Cette page a été traduite par l'API Cloud Translation.

Transcrire un fichier audio de manière asynchrone dans Cloud Storage

Effectuez une transcription asynchrone sur un fichier audio stocké dans Cloud Storage.

En savoir plus

Pour obtenir une documentation détaillée incluant cet exemple de code, consultez les articles suivants :

Transcrire des fichiers audio longs en texte

Exemple de code

Go

Pour savoir comment installer et utiliser la bibliothèque cliente pour Speech-to-Text, consultez la page Bibliothèques clientes Speech-to-Text. Pour en savoir plus, consultez la documentation de référence de l'API Speech-to-Text en langage Go.

Pour vous authentifier auprès de Speech-to-Text, configurez le service Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.


func sendGCS(w io.Writer, client *speech.Client, 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",
		},
		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(w, "\"%v\" (confidence=%3f)\n", alt.Transcript, alt.Confidence)
		}
	}
	return nil
}

Java

/**
 * Performs non-blocking speech recognition on remote FLAC file and prints the transcription.
 *
 * @param gcsUri the path to the remote LINEAR16 audio file to transcribe.
 */
public static void asyncRecognizeGcs(String gcsUri) throws Exception {
  // Configure polling algorithm
  SpeechSettings.Builder speechSettings = SpeechSettings.newBuilder();
  TimedRetryAlgorithm timedRetryAlgorithm =
      OperationTimedPollAlgorithm.create(
          RetrySettings.newBuilder()
              .setInitialRetryDelay(Duration.ofMillis(500L))
              .setRetryDelayMultiplier(1.5)
              .setMaxRetryDelay(Duration.ofMillis(5000L))
              .setInitialRpcTimeout(Duration.ZERO) // ignored
              .setRpcTimeoutMultiplier(1.0) // ignored
              .setMaxRpcTimeout(Duration.ZERO) // ignored
              .setTotalTimeout(Duration.ofHours(24L)) // set polling timeout to 24 hours
              .build());
  speechSettings.longRunningRecognizeOperationSettings().setPollingAlgorithm(timedRetryAlgorithm);

  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  try (SpeechClient speech = SpeechClient.create(speechSettings.build())) {

    // Configure remote file request for FLAC
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.FLAC)
            .setLanguageCode("en-US")
            .setSampleRateHertz(16000)
            .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());
    }
  }
}

Node.js

// 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 = {
  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();
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
console.log(`Transcription: ${transcription}`);

PHP

Pour savoir comment installer et utiliser la bibliothèque cliente pour Speech-to-Text, consultez la page Bibliothèques clientes Speech-to-Text.

use Google\Cloud\Speech\V1\SpeechClient;
use Google\Cloud\Speech\V1\RecognitionAudio;
use Google\Cloud\Speech\V1\RecognitionConfig;
use Google\Cloud\Speech\V1\RecognitionConfig\AudioEncoding;

/**
 * @param string $uri The Cloud Storage object to transcribe (gs://your-bucket-name/your-object-name)
 */
function transcribe_async_gcs(string $uri)
{
    // change these variables if necessary
    $encoding = AudioEncoding::LINEAR16;
    $sampleRateHertz = 32000;
    $languageCode = 'en-US';

    // set string as audio content
    $audio = (new RecognitionAudio())
        ->setUri($uri);

    // set config
    $config = (new RecognitionConfig())
        ->setEncoding($encoding)
        ->setSampleRateHertz($sampleRateHertz)
        ->setLanguageCode($languageCode);

    // create the speech client
    $client = new SpeechClient();

    // create the asyncronous recognize operation
    $operation = $client->longRunningRecognize($config, $audio);
    $operation->pollUntilComplete();

    if ($operation->operationSucceeded()) {
        $response = $operation->getResult();

        // each result is for a consecutive portion of the audio. iterate
        // through them to get the transcripts for the entire audio file.
        foreach ($response->getResults() as $result) {
            $alternatives = $result->getAlternatives();
            $mostLikely = $alternatives[0];
            $transcript = $mostLikely->getTranscript();
            $confidence = $mostLikely->getConfidence();
            printf('Transcript: %s' . PHP_EOL, $transcript);
            printf('Confidence: %s' . PHP_EOL, $confidence);
        }
    } else {
        print_r($operation->getError());
    }

    $client->close();
}

Python

from google.cloud import speech


def transcribe_gcs(gcs_uri: str) -> str:
    """Asynchronously transcribes the audio file from Cloud Storage
    Args:
        gcs_uri: The Google Cloud Storage path to an audio file.
            E.g., "gs://storage-bucket/file.flac".
    Returns:
        The generated transcript from the audio file provided.
    """
    client = speech.SpeechClient()

    audio = speech.RecognitionAudio(uri=gcs_uri)
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
        sample_rate_hertz=44100,
        language_code="en-US",
    )

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

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

    transcript_builder = []
    # Each result is for a consecutive portion of the audio. Iterate through
    # them to get the transcripts for the entire audio file.
    for result in response.results:
        # The first alternative is the most likely one for this portion.
        transcript_builder.append(f"\nTranscript: {result.alternatives[0].transcript}")
        transcript_builder.append(f"\nConfidence: {result.alternatives[0].confidence}")

    transcript = "".join(transcript_builder)
    print(transcript)

    return transcript

Ruby