1// Code generated by smithy-go-codegen DO NOT EDIT. 2 3package types 4 5import ( 6 "time" 7) 8 9// Settings for content redaction within a transcription job. 10type ContentRedaction struct { 11 12 // The output transcript file stored in either the default S3 bucket or in a bucket 13 // you specify. When you choose redacted Amazon Transcribe outputs only the 14 // redacted transcript. When you choose redacted_and_unredacted Amazon Transcribe 15 // outputs both the redacted and unredacted transcripts. 16 // 17 // This member is required. 18 RedactionOutput RedactionOutput 19 20 // Request parameter that defines the entities to be redacted. The only accepted 21 // value is PII. 22 // 23 // This member is required. 24 RedactionType RedactionType 25} 26 27// The object that contains the Amazon S3 object location and access role required 28// to train and tune your custom language model. 29type InputDataConfig struct { 30 31 // The Amazon Resource Name (ARN) that uniquely identifies the permissions you've 32 // given Amazon Transcribe to access your Amazon S3 buckets containing your media 33 // files or text data. 34 // 35 // This member is required. 36 DataAccessRoleArn *string 37 38 // The Amazon S3 prefix you specify to access the plain text files that you use to 39 // train your custom language model. 40 // 41 // This member is required. 42 S3Uri *string 43 44 // The Amazon S3 prefix you specify to access the plain text files that you use to 45 // tune your custom language model. 46 TuningDataS3Uri *string 47} 48 49// Provides information about when a transcription job should be executed. 50type JobExecutionSettings struct { 51 52 // Indicates whether a job should be queued by Amazon Transcribe when the 53 // concurrent execution limit is exceeded. When the AllowDeferredExecution field is 54 // true, jobs are queued and executed when the number of executing jobs falls below 55 // the concurrent execution limit. If the field is false, Amazon Transcribe returns 56 // a LimitExceededException exception. If you specify the AllowDeferredExecution 57 // field, you must specify the DataAccessRoleArn field. 58 AllowDeferredExecution *bool 59 60 // The Amazon Resource Name (ARN) of a role that has access to the S3 bucket that 61 // contains the input files. Amazon Transcribe assumes this role to read queued 62 // media files. If you have specified an output S3 bucket for the transcription 63 // results, this role should have access to the output bucket as well. If you 64 // specify the AllowDeferredExecution field, you must specify the DataAccessRoleArn 65 // field. 66 DataAccessRoleArn *string 67} 68 69// The structure used to describe a custom language model. 70type LanguageModel struct { 71 72 // The Amazon Transcribe standard language model, or base model used to create the 73 // custom language model. 74 BaseModelName BaseModelName 75 76 // The time the custom language model was created. 77 CreateTime *time.Time 78 79 // The reason why the custom language model couldn't be created. 80 FailureReason *string 81 82 // The data access role and Amazon S3 prefixes for the input files used to train 83 // the custom language model. 84 InputDataConfig *InputDataConfig 85 86 // The language code you used to create your custom language model. 87 LanguageCode CLMLanguageCode 88 89 // The most recent time the custom language model was modified. 90 LastModifiedTime *time.Time 91 92 // The name of the custom language model. 93 ModelName *string 94 95 // The creation status of a custom language model. When the status is COMPLETED the 96 // model is ready for use. 97 ModelStatus ModelStatus 98 99 // Whether the base model used for the custom language model is up to date. If this 100 // field is true then you are running the most up-to-date version of the base model 101 // in your custom language model. 102 UpgradeAvailability *bool 103} 104 105// Describes the input media file in a transcription request. 106type Media struct { 107 108 // The S3 object location of the input media file. The URI must be in the same 109 // region as the API endpoint that you are calling. The general form is: For 110 // example: For more information about S3 object names, see Object Keys 111 // (http://docs.aws.amazon.com/AmazonS3/latest/dev/UsingMetadata.html#object-keys) 112 // in the Amazon S3 Developer Guide. 113 MediaFileUri *string 114} 115 116// Identifies the location of a medical transcript. 117type MedicalTranscript struct { 118 119 // The S3 object location of the medical transcript. Use this URI to access the 120 // medical transcript. This URI points to the S3 bucket you created to store the 121 // medical transcript. 