Java AudioEncoding类代码示例

import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding; //导入依赖的package包/类
/**
 * Performs speech recognition on raw PCM audio and prints the transcription.
 *
 * @param fileName the path to a PCM audio file to transcribe.
 */
public static void syncRecognizeFile(String fileName) throws Exception, IOException {
  SpeechClient speech = SpeechClient.create();

  Path path = Paths.get(fileName);
  byte[] data = Files.readAllBytes(path);
  ByteString audioBytes = ByteString.copyFrom(data);

  // Configure request with local raw PCM audio
  RecognitionConfig config = RecognitionConfig.newBuilder()
      .setEncoding(AudioEncoding.LINEAR16)
      .setLanguageCode("en-US")
      .setSampleRateHertz(16000)
      .build();
  RecognitionAudio audio = RecognitionAudio.newBuilder()
      .setContent(audioBytes)
      .build();

  // Use blocking call to get audio transcript
  RecognizeResponse response = speech.recognize(config, audio);
  List<SpeechRecognitionResult> results = response.getResultsList();

  for (SpeechRecognitionResult result: results) {
    // 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("Transcription: %s%n", alternative.getTranscript());
  }
  speech.close();
}
 

import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding; //导入依赖的package包/类
/**
 * Performs sync recognize and prints word time offsets.
 *
 * @param fileName the path to a PCM audio file to transcribe get offsets on.
 */
public static void syncRecognizeWords(String fileName) throws Exception, IOException {
  SpeechClient speech = SpeechClient.create();

  Path path = Paths.get(fileName);
  byte[] data = Files.readAllBytes(path);
  ByteString audioBytes = ByteString.copyFrom(data);

  // Configure request with local raw PCM audio
  RecognitionConfig config = RecognitionConfig.newBuilder()
      .setEncoding(AudioEncoding.LINEAR16)
      .setLanguageCode("en-US")
      .setSampleRateHertz(16000)
      .setEnableWordTimeOffsets(true)
      .build();
  RecognitionAudio audio = RecognitionAudio.newBuilder()
      .setContent(audioBytes)
      .build();

  // Use blocking call to get audio transcript
  RecognizeResponse response = speech.recognize(config, audio);
  List<SpeechRecognitionResult> results = response.getResultsList();

  for (SpeechRecognitionResult result: results) {
    // 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("Transcription: %s%n", alternative.getTranscript());
    for (WordInfo wordInfo: alternative.getWordsList()) {
      System.out.println(wordInfo.getWord());
      System.out.printf("\t%s.%s sec - %s.%s sec\n",
          wordInfo.getStartTime().getSeconds(),
          wordInfo.getStartTime().getNanos() / 100000000,
          wordInfo.getEndTime().getSeconds(),
          wordInfo.getEndTime().getNanos() / 100000000);
    }
  }
  speech.close();
}
 

import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding; //导入依赖的package包/类
/**
 * Performs speech recognition on remote FLAC file and prints the transcription.
 *
 * @param gcsUri the path to the remote FLAC audio file to transcribe.
 */
public static void syncRecognizeGcs(String gcsUri) throws Exception, IOException {
  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  SpeechClient speech = SpeechClient.create();

  // Builds the request for remote FLAC file
  RecognitionConfig config = RecognitionConfig.newBuilder()
      .setEncoding(AudioEncoding.FLAC)
      .setLanguageCode("en-US")
      .setSampleRateHertz(16000)
      .build();
  RecognitionAudio audio = RecognitionAudio.newBuilder()
      .setUri(gcsUri)
      .build();

  // Use blocking call for getting audio transcript
  RecognizeResponse response = speech.recognize(config, audio);
  List<SpeechRecognitionResult> results = response.getResultsList();

  for (SpeechRecognitionResult result: results) {
    // 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("Transcription: %s%n", alternative.getTranscript());
  }
  speech.close();
}
 

import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding; //导入依赖的package包/类
public static void asyncRecognizeFile(String fileName) throws Exception, IOException {
  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  SpeechClient speech = SpeechClient.create();

  Path path = Paths.get(fileName);
  byte[] data = Files.readAllBytes(path);
  ByteString audioBytes = ByteString.copyFrom(data);

  // Configure request with local raw PCM audio
  RecognitionConfig config = RecognitionConfig.newBuilder()
      .setEncoding(AudioEncoding.LINEAR16)
      .setLanguageCode("en-US")
      .setSampleRateHertz(16000)
      .build();
  RecognitionAudio audio = RecognitionAudio.newBuilder()
      .setContent(audioBytes)
      .build();

