Examples with LongRunningRecognizeMetadata com.google.cloud.speech.v1.LongRunningRecognizeMetadata used on opensource projects

Example 6 with LongRunningRecognizeMetadata

use of com.google.cloud.speech.v1.LongRunningRecognizeMetadata in project java-speech by googleapis.

the class TranscribeDiarizationGcs method transcribeDiarizationGcs.

// Transcribe the give gcs file using speaker diarization
public static void transcribeDiarizationGcs(String gcsUri) throws IOException, ExecutionException, InterruptedException {
    // the "close" method on the client to safely clean up any remaining background resources.
    try (SpeechClient speechClient = SpeechClient.create()) {
        SpeakerDiarizationConfig speakerDiarizationConfig = SpeakerDiarizationConfig.newBuilder().setEnableSpeakerDiarization(true).setMinSpeakerCount(2).setMaxSpeakerCount(2).build();
        // Configure request to enable Speaker diarization
        RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(RecognitionConfig.AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(8000).setDiarizationConfig(speakerDiarizationConfig).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> future = speechClient.longRunningRecognizeAsync(config, audio);
        System.out.println("Waiting for response...");
        // Speaker Tags are only included in the last result object, which has only one alternative.
        LongRunningRecognizeResponse response = future.get();
        SpeechRecognitionAlternative alternative = response.getResults(response.getResultsCount() - 1).getAlternatives(0);
        // The alternative is made up of WordInfo objects that contain the speaker_tag.
        WordInfo wordInfo = alternative.getWords(0);
        int currentSpeakerTag = wordInfo.getSpeakerTag();
        // For each word, get all the words associated with one speaker, once the speaker changes,
        // add a new line with the new speaker and their spoken words.
        StringBuilder speakerWords = new StringBuilder(String.format("Speaker %d: %s", wordInfo.getSpeakerTag(), wordInfo.getWord()));
        for (int i = 1; i < alternative.getWordsCount(); i++) {
            wordInfo = alternative.getWords(i);
            if (currentSpeakerTag == wordInfo.getSpeakerTag()) {
                speakerWords.append(" ");
                speakerWords.append(wordInfo.getWord());
            } else {
                speakerWords.append(String.format("\nSpeaker %d: %s", wordInfo.getSpeakerTag(), wordInfo.getWord()));
                currentSpeakerTag = wordInfo.getSpeakerTag();
            }
        }
        System.out.println(speakerWords.toString());
    }
}

Example 7 with LongRunningRecognizeMetadata

use of com.google.cloud.speech.v1.LongRunningRecognizeMetadata in project java-docs-samples by GoogleCloudPlatform.

the class Recognize method asyncRecognizeGcs.

/**
 * 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 {
    // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
    try (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());
        }
    }
}

Example 8 with LongRunningRecognizeMetadata

use of com.google.cloud.speech.v1.LongRunningRecognizeMetadata in project java-docs-samples by GoogleCloudPlatform.

the class Recognize method transcribeModelSelectionGcs.

// [START speech_transcribe_model_selection_gcs]
/**
 * Performs transcription of the remote audio file asynchronously with
 * the selected model.
 * @param gcsUri the path to the remote audio file to transcribe.
 */
public static void transcribeModelSelectionGcs(String gcsUri) throws Exception {
    try (SpeechClient speech = SpeechClient.create()) {
        // Configure request with video media type
        RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(16000).setModel("video").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();
        // Just print the first result here.
        SpeechRecognitionResult result = results.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_gcs]
}

Example 9 with LongRunningRecognizeMetadata

use of com.google.cloud.speech.v1.LongRunningRecognizeMetadata in project java-docs-samples by GoogleCloudPlatform.

the class Recognize method asyncRecognizeWords.

/**
 * 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 {
    // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
    try (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);
            }
        }
    }
}

Example 10 with LongRunningRecognizeMetadata

use of com.google.cloud.speech.v1.LongRunningRecognizeMetadata in project java-docs-samples by GoogleCloudPlatform.

the class Recognize method asyncRecognizeFile.

/**
 * Performs non-blocking speech recognition on raw PCM audio and prints
 * the transcription. Note that transcription is limited to 60 seconds audio.
 *
 * @param fileName the path to a PCM audio file to transcribe.
 */
public static void asyncRecognizeFile(String fileName) throws Exception {
    // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
    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 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());
        }
    }
}