StartMedicalTranscriptionJob 搭配 a AWS SDK 或 CLI 使用 - AWS SDK 程式碼範例

文件 AWS SDK AWS 範例 SDK 儲存庫中有更多可用的 GitHub 範例。

本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

StartMedicalTranscriptionJob 搭配 a AWS SDK 或 CLI 使用

下列程式碼範例示範如何使用 StartMedicalTranscriptionJob。

.NET
AWS SDK for .NET
注意

還有更多 on GitHub。尋找完整範例，並了解如何在 AWS 程式碼範例儲存庫中設定和執行。


    /// <summary>
    /// Start a medical transcription job for a media file. This method returns
    /// as soon as the job is started.
    /// </summary>
    /// <param name="jobName">A unique name for the medical transcription job.</param>
    /// <param name="mediaFileUri">The URI of the media file, typically an Amazon S3 location.</param>
    /// <param name="mediaFormat">The format of the media file.</param>
    /// <param name="outputBucketName">Location for the output, typically an Amazon S3 location.</param>
    /// <param name="transcriptionType">Conversation or dictation transcription type.</param>
    /// <returns>A MedicalTransactionJob instance with information on the new job.</returns>
    public async Task<MedicalTranscriptionJob> StartMedicalTranscriptionJob(
        string jobName, string mediaFileUri,
        MediaFormat mediaFormat, string outputBucketName, Amazon.TranscribeService.Type transcriptionType)
    {
        var response = await _amazonTranscribeService.StartMedicalTranscriptionJobAsync(
            new StartMedicalTranscriptionJobRequest()
            {
                MedicalTranscriptionJobName = jobName,
                Media = new Media()
                {
                    MediaFileUri = mediaFileUri
                },
                MediaFormat = mediaFormat,
                LanguageCode =
                    LanguageCode
                        .EnUS, // The value must be en-US for medical transcriptions.
                OutputBucketName = outputBucketName,
                OutputKey =
                    jobName, // The value is a key used to fetch the output of the transcription.
                Specialty = Specialty.PRIMARYCARE, // The value PRIMARYCARE must be set.
                Type = transcriptionType
            });
        return response.MedicalTranscriptionJob;
    }
CLI
AWS CLI

範例 1：轉錄儲存為音訊檔案的醫學聽寫

以下 start-medical-transcription-job 範例會轉錄音訊檔案。您可在 OutputBucketName 參數中指定轉錄輸出的位置。

aws transcribe start-medical-transcription-job \
    --cli-input-json file://myfile.json

myfile.json 的內容：

{
    "MedicalTranscriptionJobName": "simple-dictation-medical-transcription-job",
    "LanguageCode": "language-code",
    "Specialty": "PRIMARYCARE",
    "Type": "DICTATION",
    "OutputBucketName":"DOC-EXAMPLE-BUCKET",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
    }
}

輸出：

{
    "MedicalTranscriptionJob": {
        "MedicalTranscriptionJobName": "simple-dictation-medical-transcription-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
        "StartTime": "2020-09-20T00:35:22.256000+00:00",
        "CreationTime": "2020-09-20T00:35:22.218000+00:00",
        "Specialty": "PRIMARYCARE",
        "Type": "DICTATION"
    }
}

如需詳細資訊，請參閱《Amazon Transcribe 開發人員指南》中的批次轉錄概觀。

範例 2：轉錄儲存為音訊檔案的臨床醫師與病患對話

以下 start-medical-transcription-job 範例會轉錄包含臨床醫師與病患對話的音訊檔案。您可以在 OutputBucketName 參數中指定轉錄輸出的位置。

aws transcribe start-medical-transcription-job \
    --cli-input-json file://mysecondfile.json

mysecondfile.json 的內容：

{
    "MedicalTranscriptionJobName": "simple-dictation-medical-transcription-job",
    "LanguageCode": "language-code",
    "Specialty": "PRIMARYCARE",
    "Type": "CONVERSATION",
    "OutputBucketName":"DOC-EXAMPLE-BUCKET",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
    }
}

輸出：

{
    "MedicalTranscriptionJob": {
        "MedicalTranscriptionJobName": "simple-conversation-medical-transcription-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
        "StartTime": "2020-09-20T23:19:49.965000+00:00",
        "CreationTime": "2020-09-20T23:19:49.941000+00:00",
        "Specialty": "PRIMARYCARE",
        "Type": "CONVERSATION"
    }
}

