841
  #
706
842
  # **See also:**
707
843
  # * [Audio
708
- # transmission](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#transmission)
844
+ # transmission](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#transmission)
709
845
  # *
710
- # [Timeouts](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#timeouts)
846
+ # [Timeouts](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#timeouts)
711
847
  #
712
848
  #
713
849
  # ### Audio formats (content types)
@@ -747,13 +883,13 @@ module IBMWatson
747
883
  # fails.
748
884
  #
749
885
  # **See also:** [Audio
750
- # formats](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-audio-formats#audio-formats).
886
+ # formats](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-audio-formats#audio-formats).
751
887
  # @param audio [String] The audio to transcribe.
752
888
  # @param content_type [String] The format (MIME type) of the audio. For more information about specifying an
753
889
  # audio format, see **Audio formats (content types)** in the method description.
754
890
  # @param model [String] The identifier of the model that is to be used for the recognition request. See
755
891
  # [Languages and
756
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-models#models).
892
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-models#models).
757
893
  # @param callback_url [String] A URL to which callback notifications are to be sent. The URL must already be
758
894
  # successfully white-listed by using the **Register a callback** method. You can
759
895
  # include the same callback URL with any number of job creation requests. Omit the
@@ -793,7 +929,7 @@ module IBMWatson
793
929
  # match the model specified with the `model` parameter. You must make the request
794
930
  # with credentials for the instance of the service that owns the custom model. By
795
931
  # default, no custom language model is used. See [Custom
796
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#custom-input).
932
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#custom-input).
797
933
  #
798
934
  #
799
935
  # **Note:** Use this parameter instead of the deprecated `customization_id`
@@ -803,13 +939,13 @@ module IBMWatson
803
939
  # match the model specified with the `model` parameter. You must make the request
804
940
  # with credentials for the instance of the service that owns the custom model. By
805
941
  # default, no custom acoustic model is used. See [Custom
806
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#custom-input).
942
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#custom-input).
807
943
  # @param base_model_version [String] The version of the specified base model that is to be used with the recognition
808
944
  # request. Multiple versions of a base model can exist when a model is updated for
809
945
  # internal improvements. The parameter is intended primarily for use with custom
810
946
  # models that have been upgraded for a new base model. The default value depends on
811
947
  # whether the parameter is used with or without a custom model. See [Base model
812
- # version](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#version).
948
+ # version](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#version).
813
949
  # @param customization_weight [Float] If you specify the customization ID (GUID) of a custom language model with the
814
950
  # recognition request, the customization weight tells the service how much weight to
815
951
  # give to words from the custom language model compared to those from the base model
@@ -827,45 +963,51 @@ module IBMWatson
827
963
  # phrases.
828
964
  #
829
965
  # See [Custom
830
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#custom-input).
966
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#custom-input).
831
967
  # @param inactivity_timeout [Fixnum] The time in seconds after which, if only silence (no speech) is detected in
832
968
  # streaming audio, the connection is closed with a 400 error. The parameter is
833
969
  # useful for stopping audio submission from a live microphone when a user simply
834
970
  # walks away. Use `-1` for infinity. See [Inactivity
835
- # timeout](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#timeouts-inactivity).
971
+ # timeout](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#timeouts-inactivity).
836
972
  # @param keywords [Array[String]] An array of keyword strings to spot in the audio. Each keyword string can include
837
973
  # one or more string tokens. Keywords are spotted only in the final results, not in
838
974
  # interim hypotheses. If you specify any keywords, you must also specify a keywords
839
- # threshold. You can spot a maximum of 1000 keywords. Omit the parameter or specify
840
- # an empty array if you do not need to spot keywords. See [Keyword
841
- # spotting](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#keyword_spotting).
975
+ # threshold. Omit the parameter or specify an empty array if you do not need to spot
976
+ # keywords.
977
+ #
978
+ # You can spot a maximum of 1000 keywords with a single request. A single keyword
979
+ # can have a maximum length of 1024 characters, though the maximum effective length
980
+ # for double-byte languages might be shorter. Keywords are case-insensitive.
981
+ #
982
+ # See [Keyword
983
+ # spotting](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#keyword_spotting).
842
984
  # @param keywords_threshold [Float] A confidence value that is the lower bound for spotting a keyword. A word is
843
985
  # considered to match a keyword if its confidence is greater than or equal to the
844
986
  # threshold. Specify a probability between 0.0 and 1.0. If you specify a threshold,
845
987
  # you must also specify one or more keywords. The service performs no keyword
846
988
  # spotting if you omit either parameter. See [Keyword
847
- # spotting](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#keyword_spotting).
989
+ # spotting](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#keyword_spotting).
848
990
  # @param max_alternatives [Fixnum] The maximum number of alternative transcripts that the service is to return. By
849
991
  # default, the service returns a single transcript. If you specify a value of `0`,
850
992
  # the service uses the default value, `1`. See [Maximum
851
- # alternatives](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#max_alternatives).
993
+ # alternatives](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#max_alternatives).
852
994
  # @param word_alternatives_threshold [Float] A confidence value that is the lower bound for identifying a hypothesis as a
853
995
  # possible word alternative (also known as "Confusion Networks"). An alternative
854
996
  # word is considered if its confidence is greater than or equal to the threshold.
855
997
  # Specify a probability between 0.0 and 1.0. By default, the service computes no
856
998
  # alternative words. See [Word
857
- # alternatives](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#word_alternatives).
999
+ # alternatives](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#word_alternatives).
858
1000
  # @param word_confidence [Boolean] If `true`, the service returns a confidence measure in the range of 0.0 to 1.0 for
859
1001
  # each word. By default, the service returns no word confidence scores. See [Word
860
- # confidence](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#word_confidence).
1002
+ # confidence](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#word_confidence).
861
1003
  # @param timestamps [Boolean] If `true`, the service returns time alignment for each word. By default, no
862
1004
  # timestamps are returned. See [Word
863
- # timestamps](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#word_timestamps).
