비동기식으로 타임스탬프를 적용한 오디오 파일 텍스트 변환

Cloud Storage에 저장된 오디오 파일에서 타임스탬프를 포함한 비동기 스크립트 작성을 수행합니다.

더 살펴보기

이 코드 샘플이 포함된 자세한 문서는 다음을 참조하세요.

• 단어 타임스탬프 가져오기

코드 샘플

Go

Cloud STT용 클라이언트 라이브러리를 설치하고 사용하는 방법은 Cloud STT 클라이언트 라이브러리를 참고하세요. 자세한 내용은 Cloud STT Go API 참고 문서를 확인하세요.

Cloud STT에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

func asyncWords(client *speech.Client, out io.Writer, gcsURI string) error {
	ctx := context.Background()

	// Send the contents of the audio file with the encoding and
	// and sample rate information to be transcripted.
	req := &speechpb.LongRunningRecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:              speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz:       16000,
			LanguageCode:          "en-US",
			EnableWordTimeOffsets: true,
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Uri{Uri: gcsURI},
		},
	}

	op, err := client.LongRunningRecognize(ctx, req)
	if err != nil {
		return err
	}
	resp, err := op.Wait(ctx)
	if err != nil {
		return err
	}

	// Print the results.
	for _, result := range resp.Results {
		for _, alt := range result.Alternatives {
			fmt.Fprintf(out, "\"%v\" (confidence=%3f)\n", alt.Transcript, alt.Confidence)
			for _, w := range alt.Words {
				fmt.Fprintf(out,
					"Word: \"%v\" (startTime=%3f, endTime=%3f)\n",
					w.Word,
					float64(w.StartTime.Seconds)+float64(w.StartTime.Nanos)*1e-9,
					float64(w.EndTime.Seconds)+float64(w.EndTime.Nanos)*1e-9,
				)
			}
		}
	}
	return nil
}

Java

Cloud STT용 클라이언트 라이브러리를 설치하고 사용하는 방법은 Cloud STT 클라이언트 라이브러리를 참고하세요. 자세한 내용은 Cloud STT Java API 참고 문서를 확인하세요.

Cloud STT에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

/**
 * Performs non-blocking speech recognition on remote FLAC file and prints the transcription as
 * well as word time offsets.
 *
 * @param gcsUri the path to the remote LINEAR16 audio file to transcribe.
 */
public static void asyncRecognizeWords(String gcsUri) throws Exception {
  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  try (SpeechClient speech = SpeechClient.create()) {

    // Configure remote file request for FLAC
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.FLAC)
            .setLanguageCode("en-US")
            .setSampleRateHertz(16000)
            .setEnableWordTimeOffsets(true)
            .build();
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use non-blocking call for getting file transcription
    OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
        speech.longRunningRecognizeAsync(config, audio);
    while (!response.isDone()) {
      System.out.println("Waiting for response...");
      Thread.sleep(10000);
    }

    List<SpeechRecognitionResult> results = response.get().getResultsList();

    for (SpeechRecognitionResult result : results) {
      // There can be several alternative transcripts for a given chunk of speech. Just use the
      // first (most likely) one here.
      SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
      System.out.printf("Transcription: %s\n", alternative.getTranscript());
      for (WordInfo wordInfo : alternative.getWordsList()) {
        System.out.println(wordInfo.getWord());
        System.out.printf(
            "\t%s.%s sec - %s.%s sec\n",
            wordInfo.getStartTime().getSeconds(),
            wordInfo.getStartTime().getNanos() / 100000000,
            wordInfo.getEndTime().getSeconds(),
            wordInfo.getEndTime().getNanos() / 100000000);
      }
    }
  }
}

Node.js

Cloud STT용 클라이언트 라이브러리를 설치하고 사용하는 방법은 Cloud STT 클라이언트 라이브러리를 참고하세요. 자세한 내용은 Cloud STT Node.js API 참고 문서를 확인하세요.

