ibm_watson 1.1.0 → 1.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/ibm_watson/assistant_v1.rb +4 -1
- data/lib/ibm_watson/assistant_v2.rb +1 -1
- data/lib/ibm_watson/compare_comply_v1.rb +1 -1
- data/lib/ibm_watson/discovery_v1.rb +6 -2
- data/lib/ibm_watson/discovery_v2.rb +10 -6
- data/lib/ibm_watson/language_translator_v3.rb +2 -2
- data/lib/ibm_watson/natural_language_classifier_v1.rb +1 -1
- data/lib/ibm_watson/natural_language_understanding_v1.rb +7 -3
- data/lib/ibm_watson/personality_insights_v3.rb +1 -1
- data/lib/ibm_watson/speech_to_text_v1.rb +120 -16
- data/lib/ibm_watson/text_to_speech_v1.rb +5 -3
- data/lib/ibm_watson/tone_analyzer_v3.rb +1 -1
- data/lib/ibm_watson/version.rb +1 -1
- data/lib/ibm_watson/visual_recognition_v3.rb +5 -3
- data/lib/ibm_watson/visual_recognition_v4.rb +1 -1
- data/test/integration/test_speech_to_text_v1.rb +5 -2
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 7c6d7f5a377f215adb0729cf0382278e5ffaab799600af790f34ccbdfc23c9bc
|
4
|
+
data.tar.gz: 2bcd42b40f431dd384e98ed4bb2189f31bc9f2e3079d3e6f99616c04dac0058e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0c596c85d58113d53c16e02d146efd8a8dcad0e182b09b5be788cd0f407270b8cdb74dc367cfd970843d29bd698e94123769322da23c35a044426b8a6e039cef
|
7
|
+
data.tar.gz: c36a5db2c61384052d8d1df6cbacaae5eec21a8acf6050c8bb3bf7eac419ccb60b34028b870d4b88845e0750698c1bb0dc08e04730265a6c30066c138428d3b6
|
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
# (C) Copyright IBM Corp.
|
3
|
+
# (C) Copyright IBM Corp. 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.
|
@@ -2306,6 +2306,9 @@ module IBMWatson
|
|
2306
2306
|
# with a request that passes data. For more information about personal data and
|
2307
2307
|
# customer IDs, see [Information
|
2308
2308
|
# security](https://cloud.ibm.com/docs/services/assistant?topic=assistant-information-security#information-security).
|
2309
|
+
#
|
2310
|
+
# This operation is limited to 4 requests per minute. For more information, see
|
2311
|
+
# **Rate limiting**.
|
2309
2312
|
# @param customer_id [String] The customer ID for which all data is to be deleted.
|
2310
2313
|
# @return [nil]
|
2311
2314
|
def delete_user_data(customer_id:)
|
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
# (C) Copyright IBM Corp.
|
3
|
+
# (C) Copyright IBM Corp. 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.
|
@@ -631,6 +631,8 @@ module IBMWatson
|
|
631
631
|
|
632
632
|
raise ArgumentError.new("collection_id must be provided") if collection_id.nil?
|
633
633
|
|
634
|
+
raise ArgumentError.new("name must be provided") if name.nil?
|
635
|
+
|
634
636
|
headers = {
|
635
637
|
}
|
636
638
|
sdk_headers = Common.new.get_sdk_headers("discovery", "V1", "update_collection")
|
@@ -1590,6 +1592,8 @@ module IBMWatson
|
|
1590
1592
|
def federated_query(environment_id:, collection_ids:, filter: nil, query: nil, natural_language_query: nil, passages: nil, aggregation: nil, count: nil, _return: nil, offset: nil, sort: nil, highlight: nil, passages_fields: nil, passages_count: nil, passages_characters: nil, deduplicate: nil, deduplicate_field: nil, similar: nil, similar_document_ids: nil, similar_fields: nil, bias: nil, x_watson_logging_opt_out: nil)
|
1591
1593
|
raise ArgumentError.new("environment_id must be provided") if environment_id.nil?
|
1592
1594
|
|
1595
|
+
raise ArgumentError.new("collection_ids must be provided") if collection_ids.nil?
