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

Example 1 with StreamingRecognitionResult

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

the class InfiniteStreamRecognize method infiniteStreamingRecognize.

/**
 * Performs infinite streaming speech recognition
 */
public static void infiniteStreamingRecognize(String languageCode) throws Exception {
    // Microphone Input buffering
    class MicBuffer implements Runnable {

        @Override
        public void run() {
            System.out.println(YELLOW);
            System.out.println("Start speaking...Press Ctrl-C to stop");
            targetDataLine.start();
            byte[] data = new byte[BYTES_PER_BUFFER];
            while (targetDataLine.isOpen()) {
                try {
                    int numBytesRead = targetDataLine.read(data, 0, data.length);
                    if ((numBytesRead <= 0) && (targetDataLine.isOpen())) {
                        continue;
                    }
                    sharedQueue.put(data.clone());
                } catch (InterruptedException e) {
                    System.out.println("Microphone input buffering interrupted : " + e.getMessage());
                }
            }
        }
    }
    // Creating microphone input buffer thread
    MicBuffer micrunnable = new MicBuffer();
    Thread micThread = new Thread(micrunnable);
    ResponseObserver<StreamingRecognizeResponse> responseObserver = null;
    try (SpeechClient client = SpeechClient.create()) {
        ClientStream<StreamingRecognizeRequest> clientStream;
        responseObserver = new ResponseObserver<StreamingRecognizeResponse>() {

            ArrayList<StreamingRecognizeResponse> responses = new ArrayList<>();

            public void onStart(StreamController controller) {
                referenceToStreamController = controller;
            }

            public void onResponse(StreamingRecognizeResponse response) {
                responses.add(response);
                StreamingRecognitionResult result = response.getResultsList().get(0);
                Duration resultEndTime = result.getResultEndTime();
                resultEndTimeInMS = (int) ((resultEndTime.getSeconds() * 1000) + (resultEndTime.getNanos() / 1000000));
                double correctedTime = resultEndTimeInMS - bridgingOffset + (STREAMING_LIMIT * restartCounter);
                SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
                if (result.getIsFinal()) {
                    System.out.print(GREEN);
                    System.out.print("\033[2K\r");
                    System.out.printf("%s: %s [confidence: %.2f]\n", convertMillisToDate(correctedTime), alternative.getTranscript(), alternative.getConfidence());
                    isFinalEndTime = resultEndTimeInMS;
                    lastTranscriptWasFinal = true;
                } else {
                    System.out.print(RED);
                    System.out.print("\033[2K\r");
                    System.out.printf("%s: %s", convertMillisToDate(correctedTime), alternative.getTranscript());
                    lastTranscriptWasFinal = false;
                }
            }

            public void onComplete() {
            }

            public void onError(Throwable t) {
            }
        };
        clientStream = client.streamingRecognizeCallable().splitCall(responseObserver);
        RecognitionConfig recognitionConfig = RecognitionConfig.newBuilder().setEncoding(RecognitionConfig.AudioEncoding.LINEAR16).setLanguageCode(languageCode).setSampleRateHertz(16000).build();
        StreamingRecognitionConfig streamingRecognitionConfig = StreamingRecognitionConfig.newBuilder().setConfig(recognitionConfig).setInterimResults(true).build();
        StreamingRecognizeRequest request = StreamingRecognizeRequest.newBuilder().setStreamingConfig(streamingRecognitionConfig).build();
        clientStream.send(request);
        try {
            // SampleRate:16000Hz, SampleSizeInBits: 16, Number of channels: 1, Signed: true,
            // bigEndian: false
            AudioFormat audioFormat = new AudioFormat(16000, 16, 1, true, false);
            DataLine.Info targetInfo = new Info(TargetDataLine.class, // Set the system information to read from the microphone audio
            audioFormat);
            if (!AudioSystem.isLineSupported(targetInfo)) {
                System.out.println("Microphone not supported");
                System.exit(0);
            }
            // Target data line captures the audio stream the microphone produces.
            targetDataLine = (TargetDataLine) AudioSystem.getLine(targetInfo);
            targetDataLine.open(audioFormat);
            micThread.start();
            long startTime = System.currentTimeMillis();
            while (true) {
                long estimatedTime = System.currentTimeMillis() - startTime;
                if (estimatedTime >= STREAMING_LIMIT) {
                    clientStream.closeSend();
                    // remove Observer
                    referenceToStreamController.cancel();
                    if (resultEndTimeInMS > 0) {
                        finalRequestEndTime = isFinalEndTime;
                    }
                    resultEndTimeInMS = 0;
                    lastAudioInput = null;
                    lastAudioInput = audioInput;
                    audioInput = new ArrayList<ByteString>();
                    restartCounter++;
                    if (!lastTranscriptWasFinal) {
                        System.out.print('\n');
                    }
                    newStream = true;
                    clientStream = client.streamingRecognizeCallable().splitCall(responseObserver);
                    request = StreamingRecognizeRequest.newBuilder().setStreamingConfig(streamingRecognitionConfig).build();
                    System.out.println(YELLOW);
                    System.out.printf("%d: RESTARTING REQUEST\n", restartCounter * STREAMING_LIMIT);
                    startTime = System.currentTimeMillis();
                } else {
                    if ((newStream) && (lastAudioInput.size() > 0)) {
                        // if this is the first audio from a new request
                        // calculate amount of unfinalized audio from last request
                        // resend the audio to the speech client before incoming audio
                        double chunkTime = STREAMING_LIMIT / lastAudioInput.size();
                        // ms length of each chunk in previous request audio arrayList
                        if (chunkTime != 0) {
                            if (bridgingOffset < 0) {
                                // bridging Offset accounts for time of resent audio
                                // calculated from last request
                                bridgingOffset = 0;
                            }
                            if (bridgingOffset > finalRequestEndTime) {
                                bridgingOffset = finalRequestEndTime;
                            }
                            int chunksFromMs = (int) Math.floor((finalRequestEndTime - bridgingOffset) / chunkTime);
                            // chunks from MS is number of chunks to resend
                            bridgingOffset = (int) Math.floor((lastAudioInput.size() - chunksFromMs) * chunkTime);
                            // set bridging offset for next request
                            for (int i = chunksFromMs; i < lastAudioInput.size(); i++) {
                                request = StreamingRecognizeRequest.newBuilder().setAudioContent(lastAudioInput.get(i)).build();
                                clientStream.send(request);
                            }
                        }
                        newStream = false;
                    }
                    tempByteString = ByteString.copyFrom(sharedQueue.take());
                    request = StreamingRecognizeRequest.newBuilder().setAudioContent(tempByteString).build();
                    audioInput.add(tempByteString);
                }
                clientStream.send(request);
            }
        } catch (Exception e) {
            System.out.println(e);
        }
    }
}