1005
+ # timestamps](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#word_timestamps).
864
1006
  # @param profanity_filter [Boolean] If `true`, the service filters profanity from all output except for keyword
865
1007
  # results by replacing inappropriate words with a series of asterisks. Set the
866
1008
  # parameter to `false` to return results with no censoring. Applies to US English
867
1009
  # transcription only. See [Profanity
868
- # filtering](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#profanity_filter).
1010
+ # filtering](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#profanity_filter).
869
1011
  # @param smart_formatting [Boolean] If `true`, the service converts dates, times, series of digits and numbers, phone
870
1012
  # numbers, currency values, and internet addresses into more readable, conventional
871
1013
  # representations in the final transcript of a recognition request. For US English,
@@ -875,21 +1017,21 @@ module IBMWatson
875
1017
  # **Note:** Applies to US English, Japanese, and Spanish transcription only.
876
1018
  #
877
1019
  # See [Smart
878
- # formatting](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#smart_formatting).
1020
+ # formatting](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#smart_formatting).
879
1021
  # @param speaker_labels [Boolean] If `true`, the response includes labels that identify which words were spoken by
880
1022
  # which participants in a multi-person exchange. By default, the service returns no
881
1023
  # speaker labels. Setting `speaker_labels` to `true` forces the `timestamps`
882
1024
  # parameter to be `true`, regardless of whether you specify `false` for the
883
1025
  # parameter.
884
1026
  #
885
- # **Note:** Applies to US English, Japanese, and Spanish (both broadband and
886
- # narrowband models) and UK English (narrowband model) transcription only. To
887
- # determine whether a language model supports speaker labels, you can also use the
888
- # **Get a model** method and check that the attribute `speaker_labels` is set to
889
- # `true`.
1027
+ # **Note:** Applies to US English, German, Japanese, Korean, and Spanish (both
1028
+ # broadband and narrowband models) and UK English (narrowband model) transcription
1029
+ # only. To determine whether a language model supports speaker labels, you can also
1030
+ # use the **Get a model** method and check that the attribute `speaker_labels` is
1031
+ # set to `true`.
890
1032
  #
891
1033
  # See [Speaker
892
- # labels](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#speaker_labels).
1034
+ # labels](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#speaker_labels).
893
1035
  # @param customization_id [String] **Deprecated.** Use the `language_customization_id` parameter to specify the
894
1036
  # customization ID (GUID) of a custom language model that is to be used with the
895
1037
  # recognition request. Do not specify both parameters with a request.
@@ -898,7 +1040,7 @@ module IBMWatson
898
1040
  # specify the name of the custom language model for which the grammar is defined.
899
1041
  # The service recognizes only strings that are recognized by the specified grammar;
900
1042
  # it does not recognize other custom words from the model's words resource. See
901
- # [Grammars](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-input#grammars-input).
1043
+ # [Grammars](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#grammars-input).
902
1044
  # @param redaction [Boolean] If `true`, the service redacts, or masks, numeric data from final transcripts. The
903
1045
  # feature redacts any number that has three or more consecutive digits by replacing
904
1046
  # each digit with an `X` character. It is intended to redact sensitive numeric data,
@@ -913,12 +1055,15 @@ module IBMWatson
913
1055
  # **Note:** Applies to US English, Japanese, and Korean transcription only.
914
1056
  #
915
1057
  # See [Numeric
916
- # redaction](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#redaction).
1058
+ # redaction](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#redaction).
917
1059
  # @param processing_metrics [Boolean] If `true`, requests processing metrics about the service's transcription of the
918
1060
  # input audio. The service returns processing metrics at the interval specified by
919
1061
  # the `processing_metrics_interval` parameter. It also returns processing metrics
920
1062
  # for transcription events, for example, for final and interim results. By default,
921
1063
  # the service returns no processing metrics.
1064
+ #
1065
+ # See [Processing
1066
+ # metrics](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-metrics#processing_metrics).
922
1067
  # @param processing_metrics_interval [Float] Specifies the interval in real wall-clock seconds at which the service is to
923
1068
  # return processing metrics. The parameter is ignored unless the
924
1069
  # `processing_metrics` parameter is set to `true`.
@@ -930,11 +1075,69 @@ module IBMWatson
930
1075
  # metrics only for transcription events instead of at periodic intervals, set the
931
1076
  # value to a large number. If the value is larger than the duration of the audio,
932
1077
  # the service returns processing metrics only for transcription events.
1078
+ #
1079
+ # See [Processing
1080
+ # metrics](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-metrics#processing_metrics).
933
1081
  # @param audio_metrics [Boolean] If `true`, requests detailed information about the signal characteristics of the
934
1082
  # input audio. The service returns audio metrics with the final transcription
935
1083
  # results. By default, the service returns no audio metrics.
1084
+ #
1085
+ # See [Audio
1086
+ # metrics](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-metrics#audio_metrics).
1087
+ # @param end_of_phrase_silence_time [Float] If `true`, specifies the duration of the pause interval at which the service
1088
+ # splits a transcript into multiple final results. If the service detects pauses or
1089
+ # extended silence before it reaches the end of the audio stream, its response can
1090
+ # include multiple final results. Silence indicates a point at which the speaker
1091
+ # pauses between spoken words or phrases.
1092
+ #
1093
+ # Specify a value for the pause interval in the range of 0.0 to 120.0.
1094
+ # * A value greater than 0 specifies the interval that the service is to use for
1095
+ # speech recognition.
1096
+ # * A value of 0 indicates that the service is to use the default interval. It is
1097
+ # equivalent to omitting the parameter.
1098
+ #
1099
+ # The default pause interval for most languages is 0.8 seconds; the default for
1100
+ # Chinese is 0.6 seconds.
1101
+ #
1102
+ # See [End of phrase silence
1103
+ # time](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#silence_time).