Cloud STT에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

// Imports the Google Cloud client library
const speech = require('@google-cloud/speech');

// Creates a client
const client = new speech.SpeechClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const gcsUri = 'gs://my-bucket/audio.raw';
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
// const sampleRateHertz = 16000;
// const languageCode = 'BCP-47 language code, e.g. en-US';

const config = {
  enableWordTimeOffsets: true,
  encoding: encoding,
  sampleRateHertz: sampleRateHertz,
  languageCode: languageCode,
};

const audio = {
  uri: gcsUri,
};

const request = {
  config: config,
  audio: audio,
};

// Detects speech in the audio file. This creates a recognition job that you
// can wait for now, or get its result later.
const [operation] = await client.longRunningRecognize(request);

// Get a Promise representation of the final result of the job
const [response] = await operation.promise();
response.results.forEach(result => {
  console.log(`Transcription: ${result.alternatives[0].transcript}`);
  result.alternatives[0].words.forEach(wordInfo => {
    // NOTE: If you have a time offset exceeding 2^32 seconds, use the
    // wordInfo.{x}Time.seconds.high to calculate seconds.
    const startSecs =
      `${wordInfo.startTime.seconds}` +
      '.' +
      wordInfo.startTime.nanos / 100000000;
    const endSecs =
      `${wordInfo.endTime.seconds}` +
      '.' +
      wordInfo.endTime.nanos / 100000000;
    console.log(`Word: ${wordInfo.word}`);
    console.log(`\t ${startSecs} secs - ${endSecs} secs`);
  });
});

PHP

Cloud STT용 클라이언트 라이브러리를 설치하고 사용하는 방법은 Cloud STT 클라이언트 라이브러리를 참고하세요.

Cloud STT에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

use Google\Cloud\Speech\V2\BatchRecognizeFileMetadata;
use Google\Cloud\Speech\V2\Client\SpeechClient;
use Google\Cloud\Speech\V2\BatchRecognizeRequest;
use Google\Cloud\Speech\V2\ExplicitDecodingConfig;
use Google\Cloud\Speech\V2\ExplicitDecodingConfig\AudioEncoding;
use Google\Cloud\Speech\V2\InlineOutputConfig;
use Google\Cloud\Speech\V2\RecognitionConfig;
use Google\Cloud\Speech\V2\RecognitionFeatures;
use Google\Cloud\Speech\V2\RecognitionOutputConfig;
use Google\Cloud\Speech\V2\SpeakerDiarizationConfig;

/**
 * @param string $projectId The Google Cloud project ID.
 * @param string $location The location of the recognizer.
 * @param string $recognizerId The ID of the recognizer to use. The recognizer's model must support
 *                             diarization (e.g. "chirp_3").
 * @param string $uri The Cloud Storage object to transcribe (other than global)
 *                    e.x. gs://cloud-samples-data/speech/brooklyn_bridge.raw
 */
function transcribe_async_words(string $projectId, string $location, string $recognizerId, string $uri)
{
    $apiEndpoint = $location === 'global' ? null : sprintf('%s-speech.googleapis.com', $location);
    $speech = new SpeechClient(['apiEndpoint' => $apiEndpoint]);
    $recognizerName = SpeechClient::recognizerName($projectId, $location, $recognizerId);

    // When this is enabled, we send all the words from the beginning of the audio.
    $features = new RecognitionFeatures([
        'diarization_config' => new SpeakerDiarizationConfig(),
    ]);

    $config = (new RecognitionConfig())
        ->setFeatures($features)
        // When running outside the "global" location, you can set the model to "chirp_3" in
        // RecognitionConfig instead of on the recognizer.
        // ->setModel('chirp_3')

        // Can also use {@see Google\Cloud\Speech\V2\AutoDetectDecodingConfig}
        // ->setAutoDecodingConfig(new AutoDetectDecodingConfig());

        ->setExplicitDecodingConfig(new ExplicitDecodingConfig([
            // change these variables if necessary
            'encoding' => AudioEncoding::LINEAR16,
            'sample_rate_hertz' => 16000,
            'audio_channel_count' => 1,
        ]));

    $outputConfig = (new RecognitionOutputConfig())
        ->setInlineResponseConfig(new InlineOutputConfig());