Example 2 with StreamingRecognitionResult

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

the class Recognize method streamingMicRecognize.

// [END speech_stream_recognize_punctuation]
// [START speech_transcribe_streaming_mic]
/**
 * Performs microphone streaming speech recognition with a duration of 1 minute.
 */
public static void streamingMicRecognize() throws Exception {
    ResponseObserver<StreamingRecognizeResponse> responseObserver = null;
    try (SpeechClient client = SpeechClient.create()) {
        responseObserver = new ResponseObserver<StreamingRecognizeResponse>() {

            ArrayList<StreamingRecognizeResponse> responses = new ArrayList<>();

            public void onStart(StreamController controller) {
            }

            public void onResponse(StreamingRecognizeResponse response) {
                responses.add(response);
            }

            public void onComplete() {
                for (StreamingRecognizeResponse response : responses) {
                    StreamingRecognitionResult result = response.getResultsList().get(0);
                    SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
                    System.out.printf("Transcript : %s\n", alternative.getTranscript());
                }
            }

            public void onError(Throwable t) {
                System.out.println(t);
            }
        };
        ClientStream<StreamingRecognizeRequest> clientStream = client.streamingRecognizeCallable().splitCall(responseObserver);
        RecognitionConfig recognitionConfig = RecognitionConfig.newBuilder().setEncoding(RecognitionConfig.AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(16000).build();
        StreamingRecognitionConfig streamingRecognitionConfig = StreamingRecognitionConfig.newBuilder().setConfig(recognitionConfig).build();
        StreamingRecognizeRequest request = StreamingRecognizeRequest.newBuilder().setStreamingConfig(streamingRecognitionConfig).build();
        clientStream.send(request);
        // SampleRate:16000Hz, SampleSizeInBits: 16, Number of channels: 1, Signed: true,
        // bigEndian: false
        AudioFormat audioFormat = new AudioFormat(16000, 16, 1, true, false);
        DataLine.Info targetInfo = new Info(TargetDataLine.class, // Set the system information to read from the microphone audio stream
        audioFormat);
        if (!AudioSystem.isLineSupported(targetInfo)) {
            System.out.println("Microphone not supported");
            System.exit(0);
        }
        // Target data line captures the audio stream the microphone produces.
        TargetDataLine targetDataLine = (TargetDataLine) AudioSystem.getLine(targetInfo);
        targetDataLine.open(audioFormat);
        targetDataLine.start();
        System.out.println("Start speaking");
        long startTime = System.currentTimeMillis();
        // Audio Input Stream
        AudioInputStream audio = new AudioInputStream(targetDataLine);
        while (true) {
            long estimatedTime = System.currentTimeMillis() - startTime;
            byte[] data = new byte[6400];
            audio.read(data);
            if (estimatedTime > 60000) {
                // 60 seconds
                System.out.println("Stop speaking.");
                targetDataLine.stop();
                targetDataLine.close();
                break;
            }
            request = StreamingRecognizeRequest.newBuilder().setAudioContent(ByteString.copyFrom(data)).build();
            clientStream.send(request);
        }
    } catch (Exception e) {
        System.out.println(e);
    }
    responseObserver.onComplete();
}

Example 3 with StreamingRecognitionResult

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

the class Recognize method streamingRecognizeFile.

