assemblyai 1.1.0 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/assemblyai/lemur/types/lemur_model.rb +1 -0
- data/lib/assemblyai/transcripts/client.rb +22 -12
- data/lib/assemblyai/transcripts/polling_client.rb +148 -68
- data/lib/assemblyai/transcripts/types/content_safety_labels_result.rb +2 -2
- data/lib/assemblyai/transcripts/types/paragraphs_response.rb +8 -8
- data/lib/assemblyai/transcripts/types/sentences_response.rb +8 -8
- data/lib/assemblyai/transcripts/types/sentiment_analysis_result.rb +12 -1
- data/lib/assemblyai/transcripts/types/topic_detection_result.rb +2 -2
- data/lib/assemblyai/transcripts/types/transcript.rb +23 -3
- data/lib/assemblyai/transcripts/types/transcript_list.rb +4 -4
- data/lib/assemblyai/transcripts/types/transcript_list_item.rb +12 -12
- data/lib/assemblyai/transcripts/types/transcript_optional_params.rb +21 -7
- data/lib/assemblyai/transcripts/types/transcript_paragraph.rb +12 -32
- data/lib/assemblyai/transcripts/types/transcript_sentence.rb +22 -11
- data/lib/assemblyai/transcripts/types/transcript_utterance.rb +14 -2
- data/lib/assemblyai/transcripts/types/transcript_word.rb +21 -11
- data/lib/gemconfig.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 829ed3bd27fb8aac58b6250478b6c4c077bf27c38a23190cab5a1781945bac99
|
4
|
+
data.tar.gz: d015981babb1021cb9418f51e1256751b91986aa8fcfb7344bbc243f660b5fdf
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 63e1f0d2256aff704d10fe8c77a0897c8826053d0838468b2f0530ee9438f8af3262568cf8a14417b7c5824e0a78e4cf813eb0767e56341093b18982c939401d
|
7
|
+
data.tar.gz: cfbb7ab4a8e5c2b196abf7ea0ee2d31b08115b7e2017f13ecfe17386e10b02c27c0e2b83649da86f922d13836ea78046035fb182740a6d659a93088cdc024fc8
|
@@ -10,6 +10,7 @@ module AssemblyAI
|
|
10
10
|
ANTHROPIC_CLAUDE3_SONNET = "anthropic/claude-3-sonnet"
|
11
11
|
ANTHROPIC_CLAUDE2_1 = "anthropic/claude-2-1"
|
12
12
|
ANTHROPIC_CLAUDE2 = "anthropic/claude-2"
|
13
|
+
ANTHROPIC_CLAUDE2_0 = "anthropic/claude-2"
|
13
14
|
DEFAULT = "default"
|
14
15
|
ANTHROPIC_CLAUDE_INSTANT1_2 = "anthropic/claude-instant-1-2"
|
15
16
|
BASIC = "basic"
|
@@ -35,7 +35,7 @@ module AssemblyAI
|
|
35
35
|
# Transcripts are sorted from newest to oldest. The previous URL always points to
|
36
36
|
# a page with older transcripts.
|
37
37
|
#
|
38
|
-
# @param limit [
|
38
|
+
# @param limit [Integer] Maximum amount of transcripts to retrieve
|
39
39
|
# @param status [AssemblyAI::Transcripts::TranscriptStatus] Filter by transcript status
|
40
40
|
# @param created_on [String] Only get transcripts created on this date
|
41
41
|
# @param before_id [String] Get transcripts that were created before this transcript ID
|
@@ -83,12 +83,16 @@ module AssemblyAI
|
|
83
83
|
# @param punctuate [Boolean] Enable Automatic Punctuation, can be true or false
|
84
84
|
# @param format_text [Boolean] Enable Text Formatting, can be true or false
|
85
85
|
# @param disfluencies [Boolean] Transcribe Filler Words, like "umm", in your media file; can be true or false
|
86
|
+
# @param multichannel [Boolean] Enable
|
87
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription)
|
88
|
+
# transcription, can be true or false.
|
86
89
|
# @param dual_channel [Boolean] Enable [Dual
|
87
90
|
# ://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription)
|
88
91
|
# transcription, can be true or false.
|
89
|
-
# @param webhook_url [String] The URL to which we send webhook requests.
|
90
|
-
#
|
91
|
-
# request when
|
92
|
+
# @param webhook_url [String] The URL to which we send webhook requests.
|
93
|
+
# We sends two different types of webhook requests.
|
94
|
+
# One request when a transcript is completed or failed, and one request when the
|
95
|
+
# redacted audio is ready if redact_pii_audio is enabled.
|
92
96
|
# @param webhook_auth_header_name [String] The header name to be sent with the transcript completed or failed webhook
|
93
97
|
# requests
|
94
98
|
# @param webhook_auth_header_value [String] The header value to send back with the transcript completed or failed webhook
|
@@ -156,9 +160,9 @@ module AssemblyAI
|
|
156
160
|
# base_url: "https://api.example.com",
|
157
161
|
# api_key: "YOUR_API_KEY"
|
158
162
|
# )
|
159
|
-
# api.transcripts.submit(audio_url: "https://
|
163
|
+
# api.transcripts.submit(audio_url: "https://assembly.ai/wildfires.mp3")
|
160
164
|
def submit(audio_url:, language_code: nil, language_detection: nil, language_confidence_threshold: nil, speech_model: nil,
|
161
|
-
punctuate: nil, format_text: nil, disfluencies: nil, dual_channel: nil, webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, custom_spelling: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, request_options: nil)
|
165
|
+
punctuate: nil, format_text: nil, disfluencies: nil, multichannel: nil, dual_channel: nil, webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, custom_spelling: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, request_options: nil)
|
162
166
|
response = @request_client.conn.post do |req|
|
163
167
|
req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
|
164
168
|
req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
|
@@ -172,6 +176,7 @@ module AssemblyAI
|
|
172
176
|
punctuate: punctuate,
|
173
177
|
format_text: format_text,
|
174
178
|
disfluencies: disfluencies,
|
179
|
+
multichannel: multichannel,
|
175
180
|
dual_channel: dual_channel,
|
176
181
|
webhook_url: webhook_url,
|
177
182
|
webhook_auth_header_name: webhook_auth_header_name,
|
@@ -380,7 +385,7 @@ module AssemblyAI
|
|
380
385
|
# Transcripts are sorted from newest to oldest. The previous URL always points to
|
381
386
|
# a page with older transcripts.
|
382
387
|
#
|
383
|
-
# @param limit [
|
388
|
+
# @param limit [Integer] Maximum amount of transcripts to retrieve
|
384
389
|
# @param status [AssemblyAI::Transcripts::TranscriptStatus] Filter by transcript status
|
385
390
|
# @param created_on [String] Only get transcripts created on this date
|
386
391
|
# @param before_id [String] Get transcripts that were created before this transcript ID
|
@@ -430,12 +435,16 @@ module AssemblyAI
|
|
430
435
|
# @param punctuate [Boolean] Enable Automatic Punctuation, can be true or false
|
431
436
|
# @param format_text [Boolean] Enable Text Formatting, can be true or false
|
432
437
|
# @param disfluencies [Boolean] Transcribe Filler Words, like "umm", in your media file; can be true or false
|
438
|
+
# @param multichannel [Boolean] Enable
|
439
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription)
|
440
|
+
# transcription, can be true or false.
|
433
441
|
# @param dual_channel [Boolean] Enable [Dual
|
434
442
|
# ://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription)
|
435
443
|
# transcription, can be true or false.
|
436
|
-
# @param webhook_url [String] The URL to which we send webhook requests.
|
437
|
-
#
|
438
|
-
# request when
|
444
|
+
# @param webhook_url [String] The URL to which we send webhook requests.
|
445
|
+
# We sends two different types of webhook requests.
|
446
|
+
# One request when a transcript is completed or failed, and one request when the
|
447
|
+
# redacted audio is ready if redact_pii_audio is enabled.
|
439
448
|
# @param webhook_auth_header_name [String] The header name to be sent with the transcript completed or failed webhook
|
440
449
|
# requests
|
441
450
|
# @param webhook_auth_header_value [String] The header value to send back with the transcript completed or failed webhook
|
@@ -503,9 +512,9 @@ module AssemblyAI
|
|
503
512
|
# base_url: "https://api.example.com",
|
504
513
|
# api_key: "YOUR_API_KEY"
|
505
514
|
# )
|
506
|
-
# api.transcripts.submit(audio_url: "https://
|
515
|
+
# api.transcripts.submit(audio_url: "https://assembly.ai/wildfires.mp3")
|
507
516
|
def submit(audio_url:, language_code: nil, language_detection: nil, language_confidence_threshold: nil, speech_model: nil,
|
508
|
-
punctuate: nil, format_text: nil, disfluencies: nil, dual_channel: nil, webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, custom_spelling: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, request_options: nil)
|
517
|
+
punctuate: nil, format_text: nil, disfluencies: nil, multichannel: nil, dual_channel: nil, webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, custom_spelling: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, request_options: nil)