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

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

  List<SpeechRecognitionResult> results = response.get().getResultsList();

  for (SpeechRecognitionResult result: results) {
    // 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("Transcription: %s%n", alternative.getTranscript());
  }
  speech.close();
}
 

import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding; //导入依赖的package包/类
/**
 * Performs non-blocking speech recognition on remote FLAC file and prints
 * the transcription.
 *
 * @param gcsUri the path to the remote LINEAR16 audio file to transcribe.
 */
public static void asyncRecognizeGcs(String gcsUri) throws Exception, IOException {
  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  SpeechClient speech = SpeechClient.create();

  // Configure remote file request for Linear16
  RecognitionConfig config = RecognitionConfig.newBuilder()
      .setEncoding(AudioEncoding.FLAC)
      .setLanguageCode("en-US")
      .setSampleRateHertz(16000)
      .build();
  RecognitionAudio audio = RecognitionAudio.newBuilder()
      .setUri(gcsUri)
      .build();

  // Use non-blocking call for getting file transcription
  OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
      speech.longRunningRecognizeAsync(config, audio);
  while (!response.isDone()) {
    System.out.println("Waiting for response...");
    Thread.sleep(10000);
  }

  List<SpeechRecognitionResult> results = response.get().getResultsList();

  for (SpeechRecognitionResult result: results) {
    // 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("Transcription: %s\n",alternative.getTranscript());
  }
  speech.close();
}
 

import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding; //导入依赖的package包/类
public static void main(String... args) throws Exception {
  // Instantiates a client
  SpeechClient speech = SpeechClient.create();

  // The path to the audio file to transcribe
  String fileName = "./resources/audio.raw";

  // Reads the audio file into memory
  Path path = Paths.get(fileName);
  byte[] data = Files.readAllBytes(path);
  ByteString audioBytes = ByteString.copyFrom(data);

  // Builds the sync recognize request
  RecognitionConfig config = RecognitionConfig.newBuilder()
      .setEncoding(AudioEncoding.LINEAR16)
      .setSampleRateHertz(16000)
      .setLanguageCode("en-US")
      .build();
  RecognitionAudio audio = RecognitionAudio.newBuilder()
      .setContent(audioBytes)
      .build();

  // Performs speech recognition on the audio file
  RecognizeResponse response = speech.recognize(config, audio);
  List<SpeechRecognitionResult> results = response.getResultsList();

  for (SpeechRecognitionResult result: results) {
    // 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("Transcription: %s%n", alternative.getTranscript());
  }
  speech.close();
}
 

import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding; //导入依赖的package包/类
/**
 * Performs non-blocking speech recognition on remote FLAC file and prints
 * the transcription as well as word time offsets.
 *
 * @param gcsUri the path to the remote LINEAR16 audio file to transcribe.
 */
public static void asyncRecognizeWords(String gcsUri) throws Exception, IOException {
  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  SpeechClient speech = SpeechClient.create();

  // Configure remote file request for Linear16
  RecognitionConfig config = RecognitionConfig.newBuilder()
      .setEncoding(AudioEncoding.FLAC)
      .setLanguageCode("en-US")
      .setSampleRateHertz(16000)
      .setEnableWordTimeOffsets(true)
      .build();
  RecognitionAudio audio = RecognitionAudio.newBuilder()
      .setUri(gcsUri)
      .build();

  // Use non-blocking call for getting file transcription
  OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
      speech.longRunningRecognizeAsync(config, audio);
  while (!response.isDone()) {
    System.out.println("Waiting for response...");
    Thread.sleep(10000);
  }

  List<SpeechRecognitionResult> results = response.get().getResultsList();

  for (SpeechRecognitionResult result: results) {
    // 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("Transcription: %s\n",alternative.getTranscript());
    for (WordInfo wordInfo: alternative.getWordsList()) {
      System.out.println(wordInfo.getWord());
      System.out.printf("\t%s.%s sec - %s.%s sec\n",
          wordInfo.getStartTime().getSeconds(),
          wordInfo.getStartTime().getNanos() / 100000000,
          wordInfo.getEndTime().getSeconds(),
          wordInfo.getEndTime().getNanos() / 100000000);
    }
  }
  speech.close();
}