|
1596
|
+
|
1593
1597
|
headers = {
|
1594
1598
|
"X-Watson-Logging-Opt-Out" => x_watson_logging_opt_out
|
1595
1599
|
}
|
@@ -2216,7 +2220,7 @@ module IBMWatson
|
|
2216
2220
|
# Create event.
|
2217
2221
|
# The **Events** API can be used to create log entries that are associated with
|
2218
2222
|
# specific queries. For example, you can record which documents in the results set
|
2219
|
-
# were "clicked" by a user and when that click
|
2223
|
+
# were "clicked" by a user and when that click occurred.
|
2220
2224
|
# @param type [String] The event type to be created.
|
2221
2225
|
# @param data [EventData] Query event data object.
|
2222
2226
|
# @return [IBMCloudSdkCore::DetailedResponse] A `IBMCloudSdkCore::DetailedResponse` object representing the response.
|
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
# (C) Copyright IBM Corp.
|
3
|
+
# (C) Copyright IBM Corp. 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.
|
@@ -387,14 +387,14 @@ module IBMWatson
|
|
387
387
|
# **_/v2/projects/{project_id}/collections/{collection_id}/documents** method.
|
388
388
|
#
|
389
389
|
# **Note:** This operation only works on collections created to accept direct file
|
390
|
-
# uploads. It cannot be used to modify a collection that
|
390
|
+
# uploads. It cannot be used to modify a collection that connects to an external
|
391
391
|
# source such as Microsoft SharePoint.
|
392
392
|
# @param project_id [String] The ID of the project. This information can be found from the deploy page of the
|
393
393
|
# Discovery administrative tooling.
|
394
394
|
# @param collection_id [String] The ID of the collection.
|
395
395
|
# @param file [File] The content of the document to ingest. The maximum supported file size when adding
|
396
396
|
# a file to a collection is 50 megabytes, the maximum supported file size when
|
397
|
-
# testing a
|
397
|
+
# testing a configuration is 1 megabyte. Files larger than the supported size are
|
398
398
|
# rejected.
|
399
399
|
# @param filename [String] The filename for file.
|
400
400
|
# @param file_content_type [String] The content type of file.
|
@@ -459,7 +459,7 @@ module IBMWatson
|
|
459
459
|
# any document stored with the same **document_id** if it exists.
|
460
460
|
#
|
461
461
|
# **Note:** This operation only works on collections created to accept direct file
|
462
|
-
# uploads. It cannot be used to modify a collection that
|
462
|
+
# uploads. It cannot be used to modify a collection that connects to an external
|
463
463
|
# source such as Microsoft SharePoint.
|
464
464
|
# @param project_id [String] The ID of the project. This information can be found from the deploy page of the
|
465
465
|
# Discovery administrative tooling.
|
@@ -467,7 +467,7 @@ module IBMWatson
|
|
467
467
|
# @param document_id [String] The ID of the document.
|
468
468
|
# @param file [File] The content of the document to ingest. The maximum supported file size when adding
|
469
469
|
# a file to a collection is 50 megabytes, the maximum supported file size when
|
470
|
-
# testing a
|
470
|
+
# testing a configuration is 1 megabyte. Files larger than the supported size are
|
471
471
|
# rejected.
|
472
472
|
# @param filename [String] The filename for file.
|
473
473
|
# @param file_content_type [String] The content type of file.
|
@@ -529,7 +529,7 @@ module IBMWatson
|
|
529
529
|
# 'deleted'.
|
530
530
|
#
|
531
531
|
# **Note:** This operation only works on collections created to accept direct file
|
532
|
-
# uploads. It cannot be used to modify a collection that
|
532
|
+
# uploads. It cannot be used to modify a collection that connects to an external
|
533
533
|
# source such as Microsoft SharePoint.
|
534
534
|
# @param project_id [String] The ID of the project. This information can be found from the deploy page of the
|
535
535
|
# Discovery administrative tooling.
|
@@ -647,6 +647,10 @@ module IBMWatson
|
|
647
647
|
def create_training_query(project_id:, natural_language_query:, examples:, filter: nil)
|
648
648
|
raise ArgumentError.new("project_id must be provided") if project_id.nil?
|
649
649
|
|
650
|
+
raise ArgumentError.new("natural_language_query must be provided") if natural_language_query.nil?