|
509
518
|
Async do
|
510
519
|
response = @request_client.conn.post do |req|
|
511
520
|
req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
|
@@ -520,6 +529,7 @@ module AssemblyAI
|
|
520
529
|
punctuate: punctuate,
|
521
530
|
format_text: format_text,
|
522
531
|
disfluencies: disfluencies,
|
532
|
+
multichannel: multichannel,
|
523
533
|
dual_channel: dual_channel,
|
524
534
|
webhook_url: webhook_url,
|
525
535
|
webhook_auth_header_name: webhook_auth_header_name,
|
@@ -26,53 +26,93 @@ module AssemblyAI
|
|
26
26
|
# Create a transcript from an audio or video file that is accessible via a URL.
|
27
27
|
# .transcribe polls for completion of the transcription, while the .submit function does not.
|
28
28
|
#
|
29
|
-
# @param
|
30
|
-
# @param
|
29
|
+
# @param language_code [AssemblyAI::Transcripts::TranscriptLanguageCode]
|
30
|
+
# @param language_detection [Boolean] Enable [Automatic language
|
31
|
+
# www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection),
|
32
|
+
# either true or false.
|
33
|
+
# @param language_confidence_threshold [Float] The confidence threshold for the automatically detected language.
|
34
|
+
# An error will be returned if the language confidence is below this threshold.
|
35
|
+
# Defaults to 0.
|
36
|
+
# @param speech_model [AssemblyAI::Transcripts::SpeechModel]
|
31
37
|
# @param punctuate [Boolean] Enable Automatic Punctuation, can be true or false
|
32
38
|
# @param format_text [Boolean] Enable Text Formatting, can be true or false
|
33
|
-
# @param
|
34
|
-
# @param
|
35
|
-
#
|
36
|
-
#
|
37
|
-
# @param
|
39
|
+
# @param disfluencies [Boolean] Transcribe Filler Words, like "umm", in your media file; can be true or false
|
40
|
+
# @param multichannel [Boolean] Enable
|
41
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription)
|
42
|
+
# transcription, can be true or false.
|
43
|
+
# @param dual_channel [Boolean] Enable [Dual
|
44
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription)
|
45
|
+
# transcription, can be true or false.
|
46
|
+
# @param webhook_url [String] The URL to which we send webhook requests.
|
47
|
+
# We sends two different types of webhook requests.
|
48
|
+
# One request when a transcript is completed or failed, and one request when the
|
49
|
+
# redacted audio is ready if redact_pii_audio is enabled.
|
50
|
+
# @param webhook_auth_header_name [String] The header name to be sent with the transcript completed or failed webhook
|
51
|
+
# requests
|
52
|
+
# @param webhook_auth_header_value [String] The header value to send back with the transcript completed or failed webhook
|
53
|
+
# requests for added security
|
54
|
+
# @param auto_highlights [Boolean] Enable Key Phrases, either true or false
|
38
55
|
# @param audio_start_from [Integer] The point in time, in milliseconds, to begin transcribing in your media file
|
39
56
|
# @param audio_end_at [Integer] The point in time, in milliseconds, to stop transcribing in your media file
|
40
57
|
# @param word_boost [Array<String>] The list of custom vocabulary to boost transcription probability for
|
41
|
-
# @param boost_param [Transcripts::TranscriptBoostParam]
|
58
|
+
# @param boost_param [AssemblyAI::Transcripts::TranscriptBoostParam] How much to boost specified words
|
42
59
|
# @param filter_profanity [Boolean] Filter profanity from the transcribed text, can be true or false
|
43
|
-
# @param redact_pii [Boolean] Redact PII from the transcribed text using the Redact PII model, can be true or
|
44
|
-
#
|
45
|
-
# @param
|
46
|
-
#
|
47
|
-
#
|
48
|
-
#
|
49
|
-
# @param
|
50
|
-
#
|
51
|
-
#
|
52
|
-
#
|
53
|
-
# @param
|
54
|
-
#
|
60
|
+
# @param redact_pii [Boolean] Redact PII from the transcribed text using the Redact PII model, can be true or
|
61
|
+
# false
|
62
|
+
# @param redact_pii_audio [Boolean] Generate a copy of the original media file with spoken PII "beeped" out, can be
|
63
|
+
# true or false. See [PII
|
64
|
+
# redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more
|
65
|
+
# details.
|
66
|
+
# @param redact_pii_audio_quality [AssemblyAI::Transcripts::RedactPiiAudioQuality] Controls the filetype of the audio created by redact_pii_audio. Currently
|
67
|
+
# supports mp3 (default) and wav. See [PII
|
68
|
+
# redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more
|
69
|
+
# details.
|
70
|
+
# @param redact_pii_policies [Array<AssemblyAI::Transcripts::PiiPolicy>] The list of PII Redaction policies to enable. See [PII
|
71
|
+
# redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more
|
72
|
+
# details.
|
73
|
+
# @param redact_pii_sub [AssemblyAI::Transcripts::SubstitutionPolicy]
|
74
|
+
# @param speaker_labels [Boolean] Enable [Speaker
|
75
|
+
# diarization](https://www.assemblyai.com/docs/models/speaker-diarization), can be
|
76
|
+
# true or false
|
77
|
+
# @param speakers_expected [Integer] Tells the speaker label model how many speakers it should attempt to identify,
|
78
|
+
# up to 10. See [Speaker
|
79
|
+
# diarization](https://www.assemblyai.com/docs/models/speaker-diarization) for
|
80
|
+
# more details.
|
81
|
+
# @param content_safety [Boolean] Enable [Content
|
82
|
+
# Moderation](https://www.assemblyai.com/docs/models/content-moderation), can be
|
83
|
+
# true or false
|
84
|
+
# @param content_safety_confidence [Integer] The confidence threshold for the Content Moderation model. Values must be
|
85
|
+
# between 25 and 100.
|
86
|
+
# @param iab_categories [Boolean] Enable [Topic
|
87
|
+
# Detection](https://www.assemblyai.com/docs/models/topic-detection), can be true
|
88
|
+
# or false
|
89
|
+
# @param custom_spelling [Array<Hash>] Customize how words are spelled and formatted using to and from valuesRequest of type Array<AssemblyAI::Transcripts::TranscriptCustomSpelling>, as a Hash
|
55
90
|
# * :from (Array<String>)
|
56
91
|
# * :to (String)
|
57
|
-
# @param
|
58
|
-
#
|
59
|
-
#
|
60
|
-
# @param
|
92
|
+
# @param sentiment_analysis [Boolean] Enable [Sentiment
|
93
|
+
# Analysis](https://www.assemblyai.com/docs/models/sentiment-analysis), can be
|
94
|
+
# true or false
|
95
|
+
# @param auto_chapters [Boolean] Enable [Auto Chapters](https://www.assemblyai.com/docs/models/auto-chapters),
|
96
|
+
# can be true or false
|
97
|
+
# @param entity_detection [Boolean] Enable [Entity
|
98
|
+
# Detection](https://www.assemblyai.com/docs/models/entity-detection), can be true
|
99
|
+
# or false
|
61
100
|
# @param speech_threshold [Float] Reject audio files that contain less than this fraction of speech.
|
62
|
-
#
|
63
|
-
# @param summarization [Boolean] Enable [Summarization](https://www.assemblyai.com/docs/models/summarization),
|
64
|
-
#
|
65
|
-
# @param
|
66
|
-
# @param
|
67
|
-
# @param
|
101
|
+
# Valid values are in the range [0, 1] inclusive.
|
102
|
+
# @param summarization [Boolean] Enable [Summarization](https://www.assemblyai.com/docs/models/summarization),
|
103
|
+
# can be true or false
|
104
|
+
# @param summary_model [AssemblyAI::Transcripts::SummaryModel] The model to summarize the transcript
|
105
|
+
# @param summary_type [AssemblyAI::Transcripts::SummaryType] The type of summary
|
106
|
+
# @param custom_topics [Boolean] Enable custom topics, either true or false
|
107
|
+
# @param topics [Array<String>] The list of custom topics
|
68
108
|
# @param audio_url [String] The URL of the audio or video file to transcribe.
|
69
|
-
# @param request_options [RequestOptions]
|
109
|
+
# @param request_options [AssemblyAI::RequestOptions]
|
70
110
|
# @param polling_options [Transcripts::PollingOptions] Configuration options for polling requests.
|
71
111
|
# @return [Transcripts::Transcript]
|
72
|
-
def transcribe(audio_url:,
|
73
|
-
webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil,
|
112
|
+
def transcribe(audio_url:, language_code: nil, language_detection: nil, language_confidence_threshold: nil, speech_model: nil,
|
113
|
+
punctuate: nil, format_text: nil, disfluencies: nil, multichannel: nil, dual_channel: nil, webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, custom_spelling: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, request_options: nil, polling_options: Transcripts::PollingOptions.new)
|
74
114
|
transcript = submit(audio_url: audio_url, speech_model: speech_model, language_code: language_code, punctuate: punctuate, format_text: format_text, dual_channel: dual_channel,
|
75
|
-
webhook_url: webhook_url, webhook_auth_header_name: webhook_auth_header_name, webhook_auth_header_value: webhook_auth_header_value, auto_highlights: auto_highlights, audio_start_from: audio_start_from, audio_end_at: audio_end_at, word_boost: word_boost, boost_param: boost_param, filter_profanity: filter_profanity, redact_pii: redact_pii, redact_pii_audio: redact_pii_audio, redact_pii_audio_quality: redact_pii_audio_quality, redact_pii_policies: redact_pii_policies, redact_pii_sub: redact_pii_sub, speaker_labels: speaker_labels, speakers_expected: speakers_expected, content_safety: content_safety, content_safety_confidence: content_safety_confidence, iab_categories: iab_categories, language_detection: language_detection, custom_spelling: custom_spelling, disfluencies: disfluencies, sentiment_analysis: sentiment_analysis, auto_chapters: auto_chapters, entity_detection: entity_detection, speech_threshold: speech_threshold, summarization: summarization, summary_model: summary_model, summary_type: summary_type, custom_topics: custom_topics, topics: topics, request_options: request_options)
|
115
|
+
webhook_url: webhook_url, webhook_auth_header_name: webhook_auth_header_name, webhook_auth_header_value: webhook_auth_header_value, auto_highlights: auto_highlights, audio_start_from: audio_start_from, audio_end_at: audio_end_at, word_boost: word_boost, boost_param: boost_param, filter_profanity: filter_profanity, redact_pii: redact_pii, redact_pii_audio: redact_pii_audio, redact_pii_audio_quality: redact_pii_audio_quality, redact_pii_policies: redact_pii_policies, redact_pii_sub: redact_pii_sub, speaker_labels: speaker_labels, speakers_expected: speakers_expected, content_safety: content_safety, content_safety_confidence: content_safety_confidence, iab_categories: iab_categories, language_detection: language_detection, language_confidence_threshold: language_confidence_threshold, custom_spelling: custom_spelling, disfluencies: disfluencies, multichannel: multichannel, sentiment_analysis: sentiment_analysis, auto_chapters: auto_chapters, entity_detection: entity_detection, speech_threshold: speech_threshold, summarization: summarization, summary_model: summary_model, summary_type: summary_type, custom_topics: custom_topics, topics: topics, request_options: request_options)
|
76
116
|
wait_until_ready(transcript_id: transcript.id, polling_options: polling_options)
