Skip to content

Commit 6160e80

Browse files
author
AWS
committed
Amazon Transcribe Streaming Service Update: This release adds language identification support for streaming transcription.
1 parent 5baa4e5 commit 6160e80

File tree

2 files changed

+89
-15
lines changed

2 files changed

+89
-15
lines changed

‎.changes/next-release/feature-AmazonTranscribeStreamingService-e728c28.json

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
{
2+
"type": "feature",
3+
"category": "Amazon Transcribe Streaming Service",
4+
"contributor": "",
5+
"description": "This release adds language identification support for streaming transcription."
6+
}

‎services/transcribestreaming/src/main/resources/codegen-resources/service-2.json

Lines changed: 83 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -136,7 +136,7 @@
136136
},
137137
"Category":{
138138
"shape":"String",
139-
"documentation":"<p>The category of of information identified in this entity; for example, PII.</p>"
139+
"documentation":"<p>The category of information identified in this entity; for example, PII.</p>"
140140
},
141141
"Type":{
142142
"shape":"String",
@@ -188,15 +188,15 @@
188188
},
189189
"VocabularyFilterMatch":{
190190
"shape":"Boolean",
191-
"documentation":"<p>Indicates whether a word in the item matches a word in the vocabulary filter you've chosen for your real-time stream. If <code>true</code> then a word in the item matches your vocabulary filter.</p>"
191+
"documentation":"<p>Indicates whether a word in the item matches a word in the vocabulary filter you've chosen for your media stream. If <code>true</code> then a word in the item matches your vocabulary filter.</p>"
192192
},
193193
"Speaker":{
194194
"shape":"String",
195-
"documentation":"<p>If speaker identification is enabled, shows the speakers identified in the real-time stream.</p>"
195+
"documentation":"<p>If speaker identification is enabled, shows the speakers identified in the media stream.</p>"
196196
},
197197
"Confidence":{
198198
"shape":"Confidence",
199-
"documentation":"<p>A value between 0 and 1 for an item that is a confidence score that Amazon Transcribe assigns to each word or phrase that it transcribes.</p>"
199+
"documentation":"<p>A value between zero and one for an item that is a confidence score that Amazon Transcribe assigns to each word or phrase that it transcribes.</p>"
200200
},
201201
"Stable":{
202202
"shape":"Stable",
@@ -233,6 +233,30 @@
233233
"zh-CN"
234234
]
235235
},
236+
"LanguageIdentification":{
237+
"type":"list",
238+
"member":{"shape":"LanguageWithScore"}
239+
},
240+
"LanguageOptions":{
241+
"type":"string",
242+
"max":200,
243+
"min":1,
244+
"pattern":"^[a-zA-Z-,]+"
245+
},
246+
"LanguageWithScore":{
247+
"type":"structure",
248+
"members":{
249+
"LanguageCode":{
250+
"shape":"LanguageCode",
251+
"documentation":"<p>The language code of the language identified by Amazon Transcribe.</p>"
252+
},
253+
"Score":{
254+
"shape":"Double",
255+
"documentation":"<p>The confidence score for the associated language code. Confidence scores are values between zero and one; larger values indicate a higher confidence in the identified language. </p>"
256+
}
257+
},
258+
"documentation":"<p>The language codes of the identified languages and their associated confidence scores. The confidence score is a value between zero and one; a larger value indicates a higher confidence in the identified language.</p>"
259+
},
236260
"LimitExceededException":{
237261
"type":"structure",
238262
"members":{
@@ -467,6 +491,14 @@
467491
"ChannelId":{
468492
"shape":"String",
469493
"documentation":"<p>When channel identification is enabled, Amazon Transcribe transcribes the speech from each audio channel separately.</p> <p>You can use <code>ChannelId</code> to retrieve the transcription results for a single channel in your audio stream.</p>"
494+
},
495+
"LanguageCode":{
496+
"shape":"LanguageCode",
497+
"documentation":"<p>The language code of the identified language in your media stream.</p>"
498+
},
499+
"LanguageIdentification":{
500+
"shape":"LanguageIdentification",
501+
"documentation":"<p>The language code of the dominant language identified in your media.</p>"
470502
}
471503
},
472504
"documentation":"<p>The result of transcribing a portion of the input audio stream. </p>"
@@ -668,21 +700,20 @@
668700
"StartStreamTranscriptionRequest":{
669701
"type":"structure",
670702
"required":[
671-
"LanguageCode",
672703
"MediaSampleRateHertz",
673704
"MediaEncoding",
674705
"AudioStream"
675706
],
676707
"members":{
677708
"LanguageCode":{
678709
