Trabalhar com Amazon Transcribe

O exemplo a seguir mostra como o streaming bidirecional funciona usando o Amazon Transcribe. O streaming bidirecional indica que há um streaming de dados que vai para o serviço e que é recebido de volta em tempo real. O exemplo usa o transcrição de streaming do Amazon Transcribe para enviar um streaming de áudio e receber um streaming de texto transcrito em tempo real.

Consulte Transcrição de streaming no Guia do desenvolvedor do Amazon Transcribe para saber mais sobre esse recurso.

Consulte Conceitos básicos no Guia do desenvolvedor do Amazon Transcribe para começar a usar o Amazon Transcribe.

Configurar o microfone

Esse código usa o pacote javax.sound.sampled para fazer streaming de áudio de um dispositivo de entrada.

Código

import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.DataLine;
import javax.sound.sampled.TargetDataLine;

public class Microphone {

    public static TargetDataLine get() throws Exception {
        AudioFormat format = new AudioFormat(16000, 16, 1, true, false);
        DataLine.Info datalineInfo = new DataLine.Info(TargetDataLine.class, format);

        TargetDataLine dataLine = (TargetDataLine) AudioSystem.getLine(datalineInfo);
        dataLine.open(format);

        return dataLine;
    }
}

Veja o exemplo completo no GitHub.

Criar um publicador

Esse código implementa um editor que publica dados de áudio do streaming de áudio do Amazon Transcribe.

Código

package com.amazonaws.transcribe;

import java.io.IOException;
import java.io.InputStream;
import java.io.UncheckedIOException;
import java.nio.ByteBuffer;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.atomic.AtomicLong;
import org.reactivestreams.Publisher;
import org.reactivestreams.Subscriber;
import org.reactivestreams.Subscription;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.services.transcribestreaming.model.AudioEvent;
import software.amazon.awssdk.services.transcribestreaming.model.AudioStream;
import software.amazon.awssdk.services.transcribestreaming.model.TranscribeStreamingException;


public class AudioStreamPublisher implements Publisher<AudioStream> {
    private final InputStream inputStream;

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

    @Override
    public void subscribe(Subscriber<? super AudioStream> s) {
        s.onSubscribe(new SubscriptionImpl(s, inputStream));
    }

    private class SubscriptionImpl implements Subscription {
        private static final int CHUNK_SIZE_IN_BYTES = 1024 * 1;
        private ExecutorService executor = Executors.newFixedThreadPool(1);
        private AtomicLong demand = new AtomicLong(0);

        private final Subscriber<? super AudioStream> subscriber;
        private final InputStream inputStream;

        private 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 (TranscribeStreamingException e) {
                    subscriber.onError(e);
                }
            });
        }

        @Override
        public void cancel() {

        }

        private ByteBuffer getNextEvent() {
            ByteBuffer audioBuffer;
            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();
        }
    }
}

Veja o exemplo completo no GitHub.

Criar o cliente e iniciar o streaming

No método principal, crie um objeto de solicitação, inicie o streaming da entrada de áudio e instancie o editor com a entrada de áudio.

Você também deve criar um StartStreamTranscriptionResponseHandler para especificar como lidar com a resposta do Amazon Transcribe.

Depois, use o método startStreamTranscription de TranscribeStreamingAsyncClient para iniciar o streaming bidirecional.

Importações

import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.DataLine;
import javax.sound.sampled.TargetDataLine;
import javax.sound.sampled.AudioInputStream;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.transcribestreaming.TranscribeStreamingAsyncClient;
import software.amazon.awssdk.services.transcribestreaming.model.TranscribeStreamingException ;
import software.amazon.awssdk.services.transcribestreaming.model.StartStreamTranscriptionRequest;
import software.amazon.awssdk.services.transcribestreaming.model.MediaEncoding;
import software.amazon.awssdk.services.transcribestreaming.model.LanguageCode;
import software.amazon.awssdk.services.transcribestreaming.model.StartStreamTranscriptionResponseHandler;
import software.amazon.awssdk.services.transcribestreaming.model.TranscriptEvent;

Código

    public static void convertAudio(TranscribeStreamingAsyncClient client) throws Exception {

        try {

            StartStreamTranscriptionRequest request = StartStreamTranscriptionRequest.builder()
                    .mediaEncoding(MediaEncoding.PCM)
                    .languageCode(LanguageCode.EN_US)
                    .mediaSampleRateHertz(16_000).build();

            TargetDataLine mic = Microphone.get();
            mic.start();

            AudioStreamPublisher publisher = new AudioStreamPublisher(new AudioInputStream(mic));

            StartStreamTranscriptionResponseHandler response =
                    StartStreamTranscriptionResponseHandler.builder().subscriber(e -> {
                        TranscriptEvent event = (TranscriptEvent) e;
                        event.transcript().results().forEach(r -> r.alternatives().forEach(a -> System.out.println(a.transcript())));
                    }).build();

            // Keeps Streaming until you end the Java program
            client.startStreamTranscription(request, publisher, response);

        } catch (TranscribeStreamingException e) {
            System.err.println(e.awsErrorDetails().errorMessage());
            System.exit(1);
         }
    }

Veja o exemplo completo no GitHub.

Mais informações

• Como funciona no Guia do desenvolvedor do Amazon Transcribe.

• Conceitos básicos do streaming de áudio no Guia do desenvolvedor do Amazon Transcribe.