複数のチャンネルを含む音声の文字変換

// transcribeMultichannel generates a transcript from a multichannel speech file and tags the speech from each channel.
func transcribeMultichannel(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 := ioutil.ReadFile("../testdata/commercial_stereo.wav")
	if err != nil {
		return fmt.Errorf("ReadFile: %w", err)
	}

	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:                            speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz:                     44100,
			LanguageCode:                        "en-US",
			AudioChannelCount:                   2,
			EnableSeparateRecognitionPerChannel: true,
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	})
	if err != nil {
		return fmt.Errorf("Recognize: %w", err)
	}

	// Print the results.
	for _, result := range resp.Results {
		for _, alt := range result.Alternatives {
			fmt.Fprintf(w, "Channel %v: %v\n", result.ChannelTag, alt.Transcript)
		}
	}
	return nil
}

/**
 * Transcribe a remote audio file with multi-channel recognition
 *
 * @param gcsUri the path to the audio file
 */
public static void transcribeMultiChannelGcs(String gcsUri) throws Exception {

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

    // Configure request to enable multiple channels
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            .setSampleRateHertz(44100)
            .setAudioChannelCount(2)
            .setEnableSeparateRecognitionPerChannel(true)
            .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);
    }
    // Just print the first result here.
    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", alternative.getTranscript());
      System.out.printf("Channel Tag : %s\n", result.getChannelTag());
    }
  }
}

const speech = require('@google-cloud/speech').v1;

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

const config = {
  encoding: 'LINEAR16',
  languageCode: 'en-US',
  audioChannelCount: 2,
  enableSeparateRecognitionPerChannel: true,
};

const audio = {
  uri: gcsUri,
};

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

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

from google.cloud import speech


def transcribe_file_with_multichannel(audio_file: str) -> speech.RecognizeResponse:
    """Transcribe the given audio file synchronously with multi channel.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
            Example: "resources/multi.wav"
    Returns:
         cloud_speech.RecognizeResponse: The full response object which includes the transcription results.
    """
    client = speech.SpeechClient()

    with open(audio_file, "rb") as f:
        audio_content = f.read()

    audio = speech.RecognitionAudio(content=audio_content)

    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=44100,
        language_code="en-US",
        audio_channel_count=2,
        enable_separate_recognition_per_channel=True,
    )

    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}")
        print(f"Channel Tag: {result.channel_tag}")

    return result