Examples with SpeechRecognitionAlternative com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative used on opensource projects

Example 11 with SpeechRecognitionAlternative

use of com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative in project java-docs-samples by GoogleCloudPlatform.

the class Recognize method streamingRecognizeFile.

/**
 * Performs streaming speech recognition on raw PCM audio data.
 *
 * @param fileName the path to a PCM audio file to transcribe.
 */
public static void streamingRecognizeFile(String fileName) throws Exception, IOException {
    Path path = Paths.get(fileName);
    byte[] data = Files.readAllBytes(path);
    // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
    try (SpeechClient speech = SpeechClient.create()) {
        // Configure request with local raw PCM audio
        RecognitionConfig recConfig = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(16000).setModel("default").build();
        StreamingRecognitionConfig config = StreamingRecognitionConfig.newBuilder().setConfig(recConfig).build();
        class ResponseApiStreamingObserver<T> implements ApiStreamObserver<T> {

            private final SettableFuture<List<T>> future = SettableFuture.create();

            private final List<T> messages = new java.util.ArrayList<T>();

            @Override
            public void onNext(T message) {
                messages.add(message);
            }

            @Override
            public void onError(Throwable t) {
                future.setException(t);
            }

            @Override
            public void onCompleted() {
                future.set(messages);
            }

            // Returns the SettableFuture object to get received messages / exceptions.
            public SettableFuture<List<T>> future() {
                return future;
            }
        }
        ResponseApiStreamingObserver<StreamingRecognizeResponse> responseObserver = new ResponseApiStreamingObserver<>();
        BidiStreamingCallable<StreamingRecognizeRequest, StreamingRecognizeResponse> callable = speech.streamingRecognizeCallable();
        ApiStreamObserver<StreamingRecognizeRequest> requestObserver = callable.bidiStreamingCall(responseObserver);
        // The first request must **only** contain the audio configuration:
        requestObserver.onNext(StreamingRecognizeRequest.newBuilder().setStreamingConfig(config).build());
        // Subsequent requests must **only** contain the audio data.
        requestObserver.onNext(StreamingRecognizeRequest.newBuilder().setAudioContent(ByteString.copyFrom(data)).build());
        // Mark transmission as completed after sending the data.
        requestObserver.onCompleted();
        List<StreamingRecognizeResponse> responses = responseObserver.future().get();
        for (StreamingRecognizeResponse response : responses) {
            // For streaming recognize, the results list has one is_final result (if available) followed
            // by a number of in-progress results (if iterim_results is true) for subsequent utterances.
            // Just print the first result here.
            StreamingRecognitionResult result = response.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());
        }
    }
}

Example 12 with SpeechRecognitionAlternative

use of com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative in project java-docs-samples by GoogleCloudPlatform.

the class Detect method speechTranscription.

// [END video_face_emotions]
// [START video_speech_transcription]
/**
 * Transcribe speech from a video stored on GCS.
 *
 * @param gcsUri the path to the video file to analyze.
 */
public static void speechTranscription(String gcsUri) throws Exception {
    // Instantiate a com.google.cloud.videointelligence.v1p1beta1.VideoIntelligenceServiceClient
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
        // Set the language code
        SpeechTranscriptionConfig config = SpeechTranscriptionConfig.newBuilder().setLanguageCode("en-US").build();
        // Set the video context with the above configuration
        VideoContext context = VideoContext.newBuilder().setSpeechTranscriptionConfig(config).build();
        // Create the request
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).addFeatures(Feature.SPEECH_TRANSCRIPTION).setVideoContext(context).build();
        // asynchronously perform facial analysis on videos
        OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> response = client.annotateVideoAsync(request);
        System.out.println("Waiting for operation to complete...");
        // Display the results
        for (VideoAnnotationResults results : response.get(180, TimeUnit.SECONDS).getAnnotationResultsList()) {
            for (SpeechTranscription speechTranscription : results.getSpeechTranscriptionsList()) {
                try {
                    // Print the transcription
                    if (speechTranscription.getAlternativesCount() > 0) {
                        SpeechRecognitionAlternative alternative = speechTranscription.getAlternatives(0);
                        System.out.printf("Transcript: %s\n", alternative.getTranscript());
                        System.out.printf("Confidence: %.2f\n", alternative.getConfidence());
                        System.out.println("Word level information:");
                        for (WordInfo wordInfo : alternative.getWordsList()) {
                            double startTime = wordInfo.getStartTime().getSeconds() + wordInfo.getStartTime().getNanos() / 1e9;
                            double endTime = wordInfo.getEndTime().getSeconds() + wordInfo.getEndTime().getNanos() / 1e9;
                            System.out.printf("\t%4.2fs - %4.2fs: %s\n", startTime, endTime, wordInfo.getWord());
                        }
                    } else {
                        System.out.println("No transcription found");
                    }
                } catch (IndexOutOfBoundsException ioe) {
                    System.out.println("Could not retrieve frame: " + ioe.getMessage());
                }
            }
        }
    }
}

Example 13 with SpeechRecognitionAlternative

use of com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative in project google-cloud-java by GoogleCloudPlatform.

the class RecognizeSpeech method main.

public static void main(String... args) throws Exception {
    // Instantiates a client
    SpeechClient speech = SpeechClient.create();
    // The path to the audio file to transcribe
    // for example "./resources/audio.raw";
    String fileName = "your/speech/audio/file.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) {
        List<SpeechRecognitionAlternative> alternatives = result.getAlternativesList();
        for (SpeechRecognitionAlternative alternative : alternatives) {
            System.out.printf("Transcription: %s%n", alternative.getTranscript());
        }
    }
    speech.close();
}