|
77
117
|
end
|
78
118
|
|
@@ -102,54 +142,94 @@ module AssemblyAI
|
|
102
142
|
# Create a transcript from an audio or video file that is accessible via a URL.
|
103
143
|
# .transcribe polls for completion of the transcription, while the .submit function does not.
|
104
144
|
#
|
105
|
-
# @param
|
106
|
-
# @param
|
145
|
+
# @param language_code [AssemblyAI::Transcripts::TranscriptLanguageCode]
|
146
|
+
# @param language_detection [Boolean] Enable [Automatic language
|
147
|
+
# www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection),
|
148
|
+
# either true or false.
|
149
|
+
# @param language_confidence_threshold [Float] The confidence threshold for the automatically detected language.
|
150
|
+
# An error will be returned if the language confidence is below this threshold.
|
151
|
+
# Defaults to 0.
|
152
|
+
# @param speech_model [AssemblyAI::Transcripts::SpeechModel]
|
107
153
|
# @param punctuate [Boolean] Enable Automatic Punctuation, can be true or false
|
108
154
|
# @param format_text [Boolean] Enable Text Formatting, can be true or false
|
109
|
-
# @param
|
110
|
-
# @param
|
111
|
-
#
|
112
|
-
#
|
113
|
-
# @param
|
155
|
+
# @param disfluencies [Boolean] Transcribe Filler Words, like "umm", in your media file; can be true or false
|
156
|
+
# @param multichannel [Boolean] Enable
|
157
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription)
|
158
|
+
# transcription, can be true or false.
|
159
|
+
# @param dual_channel [Boolean] Enable [Dual
|
160
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription)
|
161
|
+
# transcription, can be true or false.
|
162
|
+
# @param webhook_url [String] The URL to which we send webhook requests.
|
163
|
+
# We sends two different types of webhook requests.
|
164
|
+
# One request when a transcript is completed or failed, and one request when the
|
165
|
+
# redacted audio is ready if redact_pii_audio is enabled.
|
166
|
+
# @param webhook_auth_header_name [String] The header name to be sent with the transcript completed or failed webhook
|
167
|
+
# requests
|
168
|
+
# @param webhook_auth_header_value [String] The header value to send back with the transcript completed or failed webhook
|
169
|
+
# requests for added security
|
170
|
+
# @param auto_highlights [Boolean] Enable Key Phrases, either true or false
|
114
171
|
# @param audio_start_from [Integer] The point in time, in milliseconds, to begin transcribing in your media file
|
115
172
|
# @param audio_end_at [Integer] The point in time, in milliseconds, to stop transcribing in your media file
|
116
173
|
# @param word_boost [Array<String>] The list of custom vocabulary to boost transcription probability for
|
117
|
-
# @param boost_param [Transcripts::TranscriptBoostParam]
|
174
|
+
# @param boost_param [AssemblyAI::Transcripts::TranscriptBoostParam] How much to boost specified words
|
118
175
|
# @param filter_profanity [Boolean] Filter profanity from the transcribed text, can be true or false
|
119
|
-
# @param redact_pii [Boolean] Redact PII from the transcribed text using the Redact PII model, can be true or
|
120
|
-
#
|
121
|
-
# @param
|
122
|
-
#
|
123
|
-
#
|
124
|
-
#
|
125
|
-
# @param
|
126
|
-
#
|
127
|
-
#
|
128
|
-
#
|
129
|
-
# @param
|
130
|
-
#
|
176
|
+
# @param redact_pii [Boolean] Redact PII from the transcribed text using the Redact PII model, can be true or
|
177
|
+
# false
|
178
|
+
# @param redact_pii_audio [Boolean] Generate a copy of the original media file with spoken PII "beeped" out, can be
|
179
|
+
# true or false. See [PII
|
180
|
+
# redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more
|
181
|
+
# details.
|
182
|
+
# @param redact_pii_audio_quality [AssemblyAI::Transcripts::RedactPiiAudioQuality] Controls the filetype of the audio created by redact_pii_audio. Currently
|
183
|
+
# supports mp3 (default) and wav. See [PII
|
184
|
+
# redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more
|
185
|
+
# details.
|
186
|
+
# @param redact_pii_policies [Array<AssemblyAI::Transcripts::PiiPolicy>] The list of PII Redaction policies to enable. See [PII
|
187
|
+
# redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more
|
188
|
+
# details.
|
189
|
+
# @param redact_pii_sub [AssemblyAI::Transcripts::SubstitutionPolicy]
|
190
|
+
# @param speaker_labels [Boolean] Enable [Speaker
|
191
|
+
# diarization](https://www.assemblyai.com/docs/models/speaker-diarization), can be
|
192
|
+
# true or false
|
193
|
+
# @param speakers_expected [Integer] Tells the speaker label model how many speakers it should attempt to identify,
|
194
|
+
# up to 10. See [Speaker
|
195
|
+
# diarization](https://www.assemblyai.com/docs/models/speaker-diarization) for
|
196
|
+
# more details.
|
197
|
+
# @param content_safety [Boolean] Enable [Content
|
198
|
+
# Moderation](https://www.assemblyai.com/docs/models/content-moderation), can be
|
199
|
+
# true or false
|
200
|
+
# @param content_safety_confidence [Integer] The confidence threshold for the Content Moderation model. Values must be
|
201
|
+
# between 25 and 100.
|
202
|
+
# @param iab_categories [Boolean] Enable [Topic
|
203
|
+
# Detection](https://www.assemblyai.com/docs/models/topic-detection), can be true
|
204
|
+
# or false
|
205
|
+
# @param custom_spelling [Array<Hash>] Customize how words are spelled and formatted using to and from valuesRequest of type Array<AssemblyAI::Transcripts::TranscriptCustomSpelling>, as a Hash
|
131
206
|
# * :from (Array<String>)
|
132
207
|
# * :to (String)
|
133
|
-
# @param
|
134
|
-
#
|
135
|
-
#
|
136
|
-
# @param
|
208
|
+
# @param sentiment_analysis [Boolean] Enable [Sentiment
|
209
|
+
# Analysis](https://www.assemblyai.com/docs/models/sentiment-analysis), can be
|
210
|
+
# true or false
|
211
|
+
# @param auto_chapters [Boolean] Enable [Auto Chapters](https://www.assemblyai.com/docs/models/auto-chapters),
|
212
|
+
# can be true or false
|
213
|
+
# @param entity_detection [Boolean] Enable [Entity
|
214
|
+
# Detection](https://www.assemblyai.com/docs/models/entity-detection), can be true
|
215
|
+
# or false
|
137
216
|
# @param speech_threshold [Float] Reject audio files that contain less than this fraction of speech.
|
138
|
-
#
|
139
|
-
# @param summarization [Boolean] Enable [Summarization](https://www.assemblyai.com/docs/models/summarization),
|
140
|
-
#
|
141
|
-
# @param
|
142
|
-
# @param
|
143
|
-
# @param
|
217
|
+
# Valid values are in the range [0, 1] inclusive.
|
218
|
+
# @param summarization [Boolean] Enable [Summarization](https://www.assemblyai.com/docs/models/summarization),
|
219
|
+
# can be true or false
|
220
|
+
# @param summary_model [AssemblyAI::Transcripts::SummaryModel] The model to summarize the transcript
|
221
|
+
# @param summary_type [AssemblyAI::Transcripts::SummaryType] The type of summary
|
222
|
+
# @param custom_topics [Boolean] Enable custom topics, either true or false
|
223
|
+
# @param topics [Array<String>] The list of custom topics
|
144
224
|
# @param audio_url [String] The URL of the audio or video file to transcribe.
|
145
|
-
# @param request_options [RequestOptions]
|
225
|
+
# @param request_options [AssemblyAI::RequestOptions]
|
146
226
|
# @param polling_options [Transcripts::PollingOptions] Configuration options for polling requests.
|
147
227
|
# @return [Transcripts::Transcript]
|
148
|
-
def transcribe(audio_url:,
|
149
|
-
webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil,
|
228
|
+
def transcribe(audio_url:, language_code: nil, language_detection: nil, language_confidence_threshold: nil, speech_model: nil,
|
229
|
+
punctuate: nil, format_text: nil, disfluencies: nil, multichannel: nil, dual_channel: nil, webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, custom_spelling: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, request_options: nil, polling_options: Transcripts::PollingOptions.new)
|
150
230
|
Async do
|
151
231
|
transcript = submit(audio_url: audio_url, speech_model: speech_model, language_code: language_code, punctuate: punctuate, format_text: format_text, dual_channel: dual_channel,
|
152
|
-
webhook_url: webhook_url, webhook_auth_header_name: webhook_auth_header_name, webhook_auth_header_value: webhook_auth_header_value, auto_highlights: auto_highlights, audio_start_from: audio_start_from, audio_end_at: audio_end_at, word_boost: word_boost, boost_param: boost_param, filter_profanity: filter_profanity, redact_pii: redact_pii, redact_pii_audio: redact_pii_audio, redact_pii_audio_quality: redact_pii_audio_quality, redact_pii_policies: redact_pii_policies, redact_pii_sub: redact_pii_sub, speaker_labels: speaker_labels, speakers_expected: speakers_expected, content_safety: content_safety, content_safety_confidence: content_safety_confidence, iab_categories: iab_categories, language_detection: language_detection, custom_spelling: custom_spelling, disfluencies: disfluencies, sentiment_analysis: sentiment_analysis, auto_chapters: auto_chapters, entity_detection: entity_detection, speech_threshold: speech_threshold, summarization: summarization, summary_model: summary_model, summary_type: summary_type, custom_topics: custom_topics, topics: topics, request_options: request_options)
|
232
|
+
webhook_url: webhook_url, webhook_auth_header_name: webhook_auth_header_name, webhook_auth_header_value: webhook_auth_header_value, auto_highlights: auto_highlights, audio_start_from: audio_start_from, audio_end_at: audio_end_at, word_boost: word_boost, boost_param: boost_param, filter_profanity: filter_profanity, redact_pii: redact_pii, redact_pii_audio: redact_pii_audio, redact_pii_audio_quality: redact_pii_audio_quality, redact_pii_policies: redact_pii_policies, redact_pii_sub: redact_pii_sub, speaker_labels: speaker_labels, speakers_expected: speakers_expected, content_safety: content_safety, content_safety_confidence: content_safety_confidence, iab_categories: iab_categories, language_detection: language_detection, language_confidence_threshold: language_confidence_threshold, custom_spelling: custom_spelling, disfluencies: disfluencies, multichannel: multichannel, sentiment_analysis: sentiment_analysis, auto_chapters: auto_chapters, entity_detection: entity_detection, speech_threshold: speech_threshold, summarization: summarization, summary_model: summary_model, summary_type: summary_type, custom_topics: custom_topics, topics: topics, request_options: request_options)
|
153
233
|
wait_until_ready(transcript_id: transcript.id, polling_options: polling_options).wait
|
154
234
|
end
|
155
235
|
end
|
@@ -15,7 +15,7 @@ module AssemblyAI
|
|
15
15
|
# @return [AssemblyAI::Transcripts::AudioIntelligenceModelStatus] The status of the Content Moderation model. Either success, or unavailable in
