Created
October 2, 2016 22:32
-
-
Save rhulha/ab2216e6fd58976025b3c05e49afbe31 to your computer and use it in GitHub Desktop.
A small example Google Natural Language Analyzer demo client with microphone recording.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import java.io.FileOutputStream; | |
import java.io.IOException; | |
import java.util.ArrayList; | |
import java.util.HashMap; | |
import java.util.List; | |
import javax.sound.sampled.*; | |
import net.raysforge.commons.Codecs; | |
import net.raysforge.commons.Json; | |
import net.raysforge.rest.client.GenericRestClient; | |
public class SpeechClient extends GenericRestClient { | |
protected static final int SAMPLE_RATE = