Examples with RecognizeResponse com.google.cloud.speech.v1p1beta1.RecognizeResponse used on opensource projects

Example 1 with RecognizeResponse

use of com.google.cloud.speech.v1p1beta1.RecognizeResponse in project google-cloud-java by GoogleCloudPlatform.

the class SpeechClientTest method recognizeTest.

@Test
@SuppressWarnings("all")
public void recognizeTest() {
    RecognizeResponse expectedResponse = RecognizeResponse.newBuilder().build();
    mockSpeech.addResponse(expectedResponse);
    RecognitionConfig.AudioEncoding encoding = RecognitionConfig.AudioEncoding.FLAC;
    int sampleRateHertz = 44100;
    String languageCode = "en-US";
    RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(encoding).setSampleRateHertz(sampleRateHertz).setLanguageCode(languageCode).build();
    String uri = "gs://bucket_name/file_name.flac";
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(uri).build();
    RecognizeResponse actualResponse = client.recognize(config, audio);
    Assert.assertEquals(expectedResponse, actualResponse);
    List<GeneratedMessageV3> actualRequests = mockSpeech.getRequests();
    Assert.assertEquals(1, actualRequests.size());
    RecognizeRequest actualRequest = (RecognizeRequest) actualRequests.get(0);
    Assert.assertEquals(config, actualRequest.getConfig());
    Assert.assertEquals(audio, actualRequest.getAudio());
}

Example 2 with RecognizeResponse

use of com.google.cloud.speech.v1p1beta1.RecognizeResponse in project java-docs-samples by GoogleCloudPlatform.

the class QuickstartSample method main.

/**
 * Demonstrates using the Speech API to transcribe an audio file.
 */
public static void main(String... args) throws Exception {
    // Instantiates a client
    try (SpeechClient speechClient = 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 = speechClient.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());
        }
    }
}

Example 3 with RecognizeResponse

use of com.google.cloud.speech.v1p1beta1.RecognizeResponse in project java-docs-samples by GoogleCloudPlatform.

the class Recognize method syncRecognizeFile.

/**
 * 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 {
    try (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());
        }
    }
}

Example 4 with RecognizeResponse

use of com.google.cloud.speech.v1p1beta1.RecognizeResponse in project java-docs-samples by GoogleCloudPlatform.

the class Recognize method transcribeModelSelection.

// [START speech_transcribe_model_selection]
/**
 * Performs transcription of the given audio file synchronously with
 * the selected model.
 * @param fileName the path to a audio file to transcribe
 */
public static void transcribeModelSelection(String fileName) throws Exception {
    Path path = Paths.get(fileName);
    byte[] content = Files.readAllBytes(path);
    try (SpeechClient speech = SpeechClient.create()) {
        // Configure request with video media type
        RecognitionConfig recConfig = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(16000).setModel("video").build();
        RecognitionAudio recognitionAudio = RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();
        RecognizeResponse recognizeResponse = speech.recognize(recConfig, recognitionAudio);
        // Just print the first result here.
        SpeechRecognitionResult result = recognizeResponse.getResultsList().get(0);
        // 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("Transcript : %s\n", alternative.getTranscript());
    }
// [END speech_transcribe_model_selection]
}

Example 5 with RecognizeResponse

use of com.google.cloud.speech.v1p1beta1.RecognizeResponse in project java-docs-samples by GoogleCloudPlatform.

the class Recognize method syncRecognizeWords.

/**
 * 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 {
    try (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);
            }
        }
    }
}