Lokale Datei mit einem Transkriptionsmodell transkribieren

Lokale Audiodatei mit einem trainierten Transkriptionsmodell transkribieren.

Weitere Informationen

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

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 modelSelection(w io.Writer) error {
	ctx := context.Background()

	client, err := speech.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %w", err)
	}
	defer client.Close()

	data, err := os.ReadFile("../testdata/Google_Gnome.wav")
	if err != nil {
		return fmt.Errorf("ReadFile: %w", err)
	}

	req := &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
			Model:           "video",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	}

	resp, err := client.Recognize(ctx, req)
	if err != nil {
		return fmt.Errorf("recognize: %w", err)
	}

	for i, result := range resp.Results {
		fmt.Fprintf(w, "%s\n", strings.Repeat("-", 20))
		fmt.Fprintf(w, "Result %d\n", i+1)
		for j, alternative := range result.Alternatives {
			fmt.Fprintf(w, "Alternative %d: %s\n", j+1, alternative.Transcript)
		}
	}
	return nil
}

Java

/**
 * Performs transcription of the given audio file synchronously with the selected model.
 *
 * @param fileName the path to a audio file to transcribe
 */
public static void transcribeModelSelection(String fileName) throws Exception {
  Path path = Paths.get(fileName);
  byte[] content = Files.readAllBytes(path);

  try (SpeechClient speech = SpeechClient.create()) {
    // Configure request with video media type
    RecognitionConfig recConfig =
        RecognitionConfig.newBuilder()
            // encoding may either be omitted or must match the value in the file header
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            // sample rate hertz may be either be omitted or must match the value in the file
            // header
            .setSampleRateHertz(16000)
            .setModel("video")
            .build();

    RecognitionAudio recognitionAudio =
        RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();

    RecognizeResponse recognizeResponse = speech.recognize(recConfig, recognitionAudio);
    // Just print the first result here.
    SpeechRecognitionResult result = recognizeResponse.getResultsList().get(0);
    // 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("Transcript : %s\n", alternative.getTranscript());
  }
}

Node.js

// Imports the Google Cloud client library for Beta API
/**
 * TODO(developer): Update client library import to use new
 * version of API when desired features become available
 */
const speech = require('@google-cloud/speech').v1p1beta1;
const fs = require('fs');

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

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const filename = 'Local path to audio file, e.g. /path/to/audio.raw';
// const model = 'Model to use, e.g. phone_call, video, default';
// 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,
  model: model,
};
const audio = {
  content: fs.readFileSync(filename).toString('base64'),
};

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\RecognizeRequest;
use Google\Cloud\Speech\V2\RecognitionConfig;
use Google\Cloud\Speech\V2\AutoDetectDecodingConfig;

/**
 * @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 $audioFile path to an audio file.
 * @param string $model The recognition model to use.
 */
function transcribe_model_selection(string $projectId, string $location, string $recognizerId, string $audioFile, string $model)
{
    // create the speech client
    $apiEndpoint = $location === 'global' ? null : sprintf('%s-speech.googleapis.com', $location);
    $speech = new SpeechClient(['apiEndpoint' => $apiEndpoint]);

    // get contents of a file into a string
    $content = file_get_contents($audioFile);

    $recognizerName = SpeechClient::recognizerName($projectId, $location, $recognizerId);

    // set config
    $config = (new RecognitionConfig())
        ->setModel($model)

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

        ->setAutoDecodingConfig(new AutoDetectDecodingConfig());

    $request = (new RecognizeRequest())
        ->setRecognizer($recognizerName)
        ->setConfig($config)
        ->setContent($content);

    // make the API call
    $response = $speech->recognize($request);
    $results = $response->getResults();

    // print results
    foreach ($results 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);
    }

    $speech->close();
}

Python

from google.cloud import speech

# Instantiates a client
client = speech.SpeechClient()
# Reads a file as bytes
with open("resources/Google_Gnome.wav", "rb") as f:
    audio_content = f.read()

audio = speech.RecognitionAudio(content=audio_content)

config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=16000,
    language_code="en-US",
    model="video",  # Chosen model
)

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

for i, result in enumerate(response.results):
    alternative = result.alternatives[0]
    print("-" * 20)
    print(f"First alternative of result {i}")
    print(f"Transcript: {alternative.transcript}")

Ruby