|
651
|
+
|
652
|
+
raise ArgumentError.new("examples must be provided") if examples.nil?
|
653
|
+
|
650
654
|
headers = {
|
651
655
|
}
|
652
656
|
sdk_headers = Common.new.get_sdk_headers("discovery", "V2", "create_training_query")
|
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
# (C) Copyright IBM Corp.
|
3
|
+
# (C) Copyright IBM Corp. 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.
|
@@ -391,7 +391,7 @@ module IBMWatson
|
|
391
391
|
# Submit a document for translation. You can submit the document contents in the
|
392
392
|
# `file` parameter, or you can reference a previously submitted document by document
|
393
393
|
# ID.
|
394
|
-
# @param file [File] The source file to translate.
|
394
|
+
# @param file [File] The contents of the source file to translate.
|
395
395
|
#
|
396
396
|
# [Supported file
|
397
397
|
# types](https://cloud.ibm.com/docs/services/language-translator?topic=language-translator-document-translator-tutorial#supported-file-formats)
|
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
# (C) Copyright IBM Corp.
|
3
|
+
# (C) Copyright IBM Corp. 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.
|
@@ -21,8 +21,8 @@
|
|
21
21
|
#
|
22
22
|
# You can create [custom
|
23
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
|
25
|
-
#
|
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"
|
@@ -87,6 +87,10 @@ module IBMWatson
|
|
87
87
|
# - Semantic roles
|
88
88
|
# - Sentiment
|
89
89
|
# - Syntax (Experimental).
|
90
|
+
#
|
91
|
+
# If a language for the input text is not specified with the `language` parameter,
|
92
|
+
# the service [automatically detects the
|
93
|
+
# language](https://cloud.ibm.com/docs/services/natural-language-understanding?topic=natural-language-understanding-detectable-languages).
|
90
94
|
# @param features [Features] Specific features to analyze the document for.
|
91
95
|
# @param text [String] The plain text to analyze. One of the `text`, `html`, or `url` parameters is
|
92
96
|
# required.
|
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
# (C) Copyright IBM Corp.
|
3
|
+
# (C) Copyright IBM Corp. 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.
|
@@ -135,7 +135,7 @@ module IBMWatson
|
|
135
135
|
#########################
|
136
136
|
|
137
137
|
##
|
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)
|
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, end_of_phrase_silence_time: nil, split_transcript_at_phrase_end: nil)
