분할을 사용한 Cloud Storage의 파일 스크립트 작성

Cloud Storage에 저장된 오디오 파일의 여러 화자를 인식합니다.

코드 샘플

Java

Speech-to-Text용 클라이언트 라이브러리를 설치하고 사용하는 방법은 Speech-to-Text 클라이언트 라이브러리를 참조하세요. 자세한 내용은 Speech-to-Text Java API 참조 문서를 확인하세요.

Speech-to-Text에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.speech.v1.LongRunningRecognizeMetadata;
import com.google.cloud.speech.v1.LongRunningRecognizeResponse;
import com.google.cloud.speech.v1.RecognitionAudio;
import com.google.cloud.speech.v1.RecognitionConfig;
import com.google.cloud.speech.v1.SpeakerDiarizationConfig;
import com.google.cloud.speech.v1.SpeechClient;
import com.google.cloud.speech.v1.SpeechRecognitionAlternative;
import com.google.cloud.speech.v1.WordInfo;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

public class TranscribeDiarizationGcs {

  static void transcribeDiarizationGcs()
      throws IOException, ExecutionException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String gcsUri = "gs://cloud-samples-data/speech/commercial_mono.wav";
    transcribeDiarizationGcs(gcsUri);
  }

  // Transcribe the give gcs file using speaker diarization
  public static void transcribeDiarizationGcs(String gcsUri)
      throws IOException, ExecutionException, InterruptedException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (SpeechClient speechClient = SpeechClient.create()) {
      SpeakerDiarizationConfig speakerDiarizationConfig =
          SpeakerDiarizationConfig.newBuilder()
              .setEnableSpeakerDiarization(true)
              .setMinSpeakerCount(2)
              .setMaxSpeakerCount(2)
              .build();
      // Configure request to enable Speaker diarization
      RecognitionConfig config =
          RecognitionConfig.newBuilder()
              .setEncoding(RecognitionConfig.AudioEncoding.LINEAR16)
              .setLanguageCode("en-US")
              .setSampleRateHertz(8000)
              .setDiarizationConfig(speakerDiarizationConfig)
              .build();
      // Set the remote path for the audio file
      RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

      // Use non-blocking call for getting file transcription
      OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> future =
          speechClient.longRunningRecognizeAsync(config, audio);
      System.out.println("Waiting for response...");

      // Speaker Tags are only included in the last result object, which has only one alternative.
      LongRunningRecognizeResponse response = future.get();
      SpeechRecognitionAlternative alternative =
          response.getResults(response.getResultsCount() - 1).getAlternatives(0);
      // The alternative is made up of WordInfo objects that contain the speaker_tag.
      WordInfo wordInfo = alternative.getWords(0);
      int currentSpeakerTag = wordInfo.getSpeakerTag();
      // For each word, get all the words associated with one speaker, once the speaker changes,
      // add a new line with the new speaker and their spoken words.
      StringBuilder speakerWords =
          new StringBuilder(
              String.format("Speaker %d: %s", wordInfo.getSpeakerTag(), wordInfo.getWord()));
      for (int i = 1; i < alternative.getWordsCount(); i++) {
        wordInfo = alternative.getWords(i);
        if (currentSpeakerTag == wordInfo.getSpeakerTag()) {
          speakerWords.append(" ");
          speakerWords.append(wordInfo.getWord());
        } else {
          speakerWords.append(
              String.format("\nSpeaker %d: %s", wordInfo.getSpeakerTag(), wordInfo.getWord()));
          currentSpeakerTag = wordInfo.getSpeakerTag();
        }
      }
      System.out.println(speakerWords.toString());
    }
  }
}

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저 참조하기