|
16
16
|
# the rare case that the model failed.
|
17
17
|
attr_reader :status
|
18
|
-
# @return [Array<AssemblyAI::Transcripts::ContentSafetyLabelResult>]
|
18
|
+
# @return [Array<AssemblyAI::Transcripts::ContentSafetyLabelResult>] An array of results for the Content Moderation model
|
19
19
|
attr_reader :results
|
20
20
|
# @return [Hash{String => Float}] A summary of the Content Moderation confidence results for the entire audio file
|
21
21
|
attr_reader :summary
|
@@ -31,7 +31,7 @@ module AssemblyAI
|
|
31
31
|
|
32
32
|
# @param status [AssemblyAI::Transcripts::AudioIntelligenceModelStatus] The status of the Content Moderation model. Either success, or unavailable in
|
33
33
|
# the rare case that the model failed.
|
34
|
-
# @param results [Array<AssemblyAI::Transcripts::ContentSafetyLabelResult>]
|
34
|
+
# @param results [Array<AssemblyAI::Transcripts::ContentSafetyLabelResult>] An array of results for the Content Moderation model
|
35
35
|
# @param summary [Hash{String => Float}] A summary of the Content Moderation confidence results for the entire audio file
|
36
36
|
# @param severity_score_summary [Hash{String => AssemblyAI::Transcripts::SeverityScoreSummary}] A summary of the Content Moderation severity results for the entire audio file
|
37
37
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
@@ -7,13 +7,13 @@ require "json"
|
|
7
7
|
module AssemblyAI
|
8
8
|
class Transcripts
|
9
9
|
class ParagraphsResponse
|
10
|
-
# @return [String]
|
10
|
+
# @return [String] The unique identifier of your transcript
|
11
11
|
attr_reader :id
|
12
|
-
# @return [Float]
|
12
|
+
# @return [Float] The confidence score for the transcript
|
13
13
|
attr_reader :confidence
|
14
|
-
# @return [Float]
|
14
|
+
# @return [Float] The duration of the audio file in seconds
|
15
15
|
attr_reader :audio_duration
|
16
|
-
# @return [Array<AssemblyAI::Transcripts::TranscriptParagraph>]
|
16
|
+
# @return [Array<AssemblyAI::Transcripts::TranscriptParagraph>] An array of paragraphs in the transcript
|
17
17
|
attr_reader :paragraphs
|
18
18
|
# @return [OpenStruct] Additional properties unmapped to the current class definition
|
19
19
|
attr_reader :additional_properties
|
@@ -23,10 +23,10 @@ module AssemblyAI
|
|
23
23
|
|
24
24
|
OMIT = Object.new
|
25
25
|
|
26
|
-
# @param id [String]
|
27
|
-
# @param confidence [Float]
|
28
|
-
# @param audio_duration [Float]
|
29
|
-
# @param paragraphs [Array<AssemblyAI::Transcripts::TranscriptParagraph>]
|
26
|
+
# @param id [String] The unique identifier of your transcript
|
27
|
+
# @param confidence [Float] The confidence score for the transcript
|
28
|
+
# @param audio_duration [Float] The duration of the audio file in seconds
|
29
|
+
# @param paragraphs [Array<AssemblyAI::Transcripts::TranscriptParagraph>] An array of paragraphs in the transcript
|
30
30
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
31
31
|
# @return [AssemblyAI::Transcripts::ParagraphsResponse]
|
32
32
|
def initialize(id:, confidence:, audio_duration:, paragraphs:, additional_properties: nil)
|
@@ -7,13 +7,13 @@ require "json"
|
|
7
7
|
module AssemblyAI
|
8
8
|
class Transcripts
|
9
9
|
class SentencesResponse
|
10
|
-
# @return [String]
|
10
|
+
# @return [String] The unique identifier for the transcript
|
11
11
|
attr_reader :id
|
12
|
-
# @return [Float]
|
12
|
+
# @return [Float] The confidence score for the transcript
|
13
13
|
attr_reader :confidence
|
14
|
-
# @return [Float]
|
14
|
+
# @return [Float] The duration of the audio file in seconds
|
15
15
|
attr_reader :audio_duration
|
16
|
-
# @return [Array<AssemblyAI::Transcripts::TranscriptSentence>]
|
16
|
+
# @return [Array<AssemblyAI::Transcripts::TranscriptSentence>] An array of sentences in the transcript
|
17
17
|
attr_reader :sentences
|
18
18
|
# @return [OpenStruct] Additional properties unmapped to the current class definition
|
19
19
|
attr_reader :additional_properties
|
@@ -23,10 +23,10 @@ module AssemblyAI
|
|
23
23
|
|
24
24
|
OMIT = Object.new
|
25
25
|
|
26
|
-
# @param id [String]
|
27
|
-
# @param confidence [Float]
|
28
|
-
# @param audio_duration [Float]
|
29
|
-
# @param sentences [Array<AssemblyAI::Transcripts::TranscriptSentence>]
|
26
|
+
# @param id [String] The unique identifier for the transcript
|
27
|
+
# @param confidence [Float] The confidence score for the transcript
|
28
|
+
# @param audio_duration [Float] The duration of the audio file in seconds
|
29
|
+
# @param sentences [Array<AssemblyAI::Transcripts::TranscriptSentence>] An array of sentences in the transcript
|
30
30
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
31
31
|
# @return [AssemblyAI::Transcripts::SentencesResponse]
|
32
32
|
def initialize(id:, confidence:, audio_duration:, sentences:, additional_properties: nil)
|
@@ -18,6 +18,9 @@ module AssemblyAI
|
|
18
18
|
attr_reader :sentiment
|
19
19
|
# @return [Float] The confidence score for the detected sentiment of the sentence, from 0 to 1
|
20
20
|
attr_reader :confidence
|
21
|
+
# @return [String] The channel of this utterance. The left and right channels are channels 1 and 2.
|
22
|
+
# Additional channels increment the channel number sequentially.
|
23
|
+
attr_reader :channel
|
21
24
|
# @return [String] The speaker of the sentence if [Speaker
|
22
25
|
# Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is
|
23
26
|
# enabled, else null
|
@@ -35,17 +38,21 @@ module AssemblyAI
|
|
35
38
|
# @param end_ [Integer] The ending time, in milliseconds, of the sentence
|
36
39
|
# @param sentiment [AssemblyAI::Transcripts::Sentiment] The detected sentiment for the sentence, one of POSITIVE, NEUTRAL, NEGATIVE
|
37
40
|
# @param confidence [Float] The confidence score for the detected sentiment of the sentence, from 0 to 1
|
41
|
+
# @param channel [String] The channel of this utterance. The left and right channels are channels 1 and 2.
|
42
|
+
# Additional channels increment the channel number sequentially.
|
38
43
|
# @param speaker [String] The speaker of the sentence if [Speaker
|
39
44
|
# Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is
|
40
45
|
# enabled, else null
|
41
46
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
42
47
|
# @return [AssemblyAI::Transcripts::SentimentAnalysisResult]
|
43
|
-
def initialize(text:, start:, end_:, sentiment:, confidence:,
|
48
|
+
def initialize(text:, start:, end_:, sentiment:, confidence:, channel: OMIT, speaker: OMIT,
|
49
|
+
additional_properties: nil)
|
44
50
|
@text = text
|
45
51
|
@start = start
|
46
52
|
@end_ = end_
|
47
53
|
@sentiment = sentiment
|
48
54
|
@confidence = confidence
|
55
|
+
@channel = channel if channel != OMIT
|
49
56
|
@speaker = speaker if speaker != OMIT
|
50
57
|
@additional_properties = additional_properties
|
51
58
|
@_field_set = {
|
@@ -54,6 +61,7 @@ module AssemblyAI
|
|
54
61
|
"end": end_,
|
55
62
|
"sentiment": sentiment,
|
56
63
|
"confidence": confidence,
|
64
|
+
"channel": channel,
|
57
65
|
"speaker": speaker
|
58
66
|
}.reject do |_k, v|
|
59
67
|
v == OMIT
|
@@ -71,6 +79,7 @@ module AssemblyAI
|
|
71
79
|
end_ = struct["end"]
|
72
80
|
sentiment = struct["sentiment"]
|
73
81
|
confidence = struct["confidence"]
|
82
|
+
channel = struct["channel"]
|
74
83
|
speaker = struct["speaker"]
|
75
84
|
new(
|
76
85
|
text: text,
|
@@ -78,6 +87,7 @@ module AssemblyAI
|
|
78
87
|
end_: end_,
|
79
88
|
sentiment: sentiment,
|
80
89
|
confidence: confidence,
|
90
|
+
channel: channel,
|
81
91
|
speaker: speaker,
|
82
92
|
additional_properties: struct
|
83
93
|
)
|
@@ -102,6 +112,7 @@ module AssemblyAI
|
|
102
112
|
obj.end_.is_a?(Integer) != false || raise("Passed value for field obj.end_ is not the expected type, validation failed.")
|
103
113
|
obj.sentiment.is_a?(AssemblyAI::Transcripts::Sentiment) != false || raise("Passed value for field obj.sentiment is not the expected type, validation failed.")
|
104
114
|
obj.confidence.is_a?(Float) != false || raise("Passed value for field obj.confidence is not the expected type, validation failed.")
|
115
|
+
obj.channel&.is_a?(String) != false || raise("Passed value for field obj.channel is not the expected type, validation failed.")
|
105
116
|
obj.speaker&.is_a?(String) != false || raise("Passed value for field obj.speaker is not the expected type, validation failed.")