如需詳細資訊，請參閱《Amazon Transcribe 開發人員指南》中的批次轉錄概觀。

範例 3：轉錄臨床醫師與病患對話的多聲道音訊檔案

以下 start-medical-transcription-job 範例會轉錄音訊檔案中每個聲道的音訊，並將每個聲道的個別轉錄合併成單一轉錄輸出。您可在 OutputBucketName 參數中指定轉錄輸出的位置。

aws transcribe start-medical-transcription-job \
    --cli-input-json file://mythirdfile.json

mythirdfile.json 的內容：

{
    "MedicalTranscriptionJobName": "multichannel-conversation-medical-transcription-job",
    "LanguageCode": "language-code",
    "Specialty": "PRIMARYCARE",
    "Type": "CONVERSATION",
    "OutputBucketName":"DOC-EXAMPLE-BUCKET",
        "Media": {
          "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
        "Settings":{
          "ChannelIdentification": true
        }
}

輸出：

{
    "MedicalTranscriptionJob": {
        "MedicalTranscriptionJobName": "multichannel-conversation-medical-transcription-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
        "StartTime": "2020-09-20T23:46:44.081000+00:00",
        "CreationTime": "2020-09-20T23:46:44.053000+00:00",
        "Settings": {
            "ChannelIdentification": true
        },
        "Specialty": "PRIMARYCARE",
        "Type": "CONVERSATION"
    }
}

如需詳細資訊，請參閱《Amazon Transcribe 開發人員指南》中的聲道識別。

範例 4：轉錄臨床醫生與病患對話的音訊檔案，並識別轉錄輸出中的發言者

以下 start-medical-transcription-job 範例會轉錄音訊檔案，並標記轉錄輸出中每一位發言者的語音。您可在 OutputBucketName 參數中指定轉錄輸出的位置。

aws transcribe start-medical-transcription-job \
    --cli-input-json file://myfourthfile.json

myfourthfile.json 的內容：

{
    "MedicalTranscriptionJobName": "speaker-id-conversation-medical-transcription-job",
    "LanguageCode": "language-code",
    "Specialty": "PRIMARYCARE",
    "Type": "CONVERSATION",
    "OutputBucketName":"DOC-EXAMPLE-BUCKET",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
    "Settings":{
        "ShowSpeakerLabels": true,
        "MaxSpeakerLabels": 2
        }
}

輸出：

{
    "MedicalTranscriptionJob": {
        "MedicalTranscriptionJobName": "speaker-id-conversation-medical-transcription-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
        "StartTime": "2020-09-21T18:43:37.265000+00:00",
        "CreationTime": "2020-09-21T18:43:37.157000+00:00",
        "Settings": {
            "ShowSpeakerLabels": true,
            "MaxSpeakerLabels": 2
        },
        "Specialty": "PRIMARYCARE",
        "Type": "CONVERSATION"
    }
}

如需詳細資訊，請參閱《Amazon Transcribe 開發人員指南》中的識別發言者。

範例 5：轉錄儲存為音訊檔案且最多有兩個轉錄替代選項的醫學對話

以下 start-medical-transcription-job 範例會從單一音訊檔案建立最多兩個替代轉錄。每個轉錄都有相關聯的可信度等級。根據預設，Amazon Transcribe 會傳回最高可信度等級的轉錄。您可以指定 Amazon Transcribe 傳回可信度較低的其他轉錄。您可在 OutputBucketName 參數中指定轉錄輸出的位置。

aws transcribe start-medical-transcription-job \
    --cli-input-json file://myfifthfile.json

myfifthfile.json 的內容：

{
    "MedicalTranscriptionJobName": "alternatives-conversation-medical-transcription-job",
    "LanguageCode": "language-code",
    "Specialty": "PRIMARYCARE",
    "Type": "CONVERSATION",
    "OutputBucketName":"DOC-EXAMPLE-BUCKET",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
    },
    "Settings":{
        "ShowAlternatives": true,
        "MaxAlternatives": 2
    }
}

輸出：

{
    "MedicalTranscriptionJob": {
        "MedicalTranscriptionJobName": "alternatives-conversation-medical-transcription-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
        "StartTime": "2020-09-21T19:09:18.199000+00:00",
        "CreationTime": "2020-09-21T19:09:18.171000+00:00",
        "Settings": {
            "ShowAlternatives": true,
            "MaxAlternatives": 2
        },
        "Specialty": "PRIMARYCARE",
        "Type": "CONVERSATION"
    }
}