122 TranscriptFileUri *string 123} 124 125// The data structure that contains the information for a medical transcription 126// job. 127type MedicalTranscriptionJob struct { 128 129 // A timestamp that shows when the job was completed. 130 CompletionTime *time.Time 131 132 // A timestamp that shows when the job was created. 133 CreationTime *time.Time 134 135 // If the TranscriptionJobStatus field is FAILED, this field contains information 136 // about why the job failed. The FailureReason field contains one of the following 137 // values: 138 // 139 // * Unsupported media format- The media format specified in the 140 // MediaFormat field of the request isn't valid. See the description of the 141 // MediaFormat field for a list of valid values. 142 // 143 // * The media format provided does 144 // not match the detected media format- The media format of the audio file doesn't 145 // match the format specified in the MediaFormat field in the request. Check the 146 // media format of your media file and make sure the two values match. 147 // 148 // * Invalid 149 // sample rate for audio file- The sample rate specified in the 150 // MediaSampleRateHertz of the request isn't valid. The sample rate must be between 151 // 8000 and 48000 Hertz. 152 // 153 // * The sample rate provided does not match the detected 154 // sample rate- The sample rate in the audio file doesn't match the sample rate 155 // specified in the MediaSampleRateHertz field in the request. Check the sample 156 // rate of your media file and make sure that the two values match. 157 // 158 // * Invalid file 159 // size: file size too large- The size of your audio file is larger than what 160 // Amazon Transcribe Medical can process. For more information, see Guidelines and 161 // Quotas 162 // (https://docs.aws.amazon.com/transcribe/latest/dg/limits-guidelines.html#limits) 163 // in the Amazon Transcribe Medical Guide 164 // 165 // * Invalid number of channels: number of 166 // channels too large- Your audio contains more channels than Amazon Transcribe 167 // Medical is configured to process. To request additional channels, see Amazon 168 // Transcribe Medical Endpoints and Quotas 169 // (https://docs.aws.amazon.com/general/latest/gr/transcribe-medical.html) in the 170 // Amazon Web Services General Reference 171 FailureReason *string 172 173 // The language code for the language spoken in the source audio file. US English 174 // (en-US) is the only supported language for medical transcriptions. Any other 175 // value you enter for language code results in a BadRequestException error. 176 LanguageCode LanguageCode 177 178 // Describes the input media file in a transcription request. 179 Media *Media 180 181 // The format of the input media file. 182 MediaFormat MediaFormat 183 184 // The sample rate, in Hertz, of the source audio containing medical information. 185 // If you don't specify the sample rate, Amazon Transcribe Medical determines it 186 // for you. If you choose to specify the sample rate, it must match the rate 187 // detected by Amazon Transcribe Medical. In most cases, you should leave the 188 // MediaSampleHertz blank and let Amazon Transcribe Medical determine the sample 189 // rate. 190 MediaSampleRateHertz *int32 191 192 // The name for a given medical transcription job. 193 MedicalTranscriptionJobName *string 194 195 // Object that contains object. 196 Settings *MedicalTranscriptionSetting 197 198 // The medical specialty of any clinicians providing a dictation or having a 199 // conversation. PRIMARYCARE is the only available setting for this object. This 200 // specialty enables you to generate transcriptions for the following medical 201 // fields: 202 // 203 // * Family Medicine 204 Specialty Specialty 205 206 // A timestamp that shows when the job started processing. 207 StartTime *time.Time 208 209 // An object that contains the MedicalTranscript. The MedicalTranscript contains 210 // the TranscriptFileUri. 211 Transcript *MedicalTranscript 212 213 // The completion status of a medical transcription job. 214 TranscriptionJobStatus TranscriptionJobStatus 215 216 // The type of speech in the transcription job. CONVERSATION is generally used for 217 // patient-physician dialogues. DICTATION is the setting for physicians speaking 218 // their notes after seeing a patient. For more information, see how-it-works-med 219 Type Type 220} 221 222// Provides summary information about a transcription job. 223type MedicalTranscriptionJobSummary struct { 224 225 // A timestamp that shows when the job was completed. 226 CompletionTime *time.Time 227 228 // A timestamp that shows when the medical transcription job was created. 229 CreationTime *time.Time 230 231 // If the TranscriptionJobStatus field is FAILED, a description of the error. 