1104
+ # @param split_transcript_at_phrase_end [Boolean] If `true`, directs the service to split the transcript into multiple final results
1105
+ # based on semantic features of the input, for example, at the conclusion of
1106
+ # meaningful phrases such as sentences. The service bases its understanding of
1107
+ # semantic features on the base language model that you use with a request. Custom
1108
+ # language models and grammars can also influence how and where the service splits a
1109
+ # transcript. By default, the service splits transcripts based solely on the pause
1110
+ # interval.
1111
+ #
1112
+ # See [Split transcript at phrase
1113
+ # end](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-output#split_transcript).
1114
+ # @param speech_detector_sensitivity [Float] The sensitivity of speech activity detection that the service is to perform. Use
1115
+ # the parameter to suppress word insertions from music, coughing, and other
1116
+ # non-speech events. The service biases the audio it passes for speech recognition
1117
+ # by evaluating the input audio against prior models of speech and non-speech
1118
+ # activity.
1119
+ #
1120
+ # Specify a value between 0.0 and 1.0:
1121
+ # * 0.0 suppresses all audio (no speech is transcribed).
1122
+ # * 0.5 (the default) provides a reasonable compromise for the level of sensitivity.
1123
+ # * 1.0 suppresses no audio (speech detection sensitivity is disabled).
1124
+ #
1125
+ # The values increase on a monotonic curve. See [Speech Activity
1126
+ # Detection](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#detection).
1127
+ # @param background_audio_suppression [Float] The level to which the service is to suppress background audio based on its volume
1128
+ # to prevent it from being transcribed as speech. Use the parameter to suppress side
1129
+ # conversations or background noise.
1130
+ #
1131
+ # Specify a value in the range of 0.0 to 1.0:
1132
+ # * 0.0 (the default) provides no suppression (background audio suppression is
1133
+ # disabled).
1134
+ # * 0.5 provides a reasonable level of audio suppression for general usage.
1135
+ # * 1.0 suppresses all audio (no audio is transcribed).
1136
+ #
1137
+ # The values increase on a monotonic curve. See [Speech Activity
1138
+ # Detection](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-input#detection).
936
1139
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
937
- def create_job(audio:, content_type: nil, model: nil, callback_url: nil, events: nil, user_token: nil, results_ttl: nil, language_customization_id: nil, acoustic_customization_id: nil, base_model_version: nil, customization_weight: nil, inactivity_timeout: nil, keywords: nil, keywords_threshold: nil, max_alternatives: nil, word_alternatives_threshold: nil, word_confidence: nil, timestamps: nil, profanity_filter: nil, smart_formatting: nil, speaker_labels: nil, customization_id: nil, grammar_name: nil, redaction: nil, processing_metrics: nil, processing_metrics_interval: nil, audio_metrics: nil)
1140
+ def create_job(audio:, content_type: nil, model: nil, callback_url: nil, events: nil, user_token: nil, results_ttl: nil, language_customization_id: nil, acoustic_customization_id: nil, base_model_version: nil, customization_weight: nil, inactivity_timeout: nil, keywords: nil, keywords_threshold: nil, max_alternatives: nil, word_alternatives_threshold: nil, word_confidence: nil, timestamps: nil, profanity_filter: nil, smart_formatting: nil, speaker_labels: nil, customization_id: nil, grammar_name: nil, redaction: nil, processing_metrics: nil, processing_metrics_interval: nil, audio_metrics: nil, end_of_phrase_silence_time: nil, split_transcript_at_phrase_end: nil, speech_detector_sensitivity: nil, background_audio_suppression: nil)
938
1141
  raise ArgumentError.new("audio must be provided") if audio.nil?
939
1142
 
940
1143
  headers = {
@@ -969,7 +1172,11 @@ module IBMWatson
969
1172
  "redaction" => redaction,
970
1173
  "processing_metrics" => processing_metrics,
971
1174
  "processing_metrics_interval" => processing_metrics_interval,
972
- "audio_metrics" => audio_metrics
1175
+ "audio_metrics" => audio_metrics,
1176
+ "end_of_phrase_silence_time" => end_of_phrase_silence_time,
1177
+ "split_transcript_at_phrase_end" => split_transcript_at_phrase_end,
1178
+ "speech_detector_sensitivity" => speech_detector_sensitivity,
1179
+ "background_audio_suppression" => background_audio_suppression
973
1180
  }
974
1181
 
975
1182
  data = audio
@@ -1000,7 +1207,7 @@ module IBMWatson
1000
1207
  # first.
1001
1208
  #
1002
1209
  # **See also:** [Checking the status of the latest
1003
- # jobs](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-async#jobs).
1210
+ # jobs](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-async#jobs).
1004
1211
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
1005
1212
  def check_jobs
1006
1213
  headers = {
@@ -1035,7 +1242,7 @@ module IBMWatson
1035
1242
  # recent jobs associated with the calling credentials.
1036
1243
  #
1037
1244
  # **See also:** [Checking the status and retrieving the results of a
1038
- # job](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-async#job).
1245
+ # job](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-async#job).
1039
1246
  # @param id [String] The identifier of the asynchronous job that is to be used for the request. You
1040
1247
  # must make the request with credentials for the instance of the service that owns
1041
1248
  # the job.
@@ -1069,7 +1276,7 @@ module IBMWatson
1069
1276
  # owns a job to delete it.
1070
1277
  #
1071
1278
  # **See also:** [Deleting a
1072
- # job](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-async#delete-async).
1279
+ # job](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-async#delete-async).
1073
1280
  # @param id [String] The identifier of the asynchronous job that is to be used for the request. You
1074
1281
  # must make the request with credentials for the instance of the service that owns
1075
1282
  # the job.
@@ -1104,13 +1311,13 @@ module IBMWatson
1104
1311
  # model is owned by the instance of the service whose credentials are used to create
1105
1312
  # it.
1106
1313
  #
1107
- # You can create a maximum of 1024 custom language models, per credential. The
1108
- # service returns an error if you attempt to create more than 1024 models. You do
1109
- # not lose any models, but you cannot create any more until your model count is
1314
+ # You can create a maximum of 1024 custom language models per owning credentials.