|
106
117
|
end
|
107
118
|
end
|
@@ -11,7 +11,7 @@ module AssemblyAI
|
|
11
11
|
class TopicDetectionResult
|
12
12
|
# @return [String] The text in the transcript in which a detected topic occurs
|
13
13
|
attr_reader :text
|
14
|
-
# @return [Array<AssemblyAI::Transcripts::TopicDetectionResultLabelsItem>]
|
14
|
+
# @return [Array<AssemblyAI::Transcripts::TopicDetectionResultLabelsItem>] An array of detected topics in the text
|
15
15
|
attr_reader :labels
|
16
16
|
# @return [AssemblyAI::Transcripts::Timestamp]
|
17
17
|
attr_reader :timestamp
|
@@ -24,7 +24,7 @@ module AssemblyAI
|
|
24
24
|
OMIT = Object.new
|
25
25
|
|
26
26
|
# @param text [String] The text in the transcript in which a detected topic occurs
|
27
|
-
# @param labels [Array<AssemblyAI::Transcripts::TopicDetectionResultLabelsItem>]
|
27
|
+
# @param labels [Array<AssemblyAI::Transcripts::TopicDetectionResultLabelsItem>] An array of detected topics in the text
|
28
28
|
# @param timestamp [AssemblyAI::Transcripts::Timestamp]
|
29
29
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
30
30
|
# @return [AssemblyAI::Transcripts::TopicDetectionResult]
|
@@ -40,7 +40,6 @@ module AssemblyAI
|
|
40
40
|
attr_reader :language_detection
|
41
41
|
# @return [Float] The confidence threshold for the automatically detected language.
|
42
42
|
# An error will be returned if the language confidence is below this threshold.
|
43
|
-
# Defaults to 0.
|
44
43
|
attr_reader :language_confidence_threshold
|
45
44
|
# @return [Float] The confidence score for the detected language, between 0.0 (low confidence) and
|
46
45
|
# 1.0 (high confidence)
|
@@ -72,6 +71,13 @@ module AssemblyAI
|
|
72
71
|
attr_reader :format_text
|
73
72
|
# @return [Boolean] Transcribe Filler Words, like "umm", in your media file; can be true or false
|
74
73
|
attr_reader :disfluencies
|
74
|
+
# @return [Boolean] Whether [Multichannel
|
75
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription)
|
76
|
+
# was enabled in the transcription request, either true or false
|
77
|
+
attr_reader :multichannel
|
78
|
+
# @return [Integer] The number of audio channels in the audio file. This is only present when
|
79
|
+
# multichannel is enabled.
|
80
|
+
attr_reader :audio_channels
|
75
81
|
# @return [Boolean] Whether [Dual channel
|
76
82
|
# ://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription)
|
77
83
|
# was enabled in the transcription request, either true or false
|
@@ -224,7 +230,6 @@ module AssemblyAI
|
|
224
230
|
# is enabled, either true or false
|
225
231
|
# @param language_confidence_threshold [Float] The confidence threshold for the automatically detected language.
|
226
232
|
# An error will be returned if the language confidence is below this threshold.
|
227
|
-
# Defaults to 0.
|
228
233
|
# @param language_confidence [Float] The confidence score for the detected language, between 0.0 (low confidence) and
|
229
234
|
# 1.0 (high confidence)
|
230
235
|
# @param speech_model [AssemblyAI::Transcripts::SpeechModel]
|
@@ -245,6 +250,11 @@ module AssemblyAI
|
|
245
250
|
# @param punctuate [Boolean] Whether Automatic Punctuation is enabled, either true or false
|
246
251
|
# @param format_text [Boolean] Whether Text Formatting is enabled, either true or false
|
247
252
|
# @param disfluencies [Boolean] Transcribe Filler Words, like "umm", in your media file; can be true or false
|
253
|
+
# @param multichannel [Boolean] Whether [Multichannel
|
254
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription)
|
255
|
+
# was enabled in the transcription request, either true or false
|
256
|
+
# @param audio_channels [Integer] The number of audio channels in the audio file. This is only present when
|
257
|
+
# multichannel is enabled.
|
248
258
|
# @param dual_channel [Boolean] Whether [Dual channel
|
249
259
|
# ://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription)
|
250
260
|
# was enabled in the transcription request, either true or false
|
@@ -337,7 +347,7 @@ module AssemblyAI
|
|
337
347
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
338
348
|
# @return [AssemblyAI::Transcripts::Transcript]
|
339
349
|
def initialize(id:, audio_url:, status:, webhook_auth:, auto_highlights:, redact_pii:, summarization:, language_model:, acoustic_model:, language_code: OMIT, language_detection: OMIT,
|
340
|
-
language_confidence_threshold: OMIT, language_confidence: OMIT, speech_model: OMIT, text: OMIT, words: OMIT, utterances: OMIT, confidence: OMIT, audio_duration: OMIT, punctuate: OMIT, format_text: OMIT, disfluencies: OMIT, dual_channel: OMIT, webhook_url: OMIT, webhook_status_code: OMIT, webhook_auth_header_name: OMIT, speed_boost: OMIT, auto_highlights_result: OMIT, audio_start_from: OMIT, audio_end_at: OMIT, word_boost: OMIT, boost_param: OMIT, filter_profanity: OMIT, redact_pii_audio: OMIT, redact_pii_audio_quality: OMIT, redact_pii_policies: OMIT, redact_pii_sub: OMIT, speaker_labels: OMIT, speakers_expected: OMIT, content_safety: OMIT, content_safety_labels: OMIT, iab_categories: OMIT, iab_categories_result: OMIT, custom_spelling: OMIT, auto_chapters: OMIT, chapters: OMIT, summary_type: OMIT, summary_model: OMIT, summary: OMIT, custom_topics: OMIT, topics: OMIT, sentiment_analysis: OMIT, sentiment_analysis_results: OMIT, entity_detection: OMIT, entities: OMIT, speech_threshold: OMIT, throttled: OMIT, error: OMIT, additional_properties: nil)
|
350
|
+
language_confidence_threshold: OMIT, language_confidence: OMIT, speech_model: OMIT, text: OMIT, words: OMIT, utterances: OMIT, confidence: OMIT, audio_duration: OMIT, punctuate: OMIT, format_text: OMIT, disfluencies: OMIT, multichannel: OMIT, audio_channels: OMIT, dual_channel: OMIT, webhook_url: OMIT, webhook_status_code: OMIT, webhook_auth_header_name: OMIT, speed_boost: OMIT, auto_highlights_result: OMIT, audio_start_from: OMIT, audio_end_at: OMIT, word_boost: OMIT, boost_param: OMIT, filter_profanity: OMIT, redact_pii_audio: OMIT, redact_pii_audio_quality: OMIT, redact_pii_policies: OMIT, redact_pii_sub: OMIT, speaker_labels: OMIT, speakers_expected: OMIT, content_safety: OMIT, content_safety_labels: OMIT, iab_categories: OMIT, iab_categories_result: OMIT, custom_spelling: OMIT, auto_chapters: OMIT, chapters: OMIT, summary_type: OMIT, summary_model: OMIT, summary: OMIT, custom_topics: OMIT, topics: OMIT, sentiment_analysis: OMIT, sentiment_analysis_results: OMIT, entity_detection: OMIT, entities: OMIT, speech_threshold: OMIT, throttled: OMIT, error: OMIT, additional_properties: nil)
|
341
351
|
@id = id
|
342
352
|
@audio_url = audio_url
|
343
353
|
@status = status
|
@@ -354,6 +364,8 @@ module AssemblyAI
|
|
354
364
|
@punctuate = punctuate if punctuate != OMIT
|
355
365
|
@format_text = format_text if format_text != OMIT
|
356
366
|
@disfluencies = disfluencies if disfluencies != OMIT
|
367
|
+
@multichannel = multichannel if multichannel != OMIT
|
368
|
+
@audio_channels = audio_channels if audio_channels != OMIT
|
357
369
|
@dual_channel = dual_channel if dual_channel != OMIT
|
358
370
|
@webhook_url = webhook_url if webhook_url != OMIT
|
359
371
|
@webhook_status_code = webhook_status_code if webhook_status_code != OMIT
|
@@ -414,6 +426,8 @@ module AssemblyAI
|
|
414
426
|
"punctuate": punctuate,
|
415
427
|
"format_text": format_text,
|
416
428
|
"disfluencies": disfluencies,
|
429
|
+
"multichannel": multichannel,
|
430
|
+
"audio_channels": audio_channels,
|
417
431
|
"dual_channel": dual_channel,
|
418
432
|
"webhook_url": webhook_url,
|
419
433
|
"webhook_status_code": webhook_status_code,
|
@@ -490,6 +504,8 @@ module AssemblyAI
|
|
490
504
|
punctuate = struct["punctuate"]
|
491
505
|
format_text = struct["format_text"]
|
492
506
|
disfluencies = struct["disfluencies"]
|
507
|
+
multichannel = struct["multichannel"]
|
508
|
+
audio_channels = struct["audio_channels"]
|
493
509
|
dual_channel = struct["dual_channel"]
|
494
510
|
webhook_url = struct["webhook_url"]
|
495
511
|
webhook_status_code = struct["webhook_status_code"]
|
@@ -576,6 +592,8 @@ module AssemblyAI
|
|
576
592
|
punctuate: punctuate,
|
577
593
|
format_text: format_text,
|
578
594
|
disfluencies: disfluencies,
|
595
|
+
multichannel: multichannel,
|
596
|
+
audio_channels: audio_channels,
|
579
597
|
dual_channel: dual_channel,
|
580
598
|
webhook_url: webhook_url,
|
581
599
|
webhook_status_code: webhook_status_code,
|
@@ -652,6 +670,8 @@ module AssemblyAI
|
|
652
670
|
obj.punctuate&.is_a?(Boolean) != false || raise("Passed value for field obj.punctuate is not the expected type, validation failed.")
|
653
671
|
obj.format_text&.is_a?(Boolean) != false || raise("Passed value for field obj.format_text is not the expected type, validation failed.")
|
654
672
|
obj.disfluencies&.is_a?(Boolean) != false || raise("Passed value for field obj.disfluencies is not the expected type, validation failed.")
|
673
|
+
obj.multichannel&.is_a?(Boolean) != false || raise("Passed value for field obj.multichannel is not the expected type, validation failed.")
|
674
|
+
obj.audio_channels&.is_a?(Integer) != false || raise("Passed value for field obj.audio_channels is not the expected type, validation failed.")
|
655
675
|
obj.dual_channel&.is_a?(Boolean) != false || raise("Passed value for field obj.dual_channel is not the expected type, validation failed.")
|
656
676
|
obj.webhook_url&.is_a?(String) != false || raise("Passed value for field obj.webhook_url is not the expected type, validation failed.")
|
657
677
|
obj.webhook_status_code&.is_a?(Integer) != false || raise("Passed value for field obj.webhook_status_code is not the expected type, validation failed.")
