StartMedicalStreamTranscription搭配使用 AWS SDK

/*
To run this AWS code example, ensure that you have set up your development
 environment, including your AWS credentials.

 For information, see this documentation topic:

 https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html

This code demonstrates the process of starting a medical transcription job using the AWS Transcribe
Streaming service, including setting up the audio input stream, configuring the transcription request,
and handling the transcription response.
 */

public class TranscribeMedicalStreamingDemoApp {
    private static TranscribeStreamingAsyncClient client;

    public static void main(String args[])
        throws ExecutionException, InterruptedException, LineUnavailableException {

        client = TranscribeStreamingAsyncClient.builder()
            .credentialsProvider(getCredentials())
            .build();

        CompletableFuture<Void> result = client.startMedicalStreamTranscription(getMedicalRequest(16_000),
            new AudioStreamPublisher(getStreamFromMic()),
            getMedicalResponseHandler());

        result.get();
        client.close();
    }

    private static InputStream getStreamFromMic() throws LineUnavailableException {

        // Signed PCM AudioFormat with 16kHz, 16 bit sample size, mono
        int sampleRate = 16000;
        AudioFormat format = new AudioFormat(sampleRate, 16, 1, true, false);
        DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);

        if (!AudioSystem.isLineSupported(info)) {
            System.out.println("Line not supported");
            throw new LineUnavailableException("The audio system microphone line is not supported.");
        }

        TargetDataLine line = (TargetDataLine) AudioSystem.getLine(info);
        line.open(format);
        line.start();

        InputStream audioStream = new AudioInputStream(line);
        return audioStream;
    }

    private static AwsCredentialsProvider getCredentials() {
        return DefaultCredentialsProvider.create();
    }

    private static StartMedicalStreamTranscriptionRequest getMedicalRequest(Integer mediaSampleRateHertz) {
        return StartMedicalStreamTranscriptionRequest.builder()
            .languageCode(LanguageCode.EN_US.toString()) // For medical transcription, EN_US is typically used.
            .mediaEncoding(MediaEncoding.PCM)
            .mediaSampleRateHertz(mediaSampleRateHertz)
            .specialty(Specialty.PRIMARYCARE) // Specify the medical specialty.
            .type(Type.CONVERSATION) // Set the type as CONVERSATION or DICTATION.
            .build();
    }

    private static StartMedicalStreamTranscriptionResponseHandler getMedicalResponseHandler() {
        return StartMedicalStreamTranscriptionResponseHandler.builder()
            .onResponse(r -> {
                System.out.println("Received Initial response");
            })
            .onError(e -> {
                System.out.println(e.getMessage());
                StringWriter sw = new StringWriter();
                e.printStackTrace(new PrintWriter(sw));
                System.out.println("Error Occurred: " + sw.toString());
            })
            .onComplete(() -> {
                System.out.println("=== All records streamed successfully ===");
            })
            .subscriber(event -> {
                List<MedicalResult> results = ((MedicalTranscriptEvent) event).transcript().results();
                if (results.size() > 0) {
                    if (!results.get(0).alternatives().get(0).transcript().isEmpty()) {
                        System.out.println(results.get(0).alternatives().get(0).transcript());
                    }
                }
            })
            .build();
    }

    private static class AudioStreamPublisher implements Publisher<AudioStream> {
        private final InputStream inputStream;
        private static Subscription currentSubscription;

        private AudioStreamPublisher(InputStream inputStream) {
            this.inputStream = inputStream;
        }

        @Override
        public void subscribe(Subscriber<? super AudioStream> s) {

            if (this.currentSubscription == null) {
                this.currentSubscription = new SubscriptionImpl(s, inputStream);
            } else {
                this.currentSubscription.cancel();
                this.currentSubscription = new SubscriptionImpl(s, inputStream);
            }
            s.onSubscribe(currentSubscription);
        }
    }

    public static class SubscriptionImpl implements Subscription {
        private static final int CHUNK_SIZE_IN_BYTES = 1024 * 1;
        private final Subscriber<? super AudioStream> subscriber;
        private final InputStream inputStream;
        private ExecutorService executor = Executors.newFixedThreadPool(1);
        private AtomicLong demand = new AtomicLong(0);

        SubscriptionImpl(Subscriber<? super AudioStream> s, InputStream inputStream) {
            this.subscriber = s;
            this.inputStream = inputStream;
        }

        @Override
        public void request(long n) {
            if (n <= 0) {
                subscriber.onError(new IllegalArgumentException("Demand must be positive"));
            }

            demand.getAndAdd(n);
            executor.submit(() -> {
                try {
                    do {
                        ByteBuffer audioBuffer = getNextEvent();
                        if (audioBuffer.remaining() > 0) {
                            AudioEvent audioEvent = audioEventFromBuffer(audioBuffer);
                            subscriber.onNext(audioEvent);
                        } else {
                            subscriber.onComplete();
                            break;
                        }
                    } while (demand.decrementAndGet() > 0);
                } catch (Exception e) {
                    subscriber.onError(e);
                }
            });
        }

        @Override
        public void cancel() {
            executor.shutdown();
        }

        private ByteBuffer getNextEvent() {
            ByteBuffer audioBuffer = null;
            byte[] audioBytes = new byte[CHUNK_SIZE_IN_BYTES];

            int len = 0;
            try {
                len = inputStream.read(audioBytes);

                if (len <= 0) {
                    audioBuffer = ByteBuffer.allocate(0);
                } else {
                    audioBuffer = ByteBuffer.wrap(audioBytes, 0, len);
                }
            } catch (IOException e) {
                throw new UncheckedIOException(e);
            }

            return audioBuffer;
        }

        private AudioEvent audioEventFromBuffer(ByteBuffer bb) {
            return AudioEvent.builder()
                .audioChunk(SdkBytes.fromByteBuffer(bb))
                .build();
        }
    }
}