1315
+ # The service returns an error if you attempt to create more than 1024 models. You
1316
+ # do not lose any models, but you cannot create any more until your model count is
1110
1317
  # below the limit.
1111
1318
  #
1112
1319
  # **See also:** [Create a custom language
1113
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-languageCreate#createModel-language).
1320
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-languageCreate#createModel-language).
1114
1321
  # @param name [String] A user-defined name for the new custom language model. Use a name that is unique
1115
1322
  # among all custom language models that you own. Use a localized name that matches
1116
1323
  # the language of the custom model. Use a name that describes the domain of the
@@ -1122,7 +1329,7 @@ module IBMWatson
1122
1329
  # To determine whether a base model supports language model customization, use the
1123
1330
  # **Get a model** method and check that the attribute `custom_language_model` is set
1124
1331
  # to `true`. You can also refer to [Language support for
1125
- # customization](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-customization#languageSupport).
1332
+ # customization](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-customization#languageSupport).
1126
1333
  # @param dialect [String] The dialect of the specified language that is to be used with the custom language
1127
1334
  # model. For most languages, the dialect matches the language of the base model by
1128
1335
  # default. For example, `en-US` is used for either of the US English language
@@ -1184,7 +1391,7 @@ module IBMWatson
1184
1391
  # a model to list information about it.
1185
1392
  #
1186
1393
  # **See also:** [Listing custom language
1187
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageLanguageModels#listModels-language).
1394
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageLanguageModels#listModels-language).
1188
1395
  # @param language [String] The identifier of the language for which custom language or custom acoustic models
1189
1396
  # are to be returned (for example, `en-US`). Omit the parameter to see all custom
1190
1397
  # language or custom acoustic models that are owned by the requesting credentials.
@@ -1218,7 +1425,7 @@ module IBMWatson
1218
1425
  # for the instance of the service that owns a model to list information about it.
1219
1426
  #
1220
1427
  # **See also:** [Listing custom language
1221
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageLanguageModels#listModels-language).
1428
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageLanguageModels#listModels-language).
1222
1429
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1223
1430
  # the request. You must make the request with credentials for the instance of the
1224
1431
  # service that owns the custom model.
@@ -1251,7 +1458,7 @@ module IBMWatson
1251
1458
  # owns a model to delete it.
1252
1459
  #
1253
1460
  # **See also:** [Deleting a custom language
1254
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageLanguageModels#deleteModel-language).
1461
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageLanguageModels#deleteModel-language).
1255
1462
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1256
1463
  # the request. You must make the request with credentials for the instance of the
1257
1464
  # service that owns the custom model.
@@ -1299,7 +1506,7 @@ module IBMWatson
1299
1506
  # requests to add new resources until the existing request completes.
1300
1507
  #
1301
1508
  # **See also:** [Train the custom language
1302
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-languageCreate#trainModel-language).
1509
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-languageCreate#trainModel-language).
1303
1510
  #
1304
1511
  #
1305
1512
  # ### Training failures
@@ -1375,7 +1582,7 @@ module IBMWatson
1375
1582
  # it.
1376
1583
  #
1377
1584
  # **See also:** [Resetting a custom language
1378
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageLanguageModels#resetModel-language).
1585
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageLanguageModels#resetModel-language).
1379
1586
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1380
1587
  # the request. You must make the request with credentials for the instance of the
1381
1588
  # service that owns the custom model.
@@ -1419,7 +1626,7 @@ module IBMWatson
1419
1626
  # subsequent requests for the model until the upgrade completes.
1420
1627
  #
1421
1628
  # **See also:** [Upgrading a custom language
1422
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-customUpgrade#upgradeLanguage).
1629
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-customUpgrade#upgradeLanguage).
1423
1630
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1424
1631
  # the request. You must make the request with credentials for the instance of the
1425
1632
  # service that owns the custom model.
@@ -1455,7 +1662,7 @@ module IBMWatson
1455
1662
  # that owns a model to list its corpora.
1456
1663
  #
1457
1664
  # **See also:** [Listing corpora for a custom language
1458
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageCorpora#listCorpora).
1665
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageCorpora#listCorpora).
1459
1666
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1460
1667
  # the request. You must make the request with credentials for the instance of the
1461
1668
  # service that owns the custom model.
@@ -1495,18 +1702,20 @@ module IBMWatson
1495
1702
  #
1496
1703
  # The call returns an HTTP 201 response code if the corpus is valid. The service
1497
1704
  # then asynchronously processes the contents of the corpus and automatically
1498
- # extracts new words that it finds. This can take on the order of a minute or two to
1499
- # complete depending on the total number of words and the number of new words in the
1500
- # corpus, as well as the current load on the service. You cannot submit requests to
1501
- # add additional resources to the custom model or to train the model until the
1705
+ # extracts new words that it finds. This operation can take on the order of minutes
1706
+ # to complete depending on the total number of words and the number of new words in
1707
+ # the corpus, as well as the current load on the service. You cannot submit requests
1708
+ # to add additional resources to the custom model or to train the model until the
1502
1709
  # service's analysis of the corpus for the current request completes. Use the **List
1503
1710
  # a corpus** method to check the status of the analysis.
1504
1711
  #
1505
1712
  # The service auto-populates the model's words resource with words from the corpus
1506
- # that are not found in its base vocabulary. These are referred to as
1507
- # out-of-vocabulary (OOV) words. You can use the **List custom words** method to
1508
- # examine the words resource. You can use other words method to eliminate typos and
1509
- # modify how words are pronounced as needed.
1713
+ # that are not found in its base vocabulary. These words are referred to as
1714
+ # out-of-vocabulary (OOV) words. After adding a corpus, you must validate the words
1715
+ # resource to ensure that each OOV word's definition is complete and valid. You can
1716
+ # use the **List custom words** method to examine the words resource. You can use
1717
+ # other words method to eliminate typos and modify how words are pronounced as
1718
+ # needed.
