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

Example 11 with SpeechRecognitionAlternative

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

the class RecognizeBeta method transcribeMultiChannel.

// [END speech_transcribe_diarization_gcs_beta]
// [START speech_transcribe_multichannel_beta]
/**
 * Transcribe a local audio file with multi-channel recognition
 *
 * @param fileName the path to local audio file
 */
public static void transcribeMultiChannel(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();
        // Configure request to enable multiple channels
        RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(44100).setAudioChannelCount(2).setEnableSeparateRecognitionPerChannel(true).build();
        // Perform the transcription request
        RecognizeResponse recognizeResponse = speechClient.recognize(config, recognitionAudio);
        // Print out the results
        for (SpeechRecognitionResult result : recognizeResponse.getResultsList()) {
            // There can be several alternative transcripts for a given chunk of speech. Just use the
            // first (most likely) one here.
            SpeechRecognitionAlternative alternative = result.getAlternatives(0);
            System.out.format("Transcript : %s\n", alternative.getTranscript());
            System.out.printf("Channel Tag : %s\n\n", result.getChannelTag());
        }
    }
}

Example 12 with SpeechRecognitionAlternative

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

the class RecognizeBeta method transcribeFileWithMetadata.

// [START speech_transcribe_recognition_metadata_beta]
/**
 * Transcribe the given audio file and include recognition metadata in the request.
 *
 * @param fileName the path to an audio file.
 */
public static void transcribeFileWithMetadata(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();
        // Construct a recognition metadata object.
        // Most metadata fields are specified as enums that can be found
        // in speech.enums.RecognitionMetadata
        RecognitionMetadata metadata = RecognitionMetadata.newBuilder().setInteractionType(InteractionType.DISCUSSION).setMicrophoneDistance(MicrophoneDistance.NEARFIELD).setRecordingDeviceType(RecordingDeviceType.SMARTPHONE).setRecordingDeviceName(// Some metadata fields are free form strings
        "Pixel 2 XL").setIndustryNaicsCodeOfAudio(519190).build();
        // Configure request to enable enhanced models
        RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(8000).setMetadata(// Add the metadata to the config
        metadata).build();
        // Perform the transcription request
        RecognizeResponse recognizeResponse = speechClient.recognize(config, recognitionAudio);
        // Print out the results
        for (SpeechRecognitionResult result : recognizeResponse.getResultsList()) {
            // There can be several alternative transcripts for a given chunk of speech. Just use the
            // first (most likely) one here.
            SpeechRecognitionAlternative alternative = result.getAlternatives(0);
            System.out.format("Transcript: %s\n\n", alternative.getTranscript());
        }
    }
}

Example 13 with SpeechRecognitionAlternative

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

the class RecognizeBeta method transcribeMultiChannelGcs.

// [END speech_transcribe_multichannel_beta]
// [START speech_transcribe_multichannel_gcs_beta]
/**
 * Transcribe a remote audio file with multi-channel recognition
 *
 * @param gcsUri the path to the audio file
 */
public static void transcribeMultiChannelGcs(String gcsUri) throws Exception {
    try (SpeechClient speechClient = SpeechClient.create()) {
        // Configure request to enable multiple channels
        RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(44100).setAudioChannelCount(2).setEnableSeparateRecognitionPerChannel(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.
        for (SpeechRecognitionResult result : response.get().getResultsList()) {
            // 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.printf("Channel Tag : %s\n\n", result.getChannelTag());
        }
    }
}

Example 14 with SpeechRecognitionAlternative

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

the class RecognizeBeta method transcribeDiarizationGcs.

// [END speech_transcribe_diarization_beta]
// [START speech_transcribe_diarization_gcs_beta]
/**
 * Transcribe a remote audio file using speaker diarization.
 *
 * @param gcsUri the path to an audio file.
 */
public static void transcribeDiarizationGcs(String gcsUri) throws Exception {
    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(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> response = speechClient.longRunningRecognizeAsync(config, audio);
        while (!response.isDone()) {
            System.out.println("Waiting for response...");
            Thread.sleep(10000);
        }
        // Speaker Tags are only included in the last result object, which has only one alternative.
        LongRunningRecognizeResponse longRunningRecognizeResponse = response.get();
        SpeechRecognitionAlternative alternative = longRunningRecognizeResponse.getResults(longRunningRecognizeResponse.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 15 with SpeechRecognitionAlternative

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

the class RecognizeBeta method transcribeMultiLanguageGcs.

// [END speech_transcribe_multilanguage_beta]
// [START speech_transcribe_multilanguage_gcs_beta]
/**
 * Transcribe a remote audio file with multi-language recognition
 *
 * @param gcsUri the path to the remote audio file
 */
public static void transcribeMultiLanguageGcs(String gcsUri) throws Exception {
    try (SpeechClient speechClient = SpeechClient.create()) {
        ArrayList<String> languageList = new ArrayList<>();
        languageList.add("es-ES");
        languageList.add("en-US");
        // Configure request to enable multiple languages
        RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setSampleRateHertz(16000).setLanguageCode("ja-JP").addAllAlternativeLanguageCodes(languageList).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);
        }
        for (SpeechRecognitionResult result : response.get().getResultsList()) {
            // 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\n", alternative.getTranscript());
        }
    }
}