// [END speech_transcribe_async_gcs]
// [START speech_transcribe_streaming]
/**
 * 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 4 with StreamingRecognitionResult

use of com.google.cloud.speech.v1.StreamingRecognitionResult in project Saiy-PS by brandall76.

the class RecognitionGoogleCloud method onNext.

/**
 * Receives a value from the stream.
 * <p>
 * <p>Can be called many times but is never called after {@link #onError(Throwable)} or {@link
 * #onCompleted()} are called.
 * <p>
 * <p>Unary calls must invoke onNext at most once.  Clients may invoke onNext at most once for
 * server streaming calls, but may receive many onNext callbacks.  Servers may invoke onNext at
 * most once for client streaming calls, but may receive many onNext callbacks.
 * <p>
 * <p>If an exception is thrown by an implementation the caller is expected to terminate the
 * stream by calling {@link #onError(Throwable)} with the caught exception prior to
 * propagating it.
 *
 * @param value the value passed to the stream
 */
@Override
public void onNext(final StreamingRecognizeResponse value) {
    if (DEBUG) {
        MyLog.i(CLS_NAME, "onNext: " + TextFormat.printToString(value));
    }
    final StreamingRecognizeResponse.EndpointerType endpointerType = value.getEndpointerType();
    switch(endpointerType) {
        case START_OF_SPEECH:
            if (DEBUG) {
                MyLog.i(CLS_NAME, "onNext: START_OF_SPEECH");
            }
            if (doBeginning.get()) {
                doBeginning.set(false);
                listener.onBeginningOfSpeech();
            }
            break;
        case END_OF_SPEECH:
            if (DEBUG) {
                MyLog.i(CLS_NAME, "onNext: END_OF_SPEECH");
            }
            if (doEnd.get()) {
                doEnd.set(false);
                stopListening();
            }
            break;
        case END_OF_AUDIO:
            if (DEBUG) {
                MyLog.i(CLS_NAME, "onNext: END_OF_AUDIO");
            }
            if (doEnd.get()) {
                doEnd.set(false);
                stopListening();
            }
            break;
        case END_OF_UTTERANCE:
            if (DEBUG) {
                MyLog.i(CLS_NAME, "onNext: END_OF_UTTERANCE");
            }
            if (doEnd.get()) {
                doEnd.set(false);
                stopListening();
            }
            break;
        case UNRECOGNIZED:
            if (DEBUG) {
                MyLog.i(CLS_NAME, "onNext: UNRECOGNIZED");
            }
            break;
        case ENDPOINTER_EVENT_UNSPECIFIED:
        default:
            if (DEBUG) {
                MyLog.i(CLS_NAME, "onNext: ENDPOINTER_EVENT_UNSPECIFIED");
            }
            break;
    }
    if (doResults.get()) {
        if (UtilsList.notNaked(value.getResultsList())) {
            partialArray.clear();
            resultsArray.clear();
            confidenceArray.clear();
            bundle.clear();
            boolean isFinal = false;
            for (final StreamingRecognitionResult recognitionResult : value.getResultsList()) {
                if (DEBUG) {
                    MyLog.i(CLS_NAME, "recognitionResult stability: " + recognitionResult.getStability());
                }
                isFinal = recognitionResult.getIsFinal();
                if (DEBUG) {
                    MyLog.i(CLS_NAME, "isFinal: " + isFinal);
                }
                for (final SpeechRecognitionAlternative alternative : recognitionResult.getAlternativesList()) {
                    if (DEBUG) {
                        MyLog.i(CLS_NAME, "alternative: " + alternative.getTranscript());
                    }
                    if (isFinal) {
                        resultsArray.add(alternative.getTranscript());
                        confidenceArray.add(alternative.getConfidence());
                    } else {
                        if (partialArray.isEmpty()) {
                            partialArray.add(alternative.getTranscript());
                        } else {
                            partialArray.add(partialArray.get(0) + " " + alternative.getTranscript());
                        }
                    }
                }
            }
            doResults.set(!isFinal);
            if (isFinal) {
                bundle.putStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION, resultsArray);
                bundle.putFloatArray(SpeechRecognizer.CONFIDENCE_SCORES, ArrayUtils.toPrimitive(confidenceArray.toArray(new Float[0]), 0.0F));
                listener.onResults(bundle);
                stopListening();
            } else {
                bundle.putStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION, partialArray);
                listener.onPartialResults(bundle);
            }
        } else {
            if (DEBUG) {
                MyLog.i(CLS_NAME, "onNext: results list naked");
            }
        }
    } else {
        if (DEBUG) {
            MyLog.i(CLS_NAME, "onNext: doResults false");
        }
    }
}

Example 5 with StreamingRecognitionResult

use of com.google.cloud.speech.v1.StreamingRecognitionResult 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());
        }
    }
}