1510
1719
  #
1511
1720
  # To add a corpus file that has the same name as an existing corpus, set the
1512
1721
  # `allow_overwrite` parameter to `true`; otherwise, the request fails. Overwriting
@@ -1523,10 +1732,12 @@ module IBMWatson
1523
1732
  # directly.
1524
1733
  #
1525
1734
  # **See also:**
1526
- # * [Working with
1527
- # corpora](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-corporaWords#workingCorpora)
1528
1735
  # * [Add a corpus to the custom language
1529
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-languageCreate#addCorpus).
1736
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-languageCreate#addCorpus)
1737
+ # * [Working with
1738
+ # corpora](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#workingCorpora)
1739
+ # * [Validating a words
1740
+ # resource](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#validateModel).
1530
1741
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1531
1742
  # the request. You must make the request with credentials for the instance of the
1532
1743
  # service that owns the custom model.
@@ -1552,7 +1763,7 @@ module IBMWatson
1552
1763
  # Make sure that you know the character encoding of the file. You must use that
1553
1764
  # encoding when working with the words in the custom language model. For more
1554
1765
  # information, see [Character
1555
- # encoding](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-corporaWords#charEncoding).
1766
+ # encoding](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#charEncoding).
1556
1767
  #
1557
1768
  #
1558
1769
  # With the `curl` command, use the `--data-binary` option to upload the file for the
@@ -1606,7 +1817,7 @@ module IBMWatson
1606
1817
  # that owns a model to list its corpora.
1607
1818
  #
1608
1819
  # **See also:** [Listing corpora for a custom language
1609
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageCorpora#listCorpora).
1820
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageCorpora#listCorpora).
1610
1821
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1611
1822
  # the request. You must make the request with credentials for the instance of the
1612
1823
  # service that owns the custom model.
@@ -1646,7 +1857,7 @@ module IBMWatson
1646
1857
  # corpora.
1647
1858
  #
1648
1859
  # **See also:** [Deleting a corpus from a custom language
1649
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageCorpora#deleteCorpus).
1860
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageCorpora#deleteCorpus).
1650
1861
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1651
1862
  # the request. You must make the request with credentials for the instance of the
1652
1863
  # service that owns the custom model.
@@ -1688,7 +1899,7 @@ module IBMWatson
1688
1899
  # service that owns a model to list information about its words.
1689
1900
  #
1690
1901
  # **See also:** [Listing words from a custom language
1691
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageWords#listWords).
1902
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageWords#listWords).
1692
1903
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1693
1904
  # the request. You must make the request with credentials for the instance of the
1694
1905
  # service that owns the custom model.
@@ -1755,7 +1966,10 @@ module IBMWatson
1755
1966
  # the parameter for words that are difficult to pronounce, foreign words, acronyms,
1756
1967
  # and so on. For example, you might specify that the word `IEEE` can sound like `i
1757
1968
  # triple e`. You can specify a maximum of five sounds-like pronunciations for a
1758
- # word.
1969
+ # word. If you omit the `sounds_like` field, the service attempts to set the field
1970
+ # to its pronunciation of the word. It cannot generate a pronunciation for all
1971
+ # words, so you must review the word's definition to ensure that it is complete and
1972
+ # valid.
1759
1973
  # * The `display_as` field provides a different way of spelling the word in a
1760
1974
  # transcript. Use the parameter when you want the word to appear different from its
1761
1975
  # usual representation or from its spelling in training data. For example, you might
@@ -1785,10 +1999,12 @@ module IBMWatson
1785
1999
  #
1786
2000
  #
1787
2001
  # **See also:**
1788
- # * [Working with custom
1789
- # words](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-corporaWords#workingWords)
1790
2002
  # * [Add words to the custom language
1791
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-languageCreate#addWords).
2003
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-languageCreate#addWords)
2004
+ # * [Working with custom
2005
+ # words](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#workingWords)
2006
+ # * [Validating a words
2007
+ # resource](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#validateModel).
1792
2008
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1793
2009
  # the request. You must make the request with credentials for the instance of the
1794
2010
  # service that owns the custom model.
@@ -1844,7 +2060,10 @@ module IBMWatson
1844
2060
  # the parameter for words that are difficult to pronounce, foreign words, acronyms,
1845
2061
  # and so on. For example, you might specify that the word `IEEE` can sound like `i
1846
2062
  # triple e`. You can specify a maximum of five sounds-like pronunciations for a
1847
- # word.
2063
+ # word. If you omit the `sounds_like` field, the service attempts to set the field
2064
+ # to its pronunciation of the word. It cannot generate a pronunciation for all
2065
+ # words, so you must review the word's definition to ensure that it is complete and
2066
+ # valid.
1848
2067
  # * The `display_as` field provides a different way of spelling the word in a
1849
2068
  # transcript. Use the parameter when you want the word to appear different from its
1850
2069
  # usual representation or from its spelling in training data. For example, you might
@@ -1856,10 +2075,12 @@ module IBMWatson
1856
2075
  # the **List a custom word** method to review the word that you add.
1857
2076
  #
1858
2077
  # **See also:**
1859
- # * [Working with custom
1860
- # words](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-corporaWords#workingWords)
1861
2078
  # * [Add words to the custom language
1862
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-languageCreate#addWords).
2079
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-languageCreate#addWords)
2080
+ # * [Working with custom
2081
+ # words](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#workingWords)
2082
+ # * [Validating a words
2083
+ # resource](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#validateModel).
1863
2084
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1864
2085
  # the request. You must make the request with credentials for the instance of the
1865
2086
  # service that owns the custom model.
@@ -1867,7 +2088,7 @@ module IBMWatson
1867
2088
  # not include spaces in the word. Use a `-` (dash) or `_` (underscore) to connect
1868
2089
  # the tokens of compound words. URL-encode the word if it includes non-ASCII
1869
2090
  # characters. For more information, see [Character
1870
- # encoding](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-corporaWords#charEncoding).
2091
+ # encoding](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#charEncoding).