    $file = new BatchRecognizeFileMetadata();
    $file->setUri($uri);

    $request = (new BatchRecognizeRequest())
        ->setRecognizer($recognizerName)
        ->setConfig($config)
        ->setFiles([$file])
        ->setRecognitionOutputConfig($outputConfig);

    try {
        $operation = $speech->batchRecognize($request);
        $operation->pollUntilComplete();

        if ($operation->operationSucceeded()) {
            $response = $operation->getResult();
            foreach ($response->getResults() as $result) {
                if ($result->getError()) {
                    print('Error: ' . $result->getError()->getMessage());
                }
                // get the most likely transcription
                $transcript = $result->getInlineResult()->getTranscript();
                foreach ($transcript->getResults() as $transacriptResult) {
                    $alternatives = $transacriptResult->getAlternatives();
                    $mostLikely = $alternatives[0];
                    foreach ($mostLikely->getWords() as $wordInfo) {
                        $startTime = $wordInfo->getStartOffset();
                        $endTime = $wordInfo->getEndOffset();
                        printf('  Word: %s (start: %s, end: %s)' . PHP_EOL,
                            $wordInfo->getWord(),
                            $startTime?->serializeToJsonString(),
                            $endTime?->serializeToJsonString()
                        );
                    }
                }
            }
        } else {
            print_r($operation->getError());
        }
    } finally {
        $speech->close();
    }
}

Python

Cloud STT용 클라이언트 라이브러리를 설치하고 사용하는 방법은 Cloud STT 클라이언트 라이브러리를 참고하세요. 자세한 내용은 Cloud STT Python API 참고 문서를 확인하세요.

Cloud STT에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

def transcribe_gcs_with_word_time_offsets(
    audio_uri: str,
) -> speech.RecognizeResponse:
    """Transcribe the given audio file asynchronously and output the word time
    offsets.
    Args:
        audio_uri (str): The Google Cloud Storage URI of the input audio file.
            E.g., gs://[BUCKET]/[FILE]
    Returns:
        speech.RecognizeResponse: The response containing the transcription results with word time offsets.
    """
    from google.cloud import speech

    client = speech.SpeechClient()

    audio = speech.RecognitionAudio(uri=audio_uri)
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
        sample_rate_hertz=16000,
        language_code="en-US",
        enable_word_time_offsets=True,
    )

    operation = client.long_running_recognize(config=config, audio=audio)

    print("Waiting for operation to complete...")
    result = operation.result(timeout=90)

    for result in result.results:
        alternative = result.alternatives[0]
        print(f"Transcript: {alternative.transcript}")
        print(f"Confidence: {alternative.confidence}")

        for word_info in alternative.words:
            word = word_info.word
            start_time = word_info.start_time
            end_time = word_info.end_time

            print(
                f"Word: {word}, start_time: {start_time.total_seconds()}, end_time: {end_time.total_seconds()}"
            )

    return result

Ruby

Cloud STT용 클라이언트 라이브러리를 설치하고 사용하는 방법은 Cloud STT 클라이언트 라이브러리를 참고하세요.

Cloud STT에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

# storage_path = "Path to file in Cloud Storage, eg. gs://bucket/audio.raw"

require "google/cloud/speech"

speech = Google::Cloud::Speech.speech version: :v1

config = { encoding:                 :LINEAR16,
           sample_rate_hertz:        16_000,
           language_code:            "en-US",
           enable_word_time_offsets: true }
audio  = { uri: storage_path }

operation = speech.long_running_recognize config: config, audio: audio

puts "Operation started"

operation.wait_until_done!

raise operation.results.message if operation.error?

results = operation.response.results

results.first.alternatives.each do |alternative|
  puts "Transcription: #{alternative.transcript}"

  alternative.words.each do |word|
    start_time = word.start_time.seconds + (word.start_time.nanos / 1_000_000_000.0)
    end_time   = word.end_time.seconds + (word.end_time.nanos / 1_000_000_000.0)

    puts "Word: #{word.word} #{start_time} #{end_time}"
  end
end

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저를 참고하세요.