|
139
139
|
# Recognize audio.
|
140
140
|
# Sends audio and returns transcription results for a recognition request. You can
|
141
141
|
# pass a maximum of 100 MB and a minimum of 100 bytes of audio with a request. The
|
@@ -358,8 +358,38 @@ module IBMWatson
|
|
358
358
|
# @param audio_metrics [Boolean] If `true`, requests detailed information about the signal characteristics of the
|
359
359
|
# input audio. The service returns audio metrics with the final transcription
|
360
360
|
# results. By default, the service returns no audio metrics.
|
361
|
+
#
|
362
|
+
# See [Audio
|
363
|
+
# metrics](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-metrics#audio_metrics).
|
364
|
+
# @param end_of_phrase_silence_time [Float] If `true`, specifies the duration of the pause interval at which the service
|
365
|
+
# splits a transcript into multiple final results. If the service detects pauses or
|
366
|
+
# extended silence before it reaches the end of the audio stream, its response can
|
367
|
+
# include multiple final results. Silence indicates a point at which the speaker
|
368
|
+
# pauses between spoken words or phrases.
|
369
|
+
#
|
370
|
+
# Specify a value for the pause interval in the range of 0.0 to 120.0.
|
371
|
+
# * A value greater than 0 specifies the interval that the service is to use for
|
372
|
+
# speech recognition.
|
373
|
+
# * A value of 0 indicates that the service is to use the default interval. It is
|
374
|
+
# equivalent to omitting the parameter.
|
375
|
+
#
|
376
|
+
# The default pause interval for most languages is 0.8 seconds; the default for
|
377
|
+
# Chinese is 0.6 seconds.
|
378
|
+
#
|
379
|
+
# See [End of phrase silence
|
380
|
+
# time](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#silence_time).
|
381
|
+
# @param split_transcript_at_phrase_end [Boolean] If `true`, directs the service to split the transcript into multiple final results
|
382
|
+
# based on semantic features of the input, for example, at the conclusion of
|
383
|
+
# meaningful phrases such as sentences. The service bases its understanding of
|
384
|
+
# semantic features on the base language model that you use with a request. Custom
|
385
|
+
# language models and grammars can also influence how and where the service splits a
|
386
|
+
# transcript. By default, the service splits transcripts based solely on the pause
|
387
|
+
# interval.
|
388
|
+
#
|
389
|
+
# See [Split transcript at phrase
|
390
|
+
# end](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#split_transcript).
|
361
391
|
# @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)
|
392
|
+
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)
|
363
393
|
raise ArgumentError.new("audio must be provided") if audio.nil?
|
364
394
|
|
365
395
|
headers = {
|
@@ -388,7 +418,9 @@ module IBMWatson
|
|
388
418
|
"customization_id" => customization_id,
|
389
419
|
"grammar_name" => grammar_name,
|
390
420
|
"redaction" => redaction,
|
391
|
-
"audio_metrics" => audio_metrics
|
421
|
+
"audio_metrics" => audio_metrics,
|
422
|
+
"end_of_phrase_silence_time" => end_of_phrase_silence_time,
|
423
|
+
"split_transcript_at_phrase_end" => split_transcript_at_phrase_end
|
392
424
|
}
|
393
425
|
|
394
426
|
data = audio
|
@@ -407,7 +439,7 @@ module IBMWatson
|
|
407
439
|
end
|
408
440
|
|
409
441
|
##
|
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)
|
442
|
+
# @!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)
|
411
443
|
# Sends audio for speech recognition using web sockets.
|
412
444
|
# @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
445
|
# @param recognize_callback [RecognizeCallback] The instance handling events returned from the service.
|
@@ -469,6 +501,36 @@ module IBMWatson
|
|
469
501
|
# input audio. The service returns audio metrics with the final transcription
|
470
502
|
# results. By default, the service returns no audio metrics.
|
471
503
|
# @return [WebSocketClient] Returns a new WebSocketClient object
|
504
|
+
#
|
505
|
+
# See [Audio
|
506
|
+
# metrics](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-metrics#audio_metrics).
|
507
|
+
# @param end_of_phrase_silence_time [Float] If `true`, specifies the duration of the pause interval at which the service
|
508
|
+
# splits a transcript into multiple final results. If the service detects pauses or
|
509
|
+
# extended silence before it reaches the end of the audio stream, its response can
|
510
|
+
# include multiple final results. Silence indicates a point at which the speaker
|
511
|
+
# pauses between spoken words or phrases.
|
512
|
+
#
|
513
|
+
# Specify a value for the pause interval in the range of 0.0 to 120.0.
|
514
|
+
# * A value greater than 0 specifies the interval that the service is to use for
|
515
|
+
# speech recognition.
|
516
|
+
# * A value of 0 indicates that the service is to use the default interval. It is
|
517
|
+
# equivalent to omitting the parameter.
|
518
|
+
#
|
519
|
+
# The default pause interval for most languages is 0.8 seconds; the default for
|
520
|
+
# Chinese is 0.6 seconds.
|
521
|
+
#
|
522
|
+
# See [End of phrase silence
|
523
|
+
# time](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#silence_time).
|
524
|
+
# @param split_transcript_at_phrase_end [Boolean] If `true`, directs the service to split the transcript into multiple final results
|
525
|
+
# based on semantic features of the input, for example, at the conclusion of
|
526
|
+
# meaningful phrases such as sentences. The service bases its understanding of
|
527
|
+
# semantic features on the base language model that you use with a request. Custom
|
528
|
+
# language models and grammars can also influence how and where the service splits a
|
529
|
+
# transcript. By default, the service splits transcripts based solely on the pause
|
530
|
+
# interval.
|
531
|
+
#
|
532
|
+
# See [Split transcript at phrase
|
533
|
+
# end](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#split_transcript).
|
472
534
|
def recognize_using_websocket(
|
473
535
|
content_type: nil,
|
474
536
|
recognize_callback:,
|
@@ -495,7 +557,9 @@ module IBMWatson
|
|
495
557
|
redaction: nil,
|
496
558
|
processing_metrics: nil,
|
497
559
|
processing_metrics_interval: nil,
|
498
|
-
audio_metrics: nil
|
560
|
+
audio_metrics: nil,
|
561
|
+
end_of_phrase_silence_time: nil,
|
562
|
+
split_transcript_at_phrase_end: nil
|
499
563
|
)
|
500
564
|
raise ArgumentError("Audio must be provided") if audio.nil? && !chunk_data
|
501
565
|
raise ArgumentError("Recognize callback must be provided") if recognize_callback.nil?