232 FailureReason *string 233 234 // The language of the transcript in the source audio file. 235 LanguageCode LanguageCode 236 237 // The name of a medical transcription job. 238 MedicalTranscriptionJobName *string 239 240 // Indicates the location of the transcription job's output. The CUSTOMER_BUCKET is 241 // the S3 location provided in the OutputBucketName field when the 242 OutputLocationType OutputLocationType 243 244 // The medical specialty of the transcription job. Primary care is the only valid 245 // value. 246 Specialty Specialty 247 248 // A timestamp that shows when the job began processing. 249 StartTime *time.Time 250 251 // The status of the medical transcription job. 252 TranscriptionJobStatus TranscriptionJobStatus 253 254 // The speech of the clinician in the input audio. 255 Type Type 256} 257 258// Optional settings for the StartMedicalTranscriptionJob operation. 259type MedicalTranscriptionSetting struct { 260 261 // Instructs Amazon Transcribe Medical to process each audio channel separately and 262 // then merge the transcription output of each channel into a single transcription. 263 // Amazon Transcribe Medical also produces a transcription of each item detected on 264 // an audio channel, including the start time and end time of the item and 265 // alternative transcriptions of item. The alternative transcriptions also come 266 // with confidence scores provided by Amazon Transcribe Medical. You can't set both 267 // ShowSpeakerLabels and ChannelIdentification in the same request. If you set 268 // both, your request returns a BadRequestException 269 ChannelIdentification *bool 270 271 // The maximum number of alternatives that you tell the service to return. If you 272 // specify the MaxAlternatives field, you must set the ShowAlternatives field to 273 // true. 274 MaxAlternatives *int32 275 276 // The maximum number of speakers to identify in the input audio. If there are more 277 // speakers in the audio than this number, multiple speakers are identified as a 278 // single speaker. If you specify the MaxSpeakerLabels field, you must set the 279 // ShowSpeakerLabels field to true. 280 MaxSpeakerLabels *int32 281 282 // Determines whether alternative transcripts are generated along with the 283 // transcript that has the highest confidence. If you set ShowAlternatives field to 284 // true, you must also set the maximum number of alternatives to return in the 285 // MaxAlternatives field. 286 ShowAlternatives *bool 287 288 // Determines whether the transcription job uses speaker recognition to identify 289 // different speakers in the input audio. Speaker recognition labels individual 290 // speakers in the audio file. If you set the ShowSpeakerLabels field to true, you 291 // must also set the maximum number of speaker labels in the MaxSpeakerLabels 292 // field. You can't set both ShowSpeakerLabels and ChannelIdentification in the 293 // same request. If you set both, your request returns a BadRequestException. 294 ShowSpeakerLabels *bool 295 296 // The name of the vocabulary to use when processing a medical transcription job. 297 VocabularyName *string 298} 299 300// The object used to call your custom language model to your transcription job. 301type ModelSettings struct { 302 303 // The name of your custom language model. 304 LanguageModelName *string 305} 306 307// Provides optional settings for the StartTranscriptionJob operation. 308type Settings struct { 309 310 // Instructs Amazon Transcribe to process each audio channel separately and then 311 // merge the transcription output of each channel into a single transcription. 312 // Amazon Transcribe also produces a transcription of each item detected on an 313 // audio channel, including the start time and end time of the item and alternative 314 // transcriptions of the item including the confidence that Amazon Transcribe has 315 // in the transcription. You can't set both ShowSpeakerLabels and 316 // ChannelIdentification in the same request. If you set both, your request returns 317 // a BadRequestException. 318 ChannelIdentification *bool 319 320 // The number of alternative transcriptions that the service should return. If you 321 // specify the MaxAlternatives field, you must set the ShowAlternatives field to 322 // true. 323 MaxAlternatives *int32 324 325 // The maximum number of speakers to identify in the input audio. If there are more 326 // speakers in the audio than this number, multiple speakers are identified as a 327 // single speaker. If you specify the MaxSpeakerLabels field, you must set the 328 // ShowSpeakerLabels field to true. 329 MaxSpeakerLabels *int32 330 331 // Determines whether the transcription contains alternative transcriptions. If you 332 // set the ShowAlternatives field to true, you must also set the maximum number of 333 // alternatives to return in the MaxAlternatives field. 