Esta página se ha traducido con Cloud Translation API.

Transcribir de forma asíncrona un archivo de audio de Cloud Storage

Realiza una transcripción asíncrona de un archivo de audio almacenado en Cloud Storage.

Investigar más

Para obtener documentación detallada que incluya este código de muestra, consulta lo siguiente:

Transcribir archivos de audio largos a texto

Código de ejemplo

Go

Para saber cómo instalar y usar la biblioteca de cliente de Cloud STT, consulta Bibliotecas de cliente de Cloud STT. Para obtener más información, consulta la documentación de referencia de la API Cloud STT Go.

Para autenticarte en Cloud STT, configura las credenciales predeterminadas de la aplicación. Para obtener más información, consulta el artículo Configurar la autenticación en un entorno de desarrollo 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

Para saber cómo instalar y usar la biblioteca de cliente de Cloud STT, consulta Bibliotecas de cliente de Cloud STT.

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

/**
 * @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.
 * @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_gcs(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);

    $config = (new RecognitionConfig())
        // Can also use {@see Google\Cloud\Speech\V2\ExplicitDecodingConfig}
        // ->setExplicitDecodingConfig(new ExplicitDecodingConfig([...]);

        ->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];
                    $transcript = $mostLikely->getTranscript();
                    $confidence = $mostLikely->getConfidence();
                    printf('Transcript: %s' . PHP_EOL, $transcript);
                    printf('Confidence: %s' . PHP_EOL, $confidence);
                }
            }
        } else {
            print_r($operation->getError());
        }
    } finally {
        $speech->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