|
@@ -532,7 +596,9 @@ module IBMWatson
|
|
532
596
|
"redaction" => redaction,
|
533
597
|
"processing_metrics" => processing_metrics,
|
534
598
|
"processing_metrics_interval" => processing_metrics_interval,
|
535
|
-
"audio_metrics" => audio_metrics
|
599
|
+
"audio_metrics" => audio_metrics,
|
600
|
+
"end_of_phrase_silence_time" => end_of_phrase_silence_time,
|
601
|
+
"split_transcript_at_phrase_end" => split_transcript_at_phrase_end
|
536
602
|
}
|
537
603
|
options.delete_if { |_, v| v.nil? }
|
538
604
|
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)
|
@@ -650,7 +716,7 @@ module IBMWatson
|
|
650
716
|
end
|
651
717
|
|
652
718
|
##
|
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)
|
719
|
+
# @!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)
|
654
720
|
# Create a job.
|
655
721
|
# Creates a job for a new asynchronous recognition request. The job is owned by the
|
656
722
|
# instance of the service whose credentials are used to create it. How you learn the
|
@@ -919,6 +985,9 @@ module IBMWatson
|
|
919
985
|
# the `processing_metrics_interval` parameter. It also returns processing metrics
|
920
986
|
# for transcription events, for example, for final and interim results. By default,
|
921
987
|
# the service returns no processing metrics.
|
988
|
+
#
|
989
|
+
# See [Processing
|
990
|
+
# metrics](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-metrics#processing_metrics).
|
922
991
|
# @param processing_metrics_interval [Float] Specifies the interval in real wall-clock seconds at which the service is to