|
@@ -10,9 +10,9 @@ module AssemblyAI
|
|
10
10
|
# A list of transcripts. Transcripts are sorted from newest to oldest. The
|
11
11
|
# previous URL always points to a page with older transcripts.
|
12
12
|
class TranscriptList
|
13
|
-
# @return [AssemblyAI::Transcripts::PageDetails]
|
13
|
+
# @return [AssemblyAI::Transcripts::PageDetails] Details of the transcript page
|
14
14
|
attr_reader :page_details
|
15
|
-
# @return [Array<AssemblyAI::Transcripts::TranscriptListItem>]
|
15
|
+
# @return [Array<AssemblyAI::Transcripts::TranscriptListItem>] An array of transcripts
|
16
16
|
attr_reader :transcripts
|
17
17
|
# @return [OpenStruct] Additional properties unmapped to the current class definition
|
18
18
|
attr_reader :additional_properties
|
@@ -22,8 +22,8 @@ module AssemblyAI
|
|
22
22
|
|
23
23
|
OMIT = Object.new
|
24
24
|
|
25
|
-
# @param page_details [AssemblyAI::Transcripts::PageDetails]
|
26
|
-
# @param transcripts [Array<AssemblyAI::Transcripts::TranscriptListItem>]
|
25
|
+
# @param page_details [AssemblyAI::Transcripts::PageDetails] Details of the transcript page
|
26
|
+
# @param transcripts [Array<AssemblyAI::Transcripts::TranscriptListItem>] An array of transcripts
|
27
27
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
28
28
|
# @return [AssemblyAI::Transcripts::TranscriptList]
|
29
29
|
def initialize(page_details:, transcripts:, additional_properties: nil)
|
@@ -8,17 +8,17 @@ require "json"
|
|
8
8
|
module AssemblyAI
|
9
9
|
class Transcripts
|
10
10
|
class TranscriptListItem
|
11
|
-
# @return [String]
|
11
|
+
# @return [String] The unique identifier for the transcript
|
12
12
|
attr_reader :id
|
13
|
-
# @return [String]
|
13
|
+
# @return [String] The URL to retrieve the transcript
|
14
14
|
attr_reader :resource_url
|
15
|
-
# @return [AssemblyAI::Transcripts::TranscriptStatus]
|
15
|
+
# @return [AssemblyAI::Transcripts::TranscriptStatus] The status of the transcript
|
16
16
|
attr_reader :status
|
17
|
-
# @return [DateTime]
|
17
|
+
# @return [DateTime] The date and time the transcript was created
|
18
18
|
attr_reader :created
|
19
|
-
# @return [DateTime]
|
19
|
+
# @return [DateTime] The date and time the transcript was completed
|
20
20
|
attr_reader :completed
|
21
|
-
# @return [String]
|
21
|
+
# @return [String] The URL to the audio file
|
22
22
|
attr_reader :audio_url
|
23
23
|
# @return [String] Error message of why the transcript failed
|
24
24
|
attr_reader :error
|
@@ -30,12 +30,12 @@ module AssemblyAI
|
|
30
30
|
|
31
31
|
OMIT = Object.new
|
32
32
|
|
33
|
-
# @param id [String]
|
34
|
-
# @param resource_url [String]
|
35
|
-
# @param status [AssemblyAI::Transcripts::TranscriptStatus]
|
36
|
-
# @param created [DateTime]
|
37
|
-
# @param completed [DateTime]
|
38
|
-
# @param audio_url [String]
|
33
|
+
# @param id [String] The unique identifier for the transcript
|
34
|
+
# @param resource_url [String] The URL to retrieve the transcript
|
35
|
+
# @param status [AssemblyAI::Transcripts::TranscriptStatus] The status of the transcript
|
36
|
+
# @param created [DateTime] The date and time the transcript was created
|
37
|
+
# @param completed [DateTime] The date and time the transcript was completed
|
38
|
+
# @param audio_url [String] The URL to the audio file
|
39
39
|
# @param error [String] Error message of why the transcript failed
|
40
40
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
41
41
|
# @return [AssemblyAI::Transcripts::TranscriptListItem]
|
@@ -34,13 +34,18 @@ module AssemblyAI
|
|
34
34
|
attr_reader :format_text
|
35
35
|
# @return [Boolean] Transcribe Filler Words, like "umm", in your media file; can be true or false
|
36
36
|
attr_reader :disfluencies
|
37
|
+
# @return [Boolean] Enable
|
38
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription)
|
39
|
+
# transcription, can be true or false.
|
40
|
+
attr_reader :multichannel
|
37
41
|
# @return [Boolean] Enable [Dual
|
38
42
|
# ://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription)
|
39
43
|
# transcription, can be true or false.
|
40
44
|
attr_reader :dual_channel
|
41
|
-
# @return [String] The URL to which we send webhook requests.
|
42
|
-
#
|
43
|
-
# request when
|
45
|
+
# @return [String] The URL to which we send webhook requests.
|
46
|
+
# We sends two different types of webhook requests.
|
47
|
+
# One request when a transcript is completed or failed, and one request when the
|
48
|
+
# redacted audio is ready if redact_pii_audio is enabled.
|
44
49
|
attr_reader :webhook_url
|
45
50
|
# @return [String] The header name to be sent with the transcript completed or failed webhook
|
46
51
|
# requests
|
@@ -145,12 +150,16 @@ module AssemblyAI
|
|
145
150
|
# @param punctuate [Boolean] Enable Automatic Punctuation, can be true or false
|
146
151
|
# @param format_text [Boolean] Enable Text Formatting, can be true or false
|
147
152
|
# @param disfluencies [Boolean] Transcribe Filler Words, like "umm", in your media file; can be true or false
|
153
|
+
# @param multichannel [Boolean] Enable
|
154
|
+
# ://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription)
|
155
|
+
# transcription, can be true or false.
|
148
156
|
# @param dual_channel [Boolean] Enable [Dual
|
149
157
|
# ://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription)
|
150
158
|
# transcription, can be true or false.
|
151
|
-
# @param webhook_url [String] The URL to which we send webhook requests.
|
152
|
-
#
|
153
|
-
# request when
|
159
|
+
# @param webhook_url [String] The URL to which we send webhook requests.
|
160
|
+
# We sends two different types of webhook requests.
|
161
|
+
# One request when a transcript is completed or failed, and one request when the
|
162
|
+
# redacted audio is ready if redact_pii_audio is enabled.
|
154
163
|
# @param webhook_auth_header_name [String] The header name to be sent with the transcript completed or failed webhook
|
155
164
|
# requests
|
156
165
|
# @param webhook_auth_header_value [String] The header value to send back with the transcript completed or failed webhook
|
@@ -210,7 +219,7 @@ module AssemblyAI
|
|
210
219
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
211
220
|
# @return [AssemblyAI::Transcripts::TranscriptOptionalParams]
|
212
221
|
def initialize(language_code: OMIT, language_detection: OMIT, language_confidence_threshold: OMIT,
|
213
|
-
speech_model: OMIT, punctuate: OMIT, format_text: OMIT, disfluencies: OMIT, dual_channel: OMIT, webhook_url: OMIT, webhook_auth_header_name: OMIT, webhook_auth_header_value: OMIT, auto_highlights: OMIT, audio_start_from: OMIT, audio_end_at: OMIT, word_boost: OMIT, boost_param: OMIT, filter_profanity: OMIT, redact_pii: OMIT, redact_pii_audio: OMIT, redact_pii_audio_quality: OMIT, redact_pii_policies: OMIT, redact_pii_sub: OMIT, speaker_labels: OMIT, speakers_expected: OMIT, content_safety: OMIT, content_safety_confidence: OMIT, iab_categories: OMIT, custom_spelling: OMIT, sentiment_analysis: OMIT, auto_chapters: OMIT, entity_detection: OMIT, speech_threshold: OMIT, summarization: OMIT, summary_model: OMIT, summary_type: OMIT, custom_topics: OMIT, topics: OMIT, additional_properties: nil)
|
222
|
+
speech_model: OMIT, punctuate: OMIT, format_text: OMIT, disfluencies: OMIT, multichannel: OMIT, dual_channel: OMIT, webhook_url: OMIT, webhook_auth_header_name: OMIT, webhook_auth_header_value: OMIT, auto_highlights: OMIT, audio_start_from: OMIT, audio_end_at: OMIT, word_boost: OMIT, boost_param: OMIT, filter_profanity: OMIT, redact_pii: OMIT, redact_pii_audio: OMIT, redact_pii_audio_quality: OMIT, redact_pii_policies: OMIT, redact_pii_sub: OMIT, speaker_labels: OMIT, speakers_expected: OMIT, content_safety: OMIT, content_safety_confidence: OMIT, iab_categories: OMIT, custom_spelling: OMIT, sentiment_analysis: OMIT, auto_chapters: OMIT, entity_detection: OMIT, speech_threshold: OMIT, summarization: OMIT, summary_model: OMIT, summary_type: OMIT, custom_topics: OMIT, topics: OMIT, additional_properties: nil)
|
214
223
|
@language_code = language_code if language_code != OMIT
|
215
224
|
@language_detection = language_detection if language_detection != OMIT
|
216
225
|
@language_confidence_threshold = language_confidence_threshold if language_confidence_threshold != OMIT
|
@@ -218,6 +227,7 @@ module AssemblyAI
|
|
218
227
|
@punctuate = punctuate if punctuate != OMIT
|
219
228
|
@format_text = format_text if format_text != OMIT
|
220
229
|
@disfluencies = disfluencies if disfluencies != OMIT
|
230
|
+
@multichannel = multichannel if multichannel != OMIT
|
221
231
|
@dual_channel = dual_channel if dual_channel != OMIT
|
222
232
|
@webhook_url = webhook_url if webhook_url != OMIT
|
223
233
|
@webhook_auth_header_name = webhook_auth_header_name if webhook_auth_header_name != OMIT
|
@@ -257,6 +267,7 @@ module AssemblyAI
|
|
257
267
|
"punctuate": punctuate,
|
258
268
|
"format_text": format_text,
|
259
269
|
"disfluencies": disfluencies,
|
270
|
+
"multichannel": multichannel,
|
260
271
|
"dual_channel": dual_channel,
|
261
272
|
"webhook_url": webhook_url,
|
262
273
|
"webhook_auth_header_name": webhook_auth_header_name,
|
@@ -306,6 +317,7 @@ module AssemblyAI
|
|
306
317
|
punctuate = struct["punctuate"]
|
307
318
|
format_text = struct["format_text"]
|
308
319
|
disfluencies = struct["disfluencies"]
|
320
|
+
multichannel = struct["multichannel"]
|
309
321
|
dual_channel = struct["dual_channel"]
|
310
322
|
webhook_url = struct["webhook_url"]
|
311
323
|
webhook_auth_header_name = struct["webhook_auth_header_name"]
|
@@ -347,6 +359,7 @@ module AssemblyAI
|
|
347
359
|
punctuate: punctuate,
|
348
360
|
format_text: format_text,
|
349
361
|
disfluencies: disfluencies,
|
362
|
+
multichannel: multichannel,
|
350
363
|
dual_channel: dual_channel,
|
351
364
|
webhook_url: webhook_url,
|
352
365
|
webhook_auth_header_name: webhook_auth_header_name,
|
@@ -402,6 +415,7 @@ module AssemblyAI
|
|
402
415
|
obj.punctuate&.is_a?(Boolean) != false || raise("Passed value for field obj.punctuate is not the expected type, validation failed.")