334 ShowAlternatives *bool 335 336 // Determines whether the transcription job uses speaker recognition to identify 337 // different speakers in the input audio. Speaker recognition labels individual 338 // speakers in the audio file. If you set the ShowSpeakerLabels field to true, you 339 // must also set the maximum number of speaker labels MaxSpeakerLabels field. You 340 // can't set both ShowSpeakerLabels and ChannelIdentification in the same request. 341 // If you set both, your request returns a BadRequestException. 342 ShowSpeakerLabels *bool 343 344 // Set to mask to remove filtered text from the transcript and replace it with 345 // three asterisks ("***") as placeholder text. Set to remove to remove filtered 346 // text from the transcript without using placeholder text. Set to tag to mark the 347 // word in the transcription output that matches the vocabulary filter. When you 348 // set the filter method to tag, the words matching your vocabulary filter are not 349 // masked or removed. 350 VocabularyFilterMethod VocabularyFilterMethod 351 352 // The name of the vocabulary filter to use when transcribing the audio. The filter 353 // that you specify must have the same language code as the transcription job. 354 VocabularyFilterName *string 355 356 // The name of a vocabulary to use when processing the transcription job. 357 VocabularyName *string 358} 359 360// Identifies the location of a transcription. 361type Transcript struct { 362 363 // The S3 object location of the redacted transcript. Use this URI to access the 364 // redacted transcript. If you specified an S3 bucket in the OutputBucketName field 365 // when you created the job, this is the URI of that bucket. If you chose to store 366 // the transcript in Amazon Transcribe, this is a shareable URL that provides 367 // secure access to that location. 368 RedactedTranscriptFileUri *string 369 370 // The S3 object location of the transcript. Use this URI to access the transcript. 371 // If you specified an S3 bucket in the OutputBucketName field when you created the 372 // job, this is the URI of that bucket. If you chose to store the transcript in 373 // Amazon Transcribe, this is a shareable URL that provides secure access to that 374 // location. 375 TranscriptFileUri *string 376} 377 378// Describes an asynchronous transcription job that was created with the 379// StartTranscriptionJob operation. 380type TranscriptionJob struct { 381 382 // A timestamp that shows when the job was completed. 383 CompletionTime *time.Time 384 385 // An object that describes content redaction settings for the transcription job. 386 ContentRedaction *ContentRedaction 387 388 // A timestamp that shows when the job was created. 389 CreationTime *time.Time 390 391 // If the TranscriptionJobStatus field is FAILED, this field contains information 392 // about why the job failed. The FailureReason field can contain one of the 393 // following values: 394 // 395 // * Unsupported media format - The media format specified in 396 // the MediaFormat field of the request isn't valid. See the description of the 397 // MediaFormat field for a list of valid values. 398 // 399 // * The media format provided does 400 // not match the detected media format - The media format of the audio file doesn't 401 // match the format specified in the MediaFormat field in the request. Check the 402 // media format of your media file and make sure that the two values match. 403 // 404 // * 405 // Invalid sample rate for audio file - The sample rate specified in the 406 // MediaSampleRateHertz of the request isn't valid. The sample rate must be between 407 // 8000 and 48000 Hertz. 408 // 409 // * The sample rate provided does not match the detected 410 // sample rate - The sample rate in the audio file doesn't match the sample rate 411 // specified in the MediaSampleRateHertz field in the request. Check the sample 412 // rate of your media file and make sure that the two values match. 413 // 414 // * Invalid file 415 // size: file size too large - The size of your audio file is larger than Amazon 416 // Transcribe can process. For more information, see Limits 417 // (https://docs.aws.amazon.com/transcribe/latest/dg/limits-guidelines.html#limits) 418 // in the Amazon Transcribe Developer Guide. 419 // 420 // * Invalid number of channels: number 421 // of channels too large - Your audio contains more channels than Amazon Transcribe 422 // is configured to process. To request additional channels, see Amazon Transcribe 423 // Limits 424 // (https://docs.aws.amazon.com/general/latest/gr/aws_service_limits.html#limits-amazon-transcribe) 425 // in the Amazon Web Services General Reference. 