|
923
992
|
# return processing metrics. The parameter is ignored unless the
|
924
993
|
# `processing_metrics` parameter is set to `true`.
|
@@ -930,11 +999,44 @@ module IBMWatson
|
|
930
999
|
# metrics only for transcription events instead of at periodic intervals, set the
|
931
1000
|
# value to a large number. If the value is larger than the duration of the audio,
|
932
1001
|
# the service returns processing metrics only for transcription events.
|
1002
|
+
#
|
1003
|
+
# See [Processing
|
1004
|
+
# metrics](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-metrics#processing_metrics).
|
933
1005
|
# @param audio_metrics [Boolean] If `true`, requests detailed information about the signal characteristics of the
|
934
1006
|
# input audio. The service returns audio metrics with the final transcription
|
935
1007
|
# results. By default, the service returns no audio metrics.
|
1008
|
+
#
|
1009
|
+
# See [Audio
|
1010
|
+
# metrics](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-metrics#audio_metrics).
|
1011
|
+
# @param end_of_phrase_silence_time [Float] If `true`, specifies the duration of the pause interval at which the service
|
1012
|
+
# splits a transcript into multiple final results. If the service detects pauses or
|
1013
|
+
# extended silence before it reaches the end of the audio stream, its response can
|
1014
|
+
# include multiple final results. Silence indicates a point at which the speaker
|
1015
|
+
# pauses between spoken words or phrases.
|
1016
|
+
#
|
1017
|
+
# Specify a value for the pause interval in the range of 0.0 to 120.0.
|
1018
|
+
# * A value greater than 0 specifies the interval that the service is to use for
|
1019
|
+
# speech recognition.
|
1020
|
+
# * A value of 0 indicates that the service is to use the default interval. It is
|
1021
|
+
# equivalent to omitting the parameter.
|
1022
|
+
#
|
1023
|
+
# The default pause interval for most languages is 0.8 seconds; the default for
|
1024
|
+
# Chinese is 0.6 seconds.
|
1025
|
+
#
|
1026
|
+
# See [End of phrase silence
|
1027
|
+
# time](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#silence_time).
|
1028
|
+
# @param split_transcript_at_phrase_end [Boolean] If `true`, directs the service to split the transcript into multiple final results
|
1029
|
+
# based on semantic features of the input, for example, at the conclusion of
|
1030
|
+
# meaningful phrases such as sentences. The service bases its understanding of
|
1031
|
+
# semantic features on the base language model that you use with a request. Custom
|
1032
|
+
# language models and grammars can also influence how and where the service splits a
|
1033
|
+
# transcript. By default, the service splits transcripts based solely on the pause
|
1034
|
+
# interval.
|
1035
|
+
#
|
1036
|
+
# See [Split transcript at phrase
|
1037
|
+
# end](https://cloud.ibm.com/docs/services/speech-to-text?topic=speech-to-text-output#split_transcript).
|
936
1038
|
# @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)
|
1039
|
+
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)
|
938
1040
|
raise ArgumentError.new("audio must be provided") if audio.nil?