1871
2092
  # @param word [String] For the **Add custom words** method, you must specify the custom word that is to
1872
2093
  # be added to or updated in the custom model. Do not include spaces in the word. Use
1873
2094
  # a `-` (dash) or `_` (underscore) to connect the tokens of compound words.
@@ -1925,13 +2146,13 @@ module IBMWatson
1925
2146
  # about its words.
1926
2147
  #
1927
2148
  # **See also:** [Listing words from a custom language
1928
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageWords#listWords).
2149
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageWords#listWords).
1929
2150
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1930
2151
  # the request. You must make the request with credentials for the instance of the
1931
2152
  # service that owns the custom model.
1932
2153
  # @param word_name [String] The custom word that is to be read from the custom language model. URL-encode the
1933
2154
  # word if it includes non-ASCII characters. For more information, see [Character
1934
- # encoding](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-corporaWords#charEncoding).
2155
+ # encoding](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#charEncoding).
1935
2156
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
1936
2157
  def get_word(customization_id:, word_name:)
1937
2158
  raise ArgumentError.new("customization_id must be provided") if customization_id.nil?
@@ -1966,13 +2187,13 @@ module IBMWatson
1966
2187
  # instance of the service that owns a model to delete its words.
1967
2188
  #
1968
2189
  # **See also:** [Deleting a word from a custom language
1969
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageWords#deleteWord).
2190
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageWords#deleteWord).
1970
2191
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
1971
2192
  # the request. You must make the request with credentials for the instance of the
1972
2193
  # service that owns the custom model.
1973
2194
  # @param word_name [String] The custom word that is to be deleted from the custom language model. URL-encode
1974
2195
  # the word if it includes non-ASCII characters. For more information, see [Character
1975
- # encoding](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-corporaWords#charEncoding).
2196
+ # encoding](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-corporaWords#charEncoding).
1976
2197
  # @return [nil]
1977
2198
  def delete_word(customization_id:, word_name:)
1978
2199
  raise ArgumentError.new("customization_id must be provided") if customization_id.nil?
@@ -2007,7 +2228,7 @@ module IBMWatson
2007
2228
  # model to list its grammars.
2008
2229
  #
2009
2230
  # **See also:** [Listing grammars from a custom language
2010
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageGrammars#listGrammars).
2231
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageGrammars#listGrammars).
2011
2232
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
2012
2233
  # the request. You must make the request with credentials for the instance of the
2013
2234
  # service that owns the custom model.
@@ -2043,12 +2264,12 @@ module IBMWatson
2043
2264
  #
2044
2265
  # The call returns an HTTP 201 response code if the grammar is valid. The service
2045
2266
  # then asynchronously processes the contents of the grammar and automatically
2046
- # extracts new words that it finds. This can take a few seconds to complete
2047
- # depending on the size and complexity of the grammar, as well as the current load
2048
- # on the service. You cannot submit requests to add additional resources to the
2049
- # custom model or to train the model until the service's analysis of the grammar for
2050
- # the current request completes. Use the **Get a grammar** method to check the
2051
- # status of the analysis.
2267
+ # extracts new words that it finds. This operation can take a few seconds or minutes
2268
+ # to complete depending on the size and complexity of the grammar, as well as the
2269
+ # current load on the service. You cannot submit requests to add additional
2270
+ # resources to the custom model or to train the model until the service's analysis
2271
+ # of the grammar for the current request completes. Use the **Get a grammar** method
2272
+ # to check the status of the analysis.
2052
2273
  #
2053
2274
  # The service populates the model's words resource with any word that is recognized
2054
2275
  # by the grammar that is not found in the model's base vocabulary. These are
@@ -2071,9 +2292,9 @@ module IBMWatson
2071
2292
  #
2072
2293
  # **See also:**
2073
2294
  # * [Understanding
2074
- # grammars](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-grammarUnderstand#grammarUnderstand)
2295
+ # grammars](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-grammarUnderstand#grammarUnderstand)
2075
2296
  # * [Add a grammar to the custom language
2076
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-grammarAdd#addGrammar).
2297
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-grammarAdd#addGrammar).
2077
2298
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
2078
2299
  # the request. You must make the request with credentials for the instance of the
2079
2300
  # service that owns the custom model.
@@ -2153,7 +2374,7 @@ module IBMWatson
2153
2374
  # model to list its grammars.
2154
2375
  #
2155
2376
  # **See also:** [Listing grammars from a custom language
2156
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageGrammars#listGrammars).
2377
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageGrammars#listGrammars).
2157
2378
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
2158
2379
  # the request. You must make the request with credentials for the instance of the
2159
2380
  # service that owns the custom model.
@@ -2192,7 +2413,7 @@ module IBMWatson
2192
2413
  # for the instance of the service that owns a model to delete its grammar.
2193
2414
  #
2194
2415
  # **See also:** [Deleting a grammar from a custom language
2195
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageGrammars#deleteGrammar).
2416
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageGrammars#deleteGrammar).
2196
2417
  # @param customization_id [String] The customization ID (GUID) of the custom language model that is to be used for
2197
2418
  # the request. You must make the request with credentials for the instance of the
2198
2419
  # service that owns the custom model.
@@ -2230,13 +2451,13 @@ module IBMWatson
2230
2451
  # model is owned by the instance of the service whose credentials are used to create
2231
2452
  # it.
2232
2453
  #
2233
- # You can create a maximum of 1024 custom acoustic models, per credential. The
2234
- # service returns an error if you attempt to create more than 1024 models. You do
2235
- # not lose any models, but you cannot create any more until your model count is
2454
+ # You can create a maximum of 1024 custom acoustic models per owning credentials.
2455
+ # The service returns an error if you attempt to create more than 1024 models. You
2456
+ # do not lose any models, but you cannot create any more until your model count is
2236
2457
  # below the limit.
2237
2458
  #
2238
2459
  # **See also:** [Create a custom acoustic
2239
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-acoustic#createModel-acoustic).
2460
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-acoustic#createModel-acoustic).