426 FailureReason *string 427 428 // A value between zero and one that Amazon Transcribe assigned to the language 429 // that it identified in the source audio. Larger values indicate that Amazon 430 // Transcribe has higher confidence in the language it identified. 431 IdentifiedLanguageScore *float32 432 433 // A value that shows if automatic language identification was enabled for a 434 // transcription job. 435 IdentifyLanguage *bool 436 437 // Provides information about how a transcription job is executed. 438 JobExecutionSettings *JobExecutionSettings 439 440 // The language code for the input speech. 441 LanguageCode LanguageCode 442 443 // An object that shows the optional array of languages inputted for transcription 444 // jobs with automatic language identification enabled. 445 LanguageOptions []LanguageCode 446 447 // An object that describes the input media for the transcription job. 448 Media *Media 449 450 // The format of the input media file. 451 MediaFormat MediaFormat 452 453 // The sample rate, in Hertz, of the audio track in the input media file. 454 MediaSampleRateHertz *int32 455 456 // An object containing the details of your custom language model. 457 ModelSettings *ModelSettings 458 459 // Optional settings for the transcription job. Use these settings to turn on 460 // speaker recognition, to set the maximum number of speakers that should be 461 // identified and to specify a custom vocabulary to use when processing the 462 // transcription job. 463 Settings *Settings 464 465 // A timestamp that shows with the job was started processing. 466 StartTime *time.Time 467 468 // An object that describes the output of the transcription job. 469 Transcript *Transcript 470 471 // The name of the transcription job. 472 TranscriptionJobName *string 473 474 // The status of the transcription job. 475 TranscriptionJobStatus TranscriptionJobStatus 476} 477 478// Provides a summary of information about a transcription job. 479type TranscriptionJobSummary struct { 480 481 // A timestamp that shows when the job was completed. 482 CompletionTime *time.Time 483 484 // The content redaction settings of the transcription job. 485 ContentRedaction *ContentRedaction 486 487 // A timestamp that shows when the job was created. 488 CreationTime *time.Time 489 490 // If the TranscriptionJobStatus field is FAILED, a description of the error. 491 FailureReason *string 492 493 // A value between zero and one that Amazon Transcribe assigned to the language it 494 // identified in the source audio. A higher score indicates that Amazon Transcribe 495 // is more confident in the language it identified. 496 IdentifiedLanguageScore *float32 497 498 // Whether automatic language identification was enabled for a transcription job. 499 IdentifyLanguage *bool 500 501 // The language code for the input speech. 502 LanguageCode LanguageCode 503 504 // The object used to call your custom language model to your transcription job. 505 ModelSettings *ModelSettings 506 507 // Indicates the location of the output of the transcription job. If the value is 508 // CUSTOMER_BUCKET then the location is the S3 bucket specified in the 509 // outputBucketName field when the transcription job was started with the 510 // StartTranscriptionJob operation. If the value is SERVICE_BUCKET then the output 511 // is stored by Amazon Transcribe and can be retrieved using the URI in the 512 // GetTranscriptionJob response's TranscriptFileUri field. 513 OutputLocationType OutputLocationType 514 515 // A timestamp that shows when the job started processing. 516 StartTime *time.Time 517 518 // The name of the transcription job. 519 TranscriptionJobName *string 520 521 // The status of the transcription job. When the status is COMPLETED, use the 522 // GetTranscriptionJob operation to get the results of the transcription. 523 TranscriptionJobStatus TranscriptionJobStatus 524} 525 526// Provides information about a vocabulary filter. 527type VocabularyFilterInfo struct { 528 529 // The language code of the words in the vocabulary filter. 530 LanguageCode LanguageCode 531 532 // The date and time that the vocabulary was last updated. 533 LastModifiedTime *time.Time 534 535 // The name of the vocabulary filter. The name must be unique in the account that 536 // holds the filter. 537 VocabularyFilterName *string 538} 539 540// Provides information about a custom vocabulary. 541type VocabularyInfo struct { 542 543 // The language code of the vocabulary entries. 544 LanguageCode LanguageCode 545 546 // The date and time that the vocabulary was last modified. 547 LastModifiedTime *time.Time 548 549 // The name of the vocabulary. 550 VocabularyName *string 551 552 // The processing state of the vocabulary. If the state is READY you can use the 553 // vocabulary in a StartTranscriptionJob request. 554 VocabularyState VocabularyState 555} 556