|
403
416
|
obj.format_text&.is_a?(Boolean) != false || raise("Passed value for field obj.format_text is not the expected type, validation failed.")
|
404
417
|
obj.disfluencies&.is_a?(Boolean) != false || raise("Passed value for field obj.disfluencies is not the expected type, validation failed.")
|
418
|
+
obj.multichannel&.is_a?(Boolean) != false || raise("Passed value for field obj.multichannel is not the expected type, validation failed.")
|
405
419
|
obj.dual_channel&.is_a?(Boolean) != false || raise("Passed value for field obj.dual_channel is not the expected type, validation failed.")
|
406
420
|
obj.webhook_url&.is_a?(String) != false || raise("Passed value for field obj.webhook_url is not the expected type, validation failed.")
|
407
421
|
obj.webhook_auth_header_name&.is_a?(String) != false || raise("Passed value for field obj.webhook_auth_header_name is not the expected type, validation failed.")
|
@@ -7,20 +7,16 @@ require "json"
|
|
7
7
|
module AssemblyAI
|
8
8
|
class Transcripts
|
9
9
|
class TranscriptParagraph
|
10
|
-
# @return [String]
|
10
|
+
# @return [String] The transcript of the paragraph
|
11
11
|
attr_reader :text
|
12
|
-
# @return [Integer]
|
12
|
+
# @return [Integer] The starting time, in milliseconds, of the paragraph
|
13
13
|
attr_reader :start
|
14
|
-
# @return [Integer]
|
14
|
+
# @return [Integer] The ending time, in milliseconds, of the paragraph
|
15
15
|
attr_reader :end_
|
16
|
-
# @return [Float]
|
16
|
+
# @return [Float] The confidence score for the transcript of this paragraph
|
17
17
|
attr_reader :confidence
|
18
|
-
# @return [Array<AssemblyAI::Transcripts::TranscriptWord>]
|
18
|
+
# @return [Array<AssemblyAI::Transcripts::TranscriptWord>] An array of words in the paragraph
|
19
19
|
attr_reader :words
|
20
|
-
# @return [String] The speaker of the sentence if [Speaker
|
21
|
-
# Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is
|
22
|
-
# enabled, else null
|
23
|
-
attr_reader :speaker
|
24
20
|
# @return [OpenStruct] Additional properties unmapped to the current class definition
|
25
21
|
attr_reader :additional_properties
|
26
22
|
# @return [Object]
|
@@ -29,34 +25,21 @@ module AssemblyAI
|
|
29
25
|
|
30
26
|
OMIT = Object.new
|
31
27
|
|
32
|
-
# @param text [String]
|
33
|
-
# @param start [Integer]
|
34
|
-
# @param end_ [Integer]
|
35
|
-
# @param confidence [Float]
|
36
|
-
# @param words [Array<AssemblyAI::Transcripts::TranscriptWord>]
|
37
|
-
# @param speaker [String] The speaker of the sentence if [Speaker
|
38
|
-
# Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is
|
39
|
-
# enabled, else null
|
28
|
+
# @param text [String] The transcript of the paragraph
|
29
|
+
# @param start [Integer] The starting time, in milliseconds, of the paragraph
|
30
|
+
# @param end_ [Integer] The ending time, in milliseconds, of the paragraph
|
31
|
+
# @param confidence [Float] The confidence score for the transcript of this paragraph
|
32
|
+
# @param words [Array<AssemblyAI::Transcripts::TranscriptWord>] An array of words in the paragraph
|
40
33
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
41
34
|
# @return [AssemblyAI::Transcripts::TranscriptParagraph]
|
42
|
-
def initialize(text:, start:, end_:, confidence:, words:,
|
35
|
+
def initialize(text:, start:, end_:, confidence:, words:, additional_properties: nil)
|
43
36
|
@text = text
|
44
37
|
@start = start
|
45
38
|
@end_ = end_
|
46
39
|
@confidence = confidence
|
47
40
|
@words = words
|
48
|
-
@speaker = speaker if speaker != OMIT
|
49
41
|
@additional_properties = additional_properties
|
50
|
-
@_field_set = {
|
51
|
-
"text": text,
|
52
|
-
"start": start,
|
53
|
-
"end": end_,
|
54
|
-
"confidence": confidence,
|
55
|
-
"words": words,
|
56
|
-
"speaker": speaker
|
57
|
-
}.reject do |_k, v|
|
58
|
-
v == OMIT
|
59
|
-
end
|
42
|
+
@_field_set = { "text": text, "start": start, "end": end_, "confidence": confidence, "words": words }
|
60
43
|
end
|
61
44
|
|
62
45
|
# Deserialize a JSON object to an instance of TranscriptParagraph
|
@@ -74,14 +57,12 @@ module AssemblyAI
|
|
74
57
|
v = v.to_json
|
75
58
|
AssemblyAI::Transcripts::TranscriptWord.from_json(json_object: v)
|
76
59
|
end
|
77
|
-
speaker = struct["speaker"]
|
78
60
|
new(
|
79
61
|
text: text,
|
80
62
|
start: start,
|
81
63
|
end_: end_,
|
82
64
|
confidence: confidence,
|
83
65
|
words: words,
|
84
|
-
speaker: speaker,
|
85
66
|
additional_properties: struct
|
86
67
|
)
|
87
68
|
end
|
@@ -105,7 +86,6 @@ module AssemblyAI
|
|
105
86
|
obj.end_.is_a?(Integer) != false || raise("Passed value for field obj.end_ is not the expected type, validation failed.")
|
106
87
|
obj.confidence.is_a?(Float) != false || raise("Passed value for field obj.confidence is not the expected type, validation failed.")
|
107
88
|
obj.words.is_a?(Array) != false || raise("Passed value for field obj.words is not the expected type, validation failed.")
|
108
|
-
obj.speaker&.is_a?(String) != false || raise("Passed value for field obj.speaker is not the expected type, validation failed.")
|
109
89
|
end
|
110
90
|
end
|
111
91
|
end
|
@@ -7,16 +7,19 @@ require "json"
|
|
7
7
|
module AssemblyAI
|
8
8
|
class Transcripts
|
9
9
|
class TranscriptSentence
|
10
|
-
# @return [String]
|
10
|
+
# @return [String] The transcript of the sentence
|
11
11
|
attr_reader :text
|
12
|
-
# @return [Integer]
|
12
|
+
# @return [Integer] The starting time, in milliseconds, for the sentence
|
13
13
|
attr_reader :start
|
14
|
-
# @return [Integer]
|
14
|
+
# @return [Integer] The ending time, in milliseconds, for the sentence
|
15
15
|
attr_reader :end_
|
16
|
-
# @return [Float]
|
16
|
+
# @return [Float] The confidence score for the transcript of this sentence
|
17
17
|
attr_reader :confidence
|
18
|
-
# @return [Array<AssemblyAI::Transcripts::TranscriptWord>]
|
18
|
+
# @return [Array<AssemblyAI::Transcripts::TranscriptWord>] An array of words in the sentence
|
19
19
|
attr_reader :words
|
20
|
+
# @return [String] The channel of the sentence. The left and right channels are channels 1 and 2.
|
21
|
+
# Additional channels increment the channel number sequentially.
|
22
|
+
attr_reader :channel
|
20
23
|
# @return [String] The speaker of the sentence if [Speaker
|
21
24
|
# Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is
|
22
25
|
# enabled, else null
|
@@ -29,22 +32,26 @@ module AssemblyAI
|
|
29
32
|
|
30
33
|
OMIT = Object.new
|
31
34
|
|
32
|
-
# @param text [String]
|
33
|
-
# @param start [Integer]
|
34
|
-
# @param end_ [Integer]
|
35
|
-
# @param confidence [Float]
|
36
|
-
# @param words [Array<AssemblyAI::Transcripts::TranscriptWord>]
|
35
|
+
# @param text [String] The transcript of the sentence
|
36
|
+
# @param start [Integer] The starting time, in milliseconds, for the sentence
|
37
|
+
# @param end_ [Integer] The ending time, in milliseconds, for the sentence
|
38
|
+
# @param confidence [Float] The confidence score for the transcript of this sentence
|
39
|
+
# @param words [Array<AssemblyAI::Transcripts::TranscriptWord>] An array of words in the sentence
|
40
|
+
# @param channel [String] The channel of the sentence. The left and right channels are channels 1 and 2.
|
41
|
+
# Additional channels increment the channel number sequentially.
|
37
42
|
# @param speaker [String] The speaker of the sentence if [Speaker
|
38
43
|
# Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is
|
39
44
|
# enabled, else null
|
40
45
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
41
46
|
# @return [AssemblyAI::Transcripts::TranscriptSentence]
|
42
|
-
def initialize(text:, start:, end_:, confidence:, words:,
|
47
|
+
def initialize(text:, start:, end_:, confidence:, words:, channel: OMIT, speaker: OMIT,
|
48
|
+
additional_properties: nil)
|
43
49
|
@text = text
|
44
50
|
@start = start
|
45
51
|
@end_ = end_
|
46
52
|
@confidence = confidence
|
47
53
|
@words = words
|
54
|
+
@channel = channel if channel != OMIT
|
48
55
|
@speaker = speaker if speaker != OMIT
|
49
56
|
@additional_properties = additional_properties
|
50
57
|
@_field_set = {
|
@@ -53,6 +60,7 @@ module AssemblyAI
|
|
53
60
|
"end": end_,
|
54
61
|
"confidence": confidence,
|
55
62
|
"words": words,
|
63
|
+
"channel": channel,
|
56
64
|
"speaker": speaker
|
57
65
|
}.reject do |_k, v|
|
58
66
|
v == OMIT
|
@@ -74,6 +82,7 @@ module AssemblyAI
|
|
74
82
|
v = v.to_json
|
75
83
|
AssemblyAI::Transcripts::TranscriptWord.from_json(json_object: v)
|
76
84
|
end
|
85
|
+
channel = struct["channel"]
|
77
86
|
speaker = struct["speaker"]
|
78
87
|
new(
|
79
88
|
text: text,
|
@@ -81,6 +90,7 @@ module AssemblyAI
|
|
81
90
|
end_: end_,
|
82
91
|
confidence: confidence,
|
83
92
|
words: words,
|
93
|
+
channel: channel,
|
84
94
|
speaker: speaker,
|
85
95
|
additional_properties: struct
|
86
96
|
)
|
@@ -105,6 +115,7 @@ module AssemblyAI
|
|
105
115
|
obj.end_.is_a?(Integer) != false || raise("Passed value for field obj.end_ is not the expected type, validation failed.")