|
939
1041
|
|
940
1042
|
headers = {
|
@@ -969,7 +1071,9 @@ module IBMWatson
|
|
969
1071
|
"redaction" => redaction,
|
970
1072
|
"processing_metrics" => processing_metrics,
|
971
1073
|
"processing_metrics_interval" => processing_metrics_interval,
|
972
|
-
"audio_metrics" => audio_metrics
|
1074
|
+
"audio_metrics" => audio_metrics,
|
1075
|
+
"end_of_phrase_silence_time" => end_of_phrase_silence_time,
|
1076
|
+
"split_transcript_at_phrase_end" => split_transcript_at_phrase_end
|
973
1077
|
}
|
974
1078
|
|
975
1079
|
data = audio
|
@@ -1104,9 +1208,9 @@ module IBMWatson
|
|
1104
1208
|
# model is owned by the instance of the service whose credentials are used to create
|
1105
1209
|
# it.
|
1106
1210
|
#
|
1107
|
-
# You can create a maximum of 1024 custom language models
|
1108
|
-
# service returns an error if you attempt to create more than 1024 models. You
|
1109
|
-
# not lose any models, but you cannot create any more until your model count is
|
1211
|
+
# You can create a maximum of 1024 custom language models per owning credentials.
|
1212
|
+
# The service returns an error if you attempt to create more than 1024 models. You
|
1213
|
+
# do not lose any models, but you cannot create any more until your model count is
|
1110
1214
|
# below the limit.
|
1111
1215
|
#
|
1112
1216
|
# **See also:** [Create a custom language
|
@@ -2230,9 +2334,9 @@ module IBMWatson
|
|
2230
2334
|
# model is owned by the instance of the service whose credentials are used to create
|
2231
2335
|
# it.
|
2232
2336
|
#
|
2233
|
-
# You can create a maximum of 1024 custom acoustic models
|
2234
|
-
# service returns an error if you attempt to create more than 1024 models. You
|
2235
|
-
# not lose any models, but you cannot create any more until your model count is
|
2337
|
+
# You can create a maximum of 1024 custom acoustic models per owning credentials.
|
2338
|
+
# The service returns an error if you attempt to create more than 1024 models. You
|
2339
|
+
# do not lose any models, but you cannot create any more until your model count is
|
2236
2340
|
# below the limit.
|
2237
2341
|
#
|
2238
2342
|
# **See also:** [Create a custom acoustic
|
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
# (C) Copyright IBM Corp.
|
3
|
+
# (C) Copyright IBM Corp. 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.
|
@@ -263,7 +263,8 @@ module IBMWatson
|
|
263
263
|
# specific voice to see the default translation for the language of that voice or
|
264
264
|
# for a specific custom voice model to see the translation for that voice model.
|
265
265
|
#
|
266
|
-
# **Note:** This method is currently a beta release.
|
266
|
+
# **Note:** This method is currently a beta release. The method does not support the
|
267
|
+
# Arabic, Chinese, and Dutch languages.
|
267
268
|
#
|
268
269
|
# **See also:** [Querying a word from a
|
269
270
|
# language](https://cloud.ibm.com/docs/services/text-to-speech?topic=text-to-speech-customWords#cuWordsQueryLanguage).
|
@@ -319,7 +320,8 @@ module IBMWatson
|
|
319
320
|
# model. The model is owned by the instance of the service whose credentials are
|
320
321
|
# used to create it.
|
321
322
|
#
|
322
|
-
# **Note:** This method is currently a beta release.
|
323
|
+
# **Note:** This method is currently a beta release. The service does not support
|
324
|
+
# voice model customization for the Arabic, Chinese, and Dutch languages.
|
323
325
|
#
|
324
326
|
# **See also:** [Creating a custom
|
325
327
|
# model](https://cloud.ibm.com/docs/services/text-to-speech?topic=text-to-speech-customModels#cuModelsCreate).
|
data/lib/ibm_watson/version.rb
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
# (C) Copyright IBM Corp.
|
3
|
+
# (C) Copyright IBM Corp. 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.
|
@@ -177,7 +177,8 @@ module IBMWatson
|
|
177
177
|
#
|
178
178
|
# Specify the parameter name by appending `_positive_examples` to the class name.
|
179
179
|
# For example, `goldenretriever_positive_examples` creates the class
|
180
|
-
# **goldenretriever**.
|
180
|
+
# **goldenretriever**. The string cannot contain the following characters: ``$ * - {
|
181
|
+
# } \ | / ' " ` [ ]``.
|
181
182
|
#
|
182
183
|
# Include at least 10 images in .jpg or .png format. The minimum recommended image
|
183
184
|
# resolution is 32X32 pixels. The maximum number of images is 10,000 images or 100
|
@@ -328,7 +329,8 @@ module IBMWatson
|
|
328
329
|
#
|
329
330
|
# Specify the parameter name by appending `_positive_examples` to the class name.
|
330
331
|
# For example, `goldenretriever_positive_examples` creates the class
|
331
|
-
# `goldenretriever`.
|
332
|
+
# `goldenretriever`. The string cannot contain the following characters: ``$ * - { }
|
333
|
+
# \ | / ' " ` [ ]``.
|
332
334
|
#
|
333
335
|
# Include at least 10 images in .jpg or .png format. The minimum recommended image
|
334
336
|
# resolution is 32X32 pixels. The maximum number of images is 10,000 images or 100
|
@@ -88,7 +88,7 @@ if !ENV["SPEECH_TO_TEXT_APIKEY"].nil? && !ENV["SPEECH_TO_TEXT_URL"].nil?
|
|
88
88
|
end
|
89
89
|
|
90
90
|
def test_recognize_with_single_keyword
|
91
|
-
file = File.open(Dir.getwd + "/resources/
|
91
|
+
file = File.open(Dir.getwd + "/resources/sound-with-pause.wav")
|
92
92
|
output = nil
|
93
93
|
File.open(file) do |audio_file|
|
94
94
|
output = @service.recognize(
|
@@ -97,9 +97,12 @@ if !ENV["SPEECH_TO_TEXT_APIKEY"].nil? && !ENV["SPEECH_TO_TEXT_URL"].nil?
|
|
97
97
|
timestamps: true,
|
98
98
|
word_alternatives_threshold: 0.9,
|
99
99
|
keywords: %w"[colorado]",
|
100
|
-
keywords_threshold: 0.5
|
100
|
+
keywords_threshold: 0.5,
|
101
|
+
split_transcript_at_phrase_end: true,
|
102
|
+
end_of_phrase_silence_time: nil
|
101
103
|
)
|
102
104
|
refute_nil(output.result["results"][0]["alternatives"][0]["transcript"])
|
105
|
+
assert(3, output.result["results"].length)
|
103
106
|
end
|
104
107
|
end
|
105
108
|
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ibm_watson
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Max Nussbaum
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2020-01-15 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: concurrent-ruby
|
@@ -347,7 +347,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
347
347
|
- !ruby/object:Gem::Version
|
348
348
|
version: '0'
|
349
349
|
requirements: []
|
350
|
-
rubygems_version: 3.
|
350
|
+
rubygems_version: 3.1.2
|
351
351
|
signing_key:
|
352
352
|
specification_version: 4
|
353
353
|
summary: Official client library to use the IBM Watson Services
|