2240
2461
  # @param name [String] A user-defined name for the new custom acoustic model. Use a name that is unique
2241
2462
  # among all custom acoustic models that you own. Use a localized name that matches
2242
2463
  # the language of the custom model. Use a name that describes the acoustic
@@ -2248,7 +2469,7 @@ module IBMWatson
2248
2469
  #
2249
2470
  # To determine whether a base model supports acoustic model customization, refer to
2250
2471
  # [Language support for
2251
- # customization](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-customization#languageSupport).
2472
+ # customization](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-customization#languageSupport).
2252
2473
  # @param description [String] A description of the new custom acoustic model. Use a localized description that
2253
2474
  # matches the language of the custom model.
2254
2475
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
@@ -2290,7 +2511,7 @@ module IBMWatson
2290
2511
  # a model to list information about it.
2291
2512
  #
2292
2513
  # **See also:** [Listing custom acoustic
2293
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageAcousticModels#listModels-acoustic).
2514
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageAcousticModels#listModels-acoustic).
2294
2515
  # @param language [String] The identifier of the language for which custom language or custom acoustic models
2295
2516
  # are to be returned (for example, `en-US`). Omit the parameter to see all custom
2296
2517
  # language or custom acoustic models that are owned by the requesting credentials.
@@ -2324,7 +2545,7 @@ module IBMWatson
2324
2545
  # for the instance of the service that owns a model to list information about it.
2325
2546
  #
2326
2547
  # **See also:** [Listing custom acoustic
2327
- # models](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageAcousticModels#listModels-acoustic).
2548
+ # models](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageAcousticModels#listModels-acoustic).
2328
2549
  # @param customization_id [String] The customization ID (GUID) of the custom acoustic model that is to be used for
2329
2550
  # the request. You must make the request with credentials for the instance of the
2330
2551
  # service that owns the custom model.
@@ -2357,7 +2578,7 @@ module IBMWatson
2357
2578
  # model to delete it.
2358
2579
  #
2359
2580
  # **See also:** [Deleting a custom acoustic
2360
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageAcousticModels#deleteModel-acoustic).
2581
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageAcousticModels#deleteModel-acoustic).
2361
2582
  # @param customization_id [String] The customization ID (GUID) of the custom acoustic model that is to be used for
2362
2583
  # the request. You must make the request with credentials for the instance of the
2363
2584
  # service that owns the custom model.
@@ -2395,7 +2616,7 @@ module IBMWatson
2395
2616
  # to complete depending on the total amount of audio data on which the custom
2396
2617
  # acoustic model is being trained and the current load on the service. Typically,
2397
2618
  # training a custom acoustic model takes approximately two to four times the length
2398
- # of its audio data. The range of time depends on the model being trained and the
2619
+ # of its audio data. The actual time depends on the model being trained and the
2399
2620
  # nature of the audio, such as whether the audio is clean or noisy. The method
2400
2621
  # returns an HTTP 200 response code to indicate that the training process has begun.
2401
2622
  #
@@ -2414,14 +2635,15 @@ module IBMWatson
2414
2635
  # Train with a custom language model if you have verbatim transcriptions of the
2415
2636
  # audio files that you have added to the custom model or you have either corpora
2416
2637
  # (text files) or a list of words that are relevant to the contents of the audio
2417
- # files. Both of the custom models must be based on the same version of the same
2418
- # base model for training to succeed.
2638
+ # files. For training to succeed, both of the custom models must be based on the
2639
+ # same version of the same base model, and the custom language model must be fully
2640
+ # trained and available.
2419
2641
  #
2420
2642
  # **See also:**
2421
2643
  # * [Train the custom acoustic
2422
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-acoustic#trainModel-acoustic)
2644
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-acoustic#trainModel-acoustic)
2423
2645
  # * [Using custom acoustic and custom language models
2424
- # together](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-useBoth#useBoth)
2646
+ # together](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-useBoth#useBoth)
2425
2647
  #
2426
2648
  #
2427
2649
  # ### Training failures
@@ -2431,6 +2653,9 @@ module IBMWatson
2431
2653
  # another training request or a request to add audio resources to the model.
2432
2654
  # * The custom model contains less than 10 minutes or more than 200 hours of audio
2433
2655
  # data.
2656
+ # * You passed a custom language model with the `custom_language_model_id` query
2657
+ # parameter that is not in the available state. A custom language model must be
2658
+ # fully trained and available to be used to train a custom acoustic model.
2434
2659
  # * You passed an incompatible custom language model with the
2435
2660
  # `custom_language_model_id` query parameter. Both custom models must be based on
2436
2661
  # the same version of the same base model.
@@ -2446,8 +2671,8 @@ module IBMWatson
2446
2671
  # been trained with verbatim transcriptions of the audio resources or that contains
2447
2672
  # words that are relevant to the contents of the audio resources. The custom
2448
2673
  # language model must be based on the same version of the same base model as the
2449
- # custom acoustic model. The credentials specified with the request must own both
2450
- # custom models.
2674
+ # custom acoustic model, and the custom language model must be fully trained and
2675
+ # available. The credentials specified with the request must own both custom models.
2451
2676
  # @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
2452
2677
  def train_acoustic_model(customization_id:, custom_language_model_id: nil)
2453
2678
  raise ArgumentError.new("customization_id must be provided") if customization_id.nil?
@@ -2486,7 +2711,7 @@ module IBMWatson
2486
2711
  # owns a model to reset it.
2487
2712
  #
2488
2713
  # **See also:** [Resetting a custom acoustic
2489
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageAcousticModels#resetModel-acoustic).
2714
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageAcousticModels#resetModel-acoustic).
2490
2715
  # @param customization_id [String] The customization ID (GUID) of the custom acoustic model that is to be used for
2491
2716
  # the request. You must make the request with credentials for the instance of the
2492
2717
  # service that owns the custom model.
@@ -2539,20 +2764,21 @@ module IBMWatson
2539
2764
  # acoustic model was not trained with a custom language model.
2540
2765
  #
2541
2766
  # **See also:** [Upgrading a custom acoustic
2542
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-customUpgrade#upgradeAcoustic).