|
106
116
|
obj.confidence.is_a?(Float) != false || raise("Passed value for field obj.confidence is not the expected type, validation failed.")
|
107
117
|
obj.words.is_a?(Array) != false || raise("Passed value for field obj.words is not the expected type, validation failed.")
|
118
|
+
obj.channel&.is_a?(String) != false || raise("Passed value for field obj.channel is not the expected type, validation failed.")
|
108
119
|
obj.speaker&.is_a?(String) != false || raise("Passed value for field obj.speaker is not the expected type, validation failed.")
|
109
120
|
end
|
110
121
|
end
|
@@ -17,6 +17,9 @@ module AssemblyAI
|
|
17
17
|
attr_reader :text
|
18
18
|
# @return [Array<AssemblyAI::Transcripts::TranscriptWord>] The words in the utterance.
|
19
19
|
attr_reader :words
|
20
|
+
# @return [String] The channel of this utterance. The left and right channels are channels 1 and 2.
|
21
|
+
# Additional channels increment the channel number sequentially.
|
22
|
+
attr_reader :channel
|
20
23
|
# @return [String] The speaker of this utterance, where each speaker is assigned a sequential
|
21
24
|
# capital letter - e.g. "A" for Speaker A, "B" for Speaker B, etc.
|
22
25
|
attr_reader :speaker
|
@@ -33,16 +36,19 @@ module AssemblyAI
|
|
33
36
|
# @param end_ [Integer] The ending time, in milliseconds, of the utterance in the audio file
|
34
37
|
# @param text [String] The text for this utterance
|
35
38
|
# @param words [Array<AssemblyAI::Transcripts::TranscriptWord>] The words in the utterance.
|
39
|
+
# @param channel [String] The channel of this utterance. The left and right channels are channels 1 and 2.
|
40
|
+
# Additional channels increment the channel number sequentially.
|
36
41
|
# @param speaker [String] The speaker of this utterance, where each speaker is assigned a sequential
|
37
42
|
# capital letter - e.g. "A" for Speaker A, "B" for Speaker B, etc.
|
38
43
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
39
44
|
# @return [AssemblyAI::Transcripts::TranscriptUtterance]
|
40
|
-
def initialize(confidence:, start:, end_:, text:, words:, speaker:, additional_properties: nil)
|
45
|
+
def initialize(confidence:, start:, end_:, text:, words:, speaker:, channel: OMIT, additional_properties: nil)
|
41
46
|
@confidence = confidence
|
42
47
|
@start = start
|
43
48
|
@end_ = end_
|
44
49
|
@text = text
|
45
50
|
@words = words
|
51
|
+
@channel = channel if channel != OMIT
|
46
52
|
@speaker = speaker
|
47
53
|
@additional_properties = additional_properties
|
48
54
|
@_field_set = {
|
@@ -51,8 +57,11 @@ module AssemblyAI
|
|
51
57
|
"end": end_,
|
52
58
|
"text": text,
|
53
59
|
"words": words,
|
60
|
+
"channel": channel,
|
54
61
|
"speaker": speaker
|
55
|
-
}
|
62
|
+
}.reject do |_k, v|
|
63
|
+
v == OMIT
|
64
|
+
end
|
56
65
|
end
|
57
66
|
|
58
67
|
# Deserialize a JSON object to an instance of TranscriptUtterance
|
@@ -70,6 +79,7 @@ module AssemblyAI
|
|
70
79
|
v = v.to_json
|
71
80
|
AssemblyAI::Transcripts::TranscriptWord.from_json(json_object: v)
|
72
81
|
end
|
82
|
+
channel = struct["channel"]
|
73
83
|
speaker = struct["speaker"]
|
74
84
|
new(
|
75
85
|
confidence: confidence,
|
@@ -77,6 +87,7 @@ module AssemblyAI
|
|
77
87
|
end_: end_,
|
78
88
|
text: text,
|
79
89
|
words: words,
|
90
|
+
channel: channel,
|
80
91
|
speaker: speaker,
|
81
92
|
additional_properties: struct
|
82
93
|
)
|
@@ -101,6 +112,7 @@ module AssemblyAI
|
|
101
112
|
obj.end_.is_a?(Integer) != false || raise("Passed value for field obj.end_ is not the expected type, validation failed.")
|
102
113
|
obj.text.is_a?(String) != false || raise("Passed value for field obj.text is not the expected type, validation failed.")
|
103
114
|
obj.words.is_a?(Array) != false || raise("Passed value for field obj.words is not the expected type, validation failed.")
|
115
|
+
obj.channel&.is_a?(String) != false || raise("Passed value for field obj.channel is not the expected type, validation failed.")
|
104
116
|
obj.speaker.is_a?(String) != false || raise("Passed value for field obj.speaker is not the expected type, validation failed.")
|
105
117
|
end
|
106
118
|
end
|
@@ -6,15 +6,18 @@ require "json"
|
|
6
6
|
module AssemblyAI
|
7
7
|
class Transcripts
|
8
8
|
class TranscriptWord
|
9
|
-
# @return [Float]
|
9
|
+
# @return [Float] The confidence score for the transcript of this word
|
10
10
|
attr_reader :confidence
|
11
|
-
# @return [Integer]
|
11
|
+
# @return [Integer] The starting time, in milliseconds, for the word
|
12
12
|
attr_reader :start
|
13
|
-
# @return [Integer]
|
13
|
+
# @return [Integer] The ending time, in milliseconds, for the word
|
14
14
|
attr_reader :end_
|
15
|
-
# @return [String]
|
15
|
+
# @return [String] The text of the word
|
16
16
|
attr_reader :text
|
17
|
-
# @return [String] The
|
17
|
+
# @return [String] The channel of the word. The left and right channels are channels 1 and 2.
|
18
|
+
# Additional channels increment the channel number sequentially.
|
19
|
+
attr_reader :channel
|
20
|
+
# @return [String] The speaker of the word if [Speaker
|
18
21
|
# Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is
|
19
22
|
# enabled, else null
|
20
23
|
attr_reader :speaker
|
@@ -26,20 +29,23 @@ module AssemblyAI
|
|
26
29
|
|
27
30
|
OMIT = Object.new
|
28
31
|
|
29
|
-
# @param confidence [Float]
|
30
|
-
# @param start [Integer]
|
31
|
-
# @param end_ [Integer]
|
32
|
-
# @param text [String]
|
33
|
-
# @param
|
32
|
+
# @param confidence [Float] The confidence score for the transcript of this word
|
33
|
+
# @param start [Integer] The starting time, in milliseconds, for the word
|
34
|
+
# @param end_ [Integer] The ending time, in milliseconds, for the word
|
35
|
+
# @param text [String] The text of the word
|
36
|
+
# @param channel [String] The channel of the word. The left and right channels are channels 1 and 2.
|
37
|
+
# Additional channels increment the channel number sequentially.
|
38
|
+
# @param speaker [String] The speaker of the word if [Speaker
|
34
39
|
# Diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is
|
35
40
|
# enabled, else null
|
36
41
|
# @param additional_properties [OpenStruct] Additional properties unmapped to the current class definition
|
37
42
|
# @return [AssemblyAI::Transcripts::TranscriptWord]
|
38
|
-
def initialize(confidence:, start:, end_:, text:, speaker: OMIT, additional_properties: nil)
|
43
|
+
def initialize(confidence:, start:, end_:, text:, channel: OMIT, speaker: OMIT, additional_properties: nil)
|
39
44
|
@confidence = confidence
|
40
45
|
@start = start
|
41
46
|
@end_ = end_
|
42
47
|
@text = text
|
48
|
+
@channel = channel if channel != OMIT
|
43
49
|
@speaker = speaker if speaker != OMIT
|
44
50
|
@additional_properties = additional_properties
|
45
51
|
@_field_set = {
|
@@ -47,6 +53,7 @@ module AssemblyAI
|
|
47
53
|
"start": start,
|
48
54
|
"end": end_,
|
49
55
|
"text": text,
|
56
|
+
"channel": channel,
|
50
57
|
"speaker": speaker
|
51
58
|
}.reject do |_k, v|
|
52
59
|
v == OMIT
|
@@ -63,12 +70,14 @@ module AssemblyAI
|
|
63
70
|
start = struct["start"]
|
64
71
|
end_ = struct["end"]
|
65
72
|
text = struct["text"]
|
73
|
+
channel = struct["channel"]
|
66
74
|
speaker = struct["speaker"]
|
67
75
|
new(
|
68
76
|
confidence: confidence,
|
69
77
|
start: start,
|
70
78
|
end_: end_,
|
71
79
|
text: text,
|
80
|
+
channel: channel,
|
72
81
|
speaker: speaker,
|
73
82
|
additional_properties: struct
|
74
83
|
)
|
@@ -92,6 +101,7 @@ module AssemblyAI
|
|
92
101
|
obj.start.is_a?(Integer) != false || raise("Passed value for field obj.start is not the expected type, validation failed.")
|
93
102
|
obj.end_.is_a?(Integer) != false || raise("Passed value for field obj.end_ is not the expected type, validation failed.")
|
94
103
|
obj.text.is_a?(String) != false || raise("Passed value for field obj.text is not the expected type, validation failed.")
|
104
|
+
obj.channel&.is_a?(String) != false || raise("Passed value for field obj.channel is not the expected type, validation failed.")
|
95
105
|
obj.speaker&.is_a?(String) != false || raise("Passed value for field obj.speaker is not the expected type, validation failed.")
|
96
106
|
end
|
97
107
|
end
|
data/lib/gemconfig.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: assemblyai
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- AssemblyAI
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-
|
11
|
+
date: 2024-11-06 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: async-http-faraday
|