"shape":"LanguageCode",
679-
"documentation":"<p>Indicates the source language used in the input audio stream.</p>",
710+
"documentation":"<p>The language code of the input audio stream.</p>",
680711
"location":"header",
681712
"locationName":"x-amzn-transcribe-language-code"
682713
},
683714
"MediaSampleRateHertz":{
684715
"shape":"MediaSampleRateHertz",
685-
"documentation":"<p>The sample rate, in Hertz, of the input audio. We suggest that you use 8,000 Hz for low quality audio and 16,000 Hz for high quality audio.</p>",
716+
"documentation":"<p>The sample rate, in Hertz (Hz), of the input audio. We suggest that you use 8,000 Hz for low quality audio and 16,000 Hz or higher for high quality audio.</p>",
686717
"location":"header",
687718
"locationName":"x-amzn-transcribe-sample-rate"
688719
},
@@ -716,19 +747,19 @@
716747
},
717748
"VocabularyFilterMethod":{
718749
"shape":"VocabularyFilterMethod",
719-
"documentation":"<p>The manner in which you use your vocabulary filter to filter words in your transcript. <code>Remove</code> removes filtered words from your transcription results. <code>Mask</code> masks filtered words with a <code>***</code> in your transcription results. <code>Tag</code> keeps the filtered words in your transcription results and tags them. The tag appears as <code>VocabularyFilterMatch</code> equal to <code>True</code> </p>",
750+
"documentation":"<p>The manner in which you use your vocabulary filter to filter words in your transcript. <code>Remove</code> removes filtered words from your transcription results. <code>Mask</code> masks filtered words with a <code>***</code> in your transcription results. <code>Tag</code> keeps the filtered words in your transcription results and tags them. The tag appears as <code>VocabularyFilterMatch</code> equal to <code>True</code>.</p>",
720751
"location":"header",
721752
"locationName":"x-amzn-transcribe-vocabulary-filter-method"
722753
},
723754
"ShowSpeakerLabel":{
724755
"shape":"Boolean",
725-
"documentation":"<p>When <code>true</code>, enables speaker identification in your real-time stream.</p>",
756+
"documentation":"<p>When <code>true</code>, enables speaker identification in your media stream.</p>",
726757
"location":"header",
727758
"locationName":"x-amzn-transcribe-show-speaker-label"
728759
},
729760
"EnableChannelIdentification":{
730761
"shape":"Boolean",
731-
"documentation":"<p>When <code>true</code>, instructs Amazon Transcribe to process each audio channel separately and then merge the transcription output of each channel into a single transcription.</p> <p>Amazon Transcribe also produces a transcription of each item. An item includes the start time, end time, and any alternative transcriptions.</p> <p>You can't set both <code>ShowSpeakerLabel</code> and <code>EnableChannelIdentification</code> in the same request. If you set both, your request returns a <code>BadRequestException</code>.</p>",
762+
"documentation":"<p>When <code>true</code>, instructs Amazon Transcribe to process each audio channel separately, then merges the transcription output of each channel into a single transcription.</p> <p>Amazon Transcribe also produces a transcription of each item. An item includes the start time, end time, and any alternative transcriptions.</p> <p>You can't set both <code>ShowSpeakerLabel</code> and <code>EnableChannelIdentification</code> in the same request. If you set both, your request returns a <code>BadRequestException</code>.</p>",
732763
"location":"header",
733764
"locationName":"x-amzn-transcribe-enable-channel-identification"
734765
},
@@ -764,7 +795,7 @@
764795
},
765796
"PiiEntityTypes":{
766797
"shape":"PiiEntityTypes",
767-
"documentation":"<p>List the PII entity types you want to identify or redact. In order to specify entity types, you must have either <code>ContentIdentificationType</code> or <code>ContentRedactionType</code> enabled.</p> <p> <code>PiiEntityTypes</code> is an optional parameter with a default value of <code>ALL</code>.</p>",
798+
"documentation":"<p>List the PII entity types you want to identify or redact. In order to specify entity types, you must have either <code>ContentIdentificationType</code> or <code>ContentRedactionType</code> enabled.</p> <p> <code>PIIEntityTypes</code> must be comma-separated; the available values are: <code>BANK_ACCOUNT_NUMBER</code>, <code>BANK_ROUTING</code>, <code>CREDIT_DEBIT_NUMBER</code>, <code>CREDIT_DEBIT_CVV</code>, <code>CREDIT_DEBIT_EXPIRY</code>, <code>PIN</code>, <code>EMAIL</code>, <code>ADDRESS</code>, <code>NAME</code>, <code>PHONE</code>, <code>SSN</code>, and <code>ALL</code>.</p> <p> <code>PiiEntityTypes</code> is an optional parameter with a default value of <code>ALL</code>.</p>",
