Cloud Storage-Datei synchron transkribieren

Synchrone Transkription für eine in Cloud Storage gespeicherte Audiodatei ausführen.

Weitere Informationen

Eine ausführliche Dokumentation, die dieses Codebeispiel enthält, finden Sie hier:

Kurze Audiodateien transkribieren

Codebeispiel

Go

Informationen zum Installieren und Verwenden der Clientbibliothek für Cloud STT finden Sie unter Cloud STT-Clientbibliotheken. Weitere Informationen finden Sie in der API-Referenzdokumentation zu Cloud STT Go.

Richten Sie die Standardanmeldedaten für Anwendungen ein, um sich bei Cloud STT zu authentifizieren. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten.


func recognizeGCS(w io.Writer, gcsURI string) error {
	ctx := context.Background()

	client, err := speech.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	// Send the request with the URI (gs://...)
	// and sample rate information to be transcripted.
	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Uri{Uri: gcsURI},
		},
	})

	// 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 speech recognition on remote FLAC file and prints the transcription.
 *
 * @param gcsUri the path to the remote FLAC audio file to transcribe.
 */
public static void syncRecognizeGcs(String gcsUri) throws Exception {
  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  try (SpeechClient speech = SpeechClient.create()) {
    // Builds the request for remote FLAC file
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.FLAC)
            .setLanguageCode("en-US")
            .setSampleRateHertz(16000)
            .build();
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use blocking call for getting audio transcript
    RecognizeResponse response = speech.recognize(config, audio);
    List<SpeechRecognitionResult> results = response.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
const [response] = await client.recognize(request);
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
console.log('Transcription: ', transcription);

PHP

Informationen zum Installieren und Verwenden der Clientbibliothek für Cloud STT finden Sie unter Cloud STT-Clientbibliotheken.

use Google\Cloud\Speech\V2\Client\SpeechClient;
use Google\Cloud\Speech\V2\RecognitionConfig;
use Google\Cloud\Speech\V2\ExplicitDecodingConfig;
use Google\Cloud\Speech\V2\ExplicitDecodingConfig\AudioEncoding;
use Google\Cloud\Speech\V2\RecognizeRequest;

/**
 * @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 (gs://your-bucket-name/your-object-name)
 */
function transcribe_sync_gcs(string $projectId, string $location, string $recognizerId, string $uri)
{
    // create the speech client
    $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\AutoDetectDecodingConfig}
        // ->setAutoDecodingConfig(new AutoDetectDecodingConfig());

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

    $request = (new RecognizeRequest())
        ->setRecognizer($recognizerName)
        ->setConfig($config)
        ->setUri($uri);

    try {
        $response = $speech->recognize($request);
        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);
        }
    } finally {
        $speech->close();
    }
}

Python

def transcribe_gcs(audio_uri: str) -> speech.RecognizeResponse:
    """Transcribes the audio file specified by the gcs_uri.
    Args:
        audio_uri (str): The Google Cloud Storage URI of the input audio file.
            E.g., gs://cloud-samples-data/speech/audio.flac
    Returns:
        cloud_speech.RecognizeResponse: The response containing the transcription results
    """
    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",
    )

    response = client.recognize(config=config, audio=audio)

    # 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.
        print(f"Transcript: {result.alternatives[0].transcript}")

    return response

Ruby