Cloud Storage でのマルチチャンネル ファイルの音声文字変換

Cloud Storage に保存されている音声ファイルを文字に変換します（複数のチャンネルを含む）。

もっと見る

このコードサンプルを含む詳細なドキュメントについては、以下をご覧ください。

コードサンプル

Java

/**
 * 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());
    }
  }
}

Node.js

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}`);

Python

from google.cloud import speech

client = speech.SpeechClient()

audio = speech.RecognitionAudio(uri=gcs_uri)

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("First alternative of result {}".format(i))
    print(u"Transcript: {}".format(alternative.transcript))
    print(u"Channel Tag: {}".format(result.channel_tag))

Ruby

# storage_path = "Path to file in Cloud Storage, eg. gs://bucket/audio.raw"

require "google/cloud/speech"

speech = Google::Cloud::Speech.speech

config = {
  encoding:                                :LINEAR16,
  sample_rate_hertz:                       44_100,
  language_code:                           "en-US",
  audio_channel_count:                     2,
  enable_separate_recognition_per_channel: true
}

audio = { uri: storage_path }

response = speech.recognize config: config, audio: audio

results = response.results

results.each_with_index do |result, i|
  alternative = result.alternatives.first
  puts "-" * 20
  puts "First alternative of result #{i}"
  puts "Transcript: #{alternative.transcript}"
  puts "Channel Tag: #{result.channel_tag}"
end

次のステップ

他の Google Cloud プロダクトに関連するコードサンプルの検索およびフィルタ検索を行うには、Google Cloud のサンプルをご覧ください。