Transcribir un archivo multilingüe local (beta)

Transcribe un archivo de audio local que incluya más de un idioma.

Explora más

Para obtener documentación en la que se incluye esta muestra de código, consulta lo siguiente:

Muestra de código

Java

/**
 * Transcribe a local audio file with multi-language recognition
 *
 * @param fileName the path to the audio file
 */
public static void transcribeMultiLanguage(String fileName) throws Exception {
  Path path = Paths.get(fileName);
  // Get the contents of the local audio file
  byte[] content = Files.readAllBytes(path);

  try (SpeechClient speechClient = SpeechClient.create()) {

    RecognitionAudio recognitionAudio =
        RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();
    ArrayList<String> languageList = new ArrayList<>();
    languageList.add("es-ES");
    languageList.add("en-US");

    // Configure request to enable multiple languages
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.LINEAR16)
            .setSampleRateHertz(16000)
            .setLanguageCode("ja-JP")
            .addAllAlternativeLanguageCodes(languageList)
            .build();
    // Perform the transcription request
    RecognizeResponse recognizeResponse = speechClient.recognize(config, recognitionAudio);

    // Print out the results
    for (SpeechRecognitionResult result : recognizeResponse.getResultsList()) {
      // There can be several alternative transcripts for a given chunk of speech. Just use the
      // first (most likely) one here.
      SpeechRecognitionAlternative alternative = result.getAlternatives(0);
      System.out.format("Transcript : %s\n\n", alternative.getTranscript());
    }
  }
}

Node.js

const fs = require('fs');

// Imports the Google Cloud client library
const speech = require('@google-cloud/speech').v1p1beta1;

// 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 config = {
  encoding: 'LINEAR16',
  sampleRateHertz: 44100,
  languageCode: 'en-US',
  alternativeLanguageCodes: ['es-ES', 'en-US'],
};

const audio = {
  content: fs.readFileSync(fileName).toString('base64'),
};

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

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

Python

from google.cloud import speech_v1p1beta1 as speech

client = speech.SpeechClient()

speech_file = "resources/multi.wav"
first_lang = "en-US"
second_lang = "es"

with open(speech_file, "rb") as audio_file:
    content = audio_file.read()

audio = speech.RecognitionAudio(content=content)

config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=44100,
    audio_channel_count=2,
    language_code=first_lang,
    alternative_language_codes=[second_lang],
)

print("Waiting for operation to complete...")
response = client.recognize(config=config, audio=audio)

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

¿Qué sigue?

Para buscar y filtrar muestras de código para otros productos de Google Cloud, consulta el navegador de muestra de Google Cloud.