Examples with SpeechRecognitionAlternative com.google.cloud.videointelligence.v1.SpeechRecognitionAlternative used on opensource projects

Example 41 with SpeechRecognitionAlternative

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

the class Recognize method syncRecognizeFile.

// [START speech_transcribe_sync]
/**
 * 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 42 with SpeechRecognitionAlternative

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

the class Recognize method streamingTranscribeWithAutomaticPunctuation.

// [END speech_transcribe_auto_punctuation]
// [START speech_stream_recognize_punctuation]
/**
 * Performs streaming speech recognition on raw PCM audio data.
 *
 * @param fileName the path to a PCM audio file to transcribe.
 */
public static void streamingTranscribeWithAutomaticPunctuation(String fileName) throws Exception {
    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).setEnableAutomaticPunctuation(true).build();
        // Build the streaming config with the audio config
        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 43 with SpeechRecognitionAlternative

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

the class Recognize method syncRecognizeGcs.

// [START speech_transcribe_sync_gcs]
/**
 * 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 {
    // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
    try (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());
        }
    }
}

Example 44 with SpeechRecognitionAlternative

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

the class RecognizeBeta method transcribeDiarization.

// [END speech_transcribe_recognition_metadata_beta]
// [START speech_transcribe_diarization_beta]
/**
 * Transcribe the given audio file using speaker diarization.
 *
 * @param fileName the path to an audio file.
 */
public static void transcribeDiarization(String fileName) throws Exception {
    Path path = Paths.get(fileName);
    byte[] content = Files.readAllBytes(path);
    try (SpeechClient speechClient = SpeechClient.create()) {
        // Get the contents of the local audio file
        RecognitionAudio recognitionAudio = RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();
        SpeakerDiarizationConfig speakerDiarizationConfig = SpeakerDiarizationConfig.newBuilder().setEnableSpeakerDiarization(true).setMinSpeakerCount(2).setMaxSpeakerCount(2).build();
        // Configure request to enable Speaker diarization
        RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(8000).setDiarizationConfig(speakerDiarizationConfig).build();
        // Perform the transcription request
        RecognizeResponse recognizeResponse = speechClient.recognize(config, recognitionAudio);
        // Speaker Tags are only included in the last result object, which has only one alternative.
        SpeechRecognitionAlternative alternative = recognizeResponse.getResults(recognizeResponse.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 45 with SpeechRecognitionAlternative

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

the class RecognizeBeta method transcribeWordLevelConfidenceGcs.

// [END speech_transcribe_word_level_confidence_beta]
// [START speech_transcribe_word_level_confidence_gcs_beta]
/**
 * Transcribe a remote audio file with word level confidence
 *
 * @param gcsUri path to the remote audio file
 */
public static void transcribeWordLevelConfidenceGcs(String gcsUri) throws Exception {
    try (SpeechClient speechClient = SpeechClient.create()) {
        // Configure request to enable word level confidence
        RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.FLAC).setSampleRateHertz(44100).setLanguageCode("en-US").setEnableWordConfidence(true).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> response = speechClient.longRunningRecognizeAsync(config, audio);
        while (!response.isDone()) {
            System.out.println("Waiting for response...");
            Thread.sleep(10000);
        }
        // Just print the first result here.
        SpeechRecognitionResult result = response.get().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);
        // Print out the result
        System.out.printf("Transcript : %s\n", alternative.getTranscript());
        System.out.format("First Word and Confidence : %s %s \n", alternative.getWords(0).getWord(), alternative.getWords(0).getConfidence());
    }
}