如需詳細資訊，請參閱《Amazon Transcribe 開發人員指南》中的替代轉錄。

範例 6：轉錄最多有兩個替代轉錄的醫學聽寫的音訊檔案

以下 start-medical-transcription-job 範例會轉錄音訊檔案，並使用詞彙篩選器來為任何不希望出現的字詞加上遮罩。您可以在 OutputBucketName 參數中指定轉錄輸出的位置。

aws transcribe start-medical-transcription-job \
    --cli-input-json file://mysixthfile.json

mysixthfile.json 的內容：

{
    "MedicalTranscriptionJobName": "alternatives-conversation-medical-transcription-job",
    "LanguageCode": "language-code",
    "Specialty": "PRIMARYCARE",
    "Type": "DICTATION",
    "OutputBucketName":"DOC-EXAMPLE-BUCKET",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
    },
    "Settings":{
          "ShowAlternatives": true,
          "MaxAlternatives": 2
    }
}

輸出：

{
    "MedicalTranscriptionJob": {
        "MedicalTranscriptionJobName": "alternatives-dictation-medical-transcription-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
        "StartTime": "2020-09-21T21:01:14.592000+00:00",
        "CreationTime": "2020-09-21T21:01:14.569000+00:00",
        "Settings": {
            "ShowAlternatives": true,
            "MaxAlternatives": 2
        },
        "Specialty": "PRIMARYCARE",
        "Type": "DICTATION"
    }
}

如需詳細資訊，請參閱《Amazon Transcribe 開發人員指南》中的替代轉錄。

範例 7：使用自訂詞彙以更準確的方式轉錄醫學聽寫的音訊檔案

以下 start-medical-transcription-job 範例會轉錄音訊檔案，並使用您先前建立的醫學自訂詞彙來提高轉錄準確度。您可在 OutputBucketName 參數中指定轉錄輸出的位置。

aws transcribe start-transcription-job \
    --cli-input-json file://myseventhfile.json

mysixthfile.json 的內容：

{
    "MedicalTranscriptionJobName": "vocabulary-dictation-medical-transcription-job",
    "LanguageCode": "language-code",
    "Specialty": "PRIMARYCARE",
    "Type": "DICTATION",
    "OutputBucketName":"DOC-EXAMPLE-BUCKET",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
    },
    "Settings":{
        "VocabularyName": "cli-medical-vocab-1"
    }
}

輸出：

{
    "MedicalTranscriptionJob": {
        "MedicalTranscriptionJobName": "vocabulary-dictation-medical-transcription-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.extension"
        },
        "StartTime": "2020-09-21T21:17:27.045000+00:00",
        "CreationTime": "2020-09-21T21:17:27.016000+00:00",
        "Settings": {
            "VocabularyName": "cli-medical-vocab-1"
        },
        "Specialty": "PRIMARYCARE",
        "Type": "DICTATION"
    }
}

如需詳細資訊，請參閱《Amazon Transcribe 開發人員指南》中的醫學自訂詞彙。

JavaScript
SDK for JavaScript (v3)
注意

還有更多 on GitHub。尋找完整範例，並了解如何在 AWS 程式碼範例儲存庫中設定和執行。

建立用戶端。

import { TranscribeClient } from "@aws-sdk/client-transcribe";
// Set the AWS Region.
const REGION = "REGION"; //e.g. "us-east-1"
// Create an Amazon Transcribe service client object.
const transcribeClient = new TranscribeClient({ region: REGION });
export { transcribeClient };

開始醫學轉錄作業。

// Import the required AWS SDK clients and commands for Node.js
import { StartMedicalTranscriptionJobCommand } from "@aws-sdk/client-transcribe";
import { transcribeClient } from "./libs/transcribeClient.js";

// Set the parameters
export const params = {
  MedicalTranscriptionJobName: "MEDICAL_JOB_NAME", // Required
  OutputBucketName: "OUTPUT_BUCKET_NAME", // Required
  Specialty: "PRIMARYCARE", // Required. Possible values are 'PRIMARYCARE'
  Type: "JOB_TYPE", // Required. Possible values are 'CONVERSATION' and 'DICTATION'
  LanguageCode: "LANGUAGE_CODE", // For example, 'en-US'
  MediaFormat: "SOURCE_FILE_FORMAT", // For example, 'wav'
  Media: {
    MediaFileUri: "SOURCE_FILE_LOCATION",
    // The S3 object location of the input media file. The URI must be in the same region
    // as the API endpoint that you are calling.For example,
    // "https://transcribe-demo.s3-REGION.amazonaws.com/hello_world.wav"
  },
};

export const run = async () => {
  try {
    const data = await transcribeClient.send(
      new StartMedicalTranscriptionJobCommand(params),
    );
    console.log("Success - put", data);
    return data; // For unit tests.
  } catch (err) {
    console.log("Error", err);
  }
};
run();