768799
"location":"header",
769800
"locationName":"x-amzn-transcribe-pii-entity-types"
770801
},
@@ -773,6 +804,24 @@
773804
"documentation":"<p>The name of the language model you want to use.</p>",
774805
"location":"header",
775806
"locationName":"x-amzn-transcribe-language-model-name"
807+
},
808+
"IdentifyLanguage":{
809+
"shape":"Boolean",
810+
"documentation":"<p>Optional. Set this value to <code>true</code> to enable language identification for your media stream.</p>",
811+
"location":"header",
812+
"locationName":"x-amzn-transcribe-identify-language"
813+
},
814+
"LanguageOptions":{
815+
"shape":"LanguageOptions",
816+
"documentation":"<p>An object containing a list of languages that might be present in your audio.</p> <p>You must provide two or more language codes to help Amazon Transcribe identify the correct language of your media stream with the highest possible accuracy. You can only select one variant per language; for example, you can't include both <code>en-US</code> and <code>en-UK</code> in the same request.</p> <p>You can only use this parameter if you've set <code>IdentifyLanguage</code> to <code>true</code>in your request.</p>",
817+
"location":"header",
818+
"locationName":"x-amzn-transcribe-language-options"
819+
},
820+
"PreferredLanguage":{
821+
"shape":"LanguageCode",
822+
"documentation":"<p>Optional. From the subset of languages codes you provided for <code>LanguageOptions</code>, you can select one preferred language for your transcription.</p> <p>You can only use this parameter if you've set <code>IdentifyLanguage</code> to <code>true</code>in your request.</p>",
823+
"location":"header",
824+
"locationName":"x-amzn-transcribe-preferred-language"
776825
}
777826
},
778827
"payload":"AudioStream"
@@ -788,13 +837,13 @@
788837
},
789838
"LanguageCode":{
790839
"shape":"LanguageCode",
791-
"documentation":"<p>The language code for the input audio stream.</p>",
840+
"documentation":"<p>The language code of the input audio stream.</p>",
792841
"location":"header",
793842
"locationName":"x-amzn-transcribe-language-code"
794843
},
795844
"MediaSampleRateHertz":{
796845
"shape":"MediaSampleRateHertz",
797-
"documentation":"<p>The sample rate for the input audio stream. Use 8,000 Hz for low quality audio and 16,000 Hz for high quality audio.</p>",
846+
"documentation":"<p>The sample rate, in Hertz (Hz), for the input audio stream. Use 8,000 Hz for low quality audio and 16,000 Hz or higher for high quality audio.</p>",
798847
"location":"header",
799848
"locationName":"x-amzn-transcribe-sample-rate"
800849
},
@@ -822,13 +871,13 @@
822871
},
823872
"VocabularyFilterName":{
824873
"shape":"VocabularyFilterName",
825-
"documentation":"<p>The name of the vocabulary filter used in your real-time stream.</p>",
874+
"documentation":"<p>The name of the vocabulary filter used in your media stream.</p>",
826875
"location":"header",
827876
"locationName":"x-amzn-transcribe-vocabulary-filter-name"
828877
},
829878
"VocabularyFilterMethod":{
830879
"shape":"VocabularyFilterMethod",
831-
"documentation":"<p>The vocabulary filtering method used in the real-time stream.</p>",
880+
"documentation":"<p>The vocabulary filtering method used in the media stream.</p>",
832881
"location":"header",
833882
"locationName":"x-amzn-transcribe-vocabulary-filter-method"
834883
},
@@ -882,8 +931,27 @@
882931
},
883932
"LanguageModelName":{
884933
"shape":"ModelName",
934+
"documentation":"<p>The name of the language model used in your media stream.</p>",
885935
"location":"header",
886936
"locationName":"x-amzn-transcribe-language-model-name"
937+
},
938+
"IdentifyLanguage":{
939+
"shape":"Boolean",
940+
"documentation":"<p>The language code of the language identified in your media stream.</p>",
941+
"location":"header",
942+
"locationName":"x-amzn-transcribe-identify-language"
943+
},
944+
"LanguageOptions":{
945+
"shape":"LanguageOptions",
946+
"documentation":"<p>The language codes used in the identification of your media stream's predominant language.</p>",
947+
"location":"header",
948+
"locationName":"x-amzn-transcribe-language-options"
949+
},
950+
"PreferredLanguage":{
951+
"shape":"LanguageCode",
952+
"documentation":"<p>The preferred language you specified in your request.</p>",
953+
"location":"header",
954+
"locationName":"x-amzn-transcribe-preferred-language"
887955
}
888956
},
889957
"payload":"TranscriptResultStream"

0 commit comments

Comments
 (0)