Speech-to-Text で言語認識を有効にする

/**
 * 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());
    }
  }
}

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}`);

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(f"First alternative of result {i}: {alternative}")
    print(f"Transcript: {alternative.transcript}")

return response.results

/**
 * Transcribe a remote audio file with multi-language recognition
 *
 * @param gcsUri the path to the remote audio file
 */
public static void transcribeMultiLanguageGcs(String gcsUri) throws Exception {
  try (SpeechClient speechClient = SpeechClient.create()) {

    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();

    // Set the remote path for the audio file
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use non-blocking call for getting file transcription
    OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
        speechClient.longRunningRecognizeAsync(config, audio);

    while (!response.isDone()) {
      System.out.println("Waiting for response...");
      Thread.sleep(10000);
    }

    for (SpeechRecognitionResult result : response.get().getResultsList()) {

      // 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);

      // Print out the result
      System.out.printf("Transcript : %s\n\n", alternative.getTranscript());
    }
  }
}

// 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 line before running the sample.
 */
// const uri = path to GCS audio file e.g. `gs:/bucket/audio.wav`;

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

const audio = {
  uri: gcsUri,
};

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

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

from google.cloud import speech_v1p1beta1 as speech


def transcribe_file_with_multilanguage_gcs(audio_uri: str) -> str:
    """Transcribe a remote audio file with multi-language recognition
    Args:
        audio_uri (str): The Google Cloud Storage path to an audio file.
            E.g., gs://[BUCKET]/[FILE]
    Returns:
        str: The generated transcript from the audio file provided.
    """

    client = speech.SpeechClient()

    first_language = "es-ES"
    alternate_languages = ["en-US", "fr-FR"]

    # Configure request to enable multiple languages
    recognition_config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
        sample_rate_hertz=44100,
        language_code=first_language,
        alternative_language_codes=alternate_languages,
    )

    # Set the remote path for the audio file
    audio = speech.RecognitionAudio(uri=audio_uri)

    # Use non-blocking call for getting file transcription
    response = client.long_running_recognize(
        config=recognition_config, audio=audio
    ).result(timeout=300)

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

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

    return transcript