2767
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-customUpgrade#upgradeAcoustic).
2543
2768
  # @param customization_id [String] The customization ID (GUID) of the custom acoustic model that is to be used for
2544
2769
  # the request. You must make the request with credentials for the instance of the
2545
2770
  # service that owns the custom model.
2546
2771
  # @param custom_language_model_id [String] If the custom acoustic model was trained with a custom language model, the
2547
2772
  # customization ID (GUID) of that custom language model. The custom language model
2548
- # must be upgraded before the custom acoustic model can be upgraded. The credentials
2549
- # specified with the request must own both custom models.
2773
+ # must be upgraded before the custom acoustic model can be upgraded. The custom
2774
+ # language model must be fully trained and available. The credentials specified with
2775
+ # the request must own both custom models.
2550
2776
  # @param force [Boolean] If `true`, forces the upgrade of a custom acoustic model for which no input data
2551
2777
  # has been modified since it was last trained. Use this parameter only to force the
2552
2778
  # upgrade of a custom acoustic model that is trained with a custom language model,
2553
2779
  # and only if you receive a 400 response code and the message `No input data
2554
2780
  # modified since last training`. See [Upgrading a custom acoustic
2555
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-customUpgrade#upgradeAcoustic).
2781
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-customUpgrade#upgradeAcoustic).
2556
2782
  # @return [nil]
2557
2783
  def upgrade_acoustic_model(customization_id:, custom_language_model_id: nil, force: nil)
2558
2784
  raise ArgumentError.new("customization_id must be provided") if customization_id.nil?
@@ -2593,7 +2819,7 @@ module IBMWatson
2593
2819
  # the instance of the service that owns a model to list its audio resources.
2594
2820
  #
2595
2821
  # **See also:** [Listing audio resources for a custom acoustic
2596
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageAudio#listAudio).
2822
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageAudio#listAudio).
2597
2823
  # @param customization_id [String] The customization ID (GUID) of the custom acoustic model that is to be used for
2598
2824
  # the request. You must make the request with credentials for the instance of the
2599
2825
  # service that owns the custom model.
@@ -2641,14 +2867,14 @@ module IBMWatson
2641
2867
  # same name as an existing audio resource, set the `allow_overwrite` parameter to
2642
2868
  # `true`; otherwise, the request fails.
2643
2869
  #
2644
- # The method is asynchronous. It can take several seconds to complete depending on
2645
- # the duration of the audio and, in the case of an archive file, the total number of
2646
- # audio files being processed. The service returns a 201 response code if the audio
2647
- # is valid. It then asynchronously analyzes the contents of the audio file or files
2648
- # and automatically extracts information about the audio such as its length,
2649
- # sampling rate, and encoding. You cannot submit requests to train or upgrade the
2650
- # model until the service's analysis of all audio resources for current requests
2651
- # completes.
2870
+ # The method is asynchronous. It can take several seconds or minutes to complete
2871
+ # depending on the duration of the audio and, in the case of an archive file, the
2872
+ # total number of audio files being processed. The service returns a 201 response
2873
+ # code if the audio is valid. It then asynchronously analyzes the contents of the
2874
+ # audio file or files and automatically extracts information about the audio such as
2875
+ # its length, sampling rate, and encoding. You cannot submit requests to train or
2876
+ # upgrade the model until the service's analysis of all audio resources for current
2877
+ # requests completes.
2652
2878
  #
2653
2879
  # To determine the status of the service's analysis of the audio, use the **Get an
2654
2880
  # audio resource** method to poll the status of the audio. The method accepts the
@@ -2657,7 +2883,7 @@ module IBMWatson
2657
2883
  # every few seconds until it becomes `ok`.
2658
2884
  #
2659
2885
  # **See also:** [Add audio to the custom acoustic
2660
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-acoustic#addAudio).
2886
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-acoustic#addAudio).
2661
2887
  #
2662
2888
  #
2663
2889
  # ### Content types for audio-type resources
@@ -2691,7 +2917,7 @@ module IBMWatson
2691
2917
  # service labels the audio file as `invalid`.
2692
2918
  #
2693
2919
  # **See also:** [Audio
2694
- # formats](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-audio-formats#audio-formats).
2920
+ # formats](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-audio-formats#audio-formats).
2695
2921
  #
2696
2922
  #
2697
2923
  # ### Content types for archive-type resources
@@ -2827,7 +3053,7 @@ module IBMWatson
2827
3053
  # its audio resources.
2828
3054
  #
2829
3055
  # **See also:** [Listing audio resources for a custom acoustic
2830
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageAudio#listAudio).
3056
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageAudio#listAudio).
2831
3057
  # @param customization_id [String] The customization ID (GUID) of the custom acoustic model that is to be used for
2832
3058
  # the request. You must make the request with credentials for the instance of the
2833
3059
  # service that owns the custom model.
@@ -2868,7 +3094,7 @@ module IBMWatson
2868
3094
  # service that owns a model to delete its audio resources.
2869
3095
  #
2870
3096
  # **See also:** [Deleting an audio resource from a custom acoustic
2871
- # model](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-manageAudio#deleteAudio).
3097
+ # model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageAudio#deleteAudio).
2872
3098
  # @param customization_id [String] The customization ID (GUID) of the custom acoustic model that is to be used for
2873
3099
  # the request. You must make the request with credentials for the instance of the
2874
3100
  # service that owns the custom model.
@@ -2911,7 +3137,7 @@ module IBMWatson
2911
3137
  # with a request that passes the data.
2912
3138
  #
2913
3139
  # **See also:** [Information
2914
- # security](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-information-security#information-security).
3140
+ # security](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-information-security#information-security).
2915
3141
  # @param customer_id [String] The customer ID for which all data is to be deleted.
2916
3142
  # @return [nil]
2917
3143
  def delete_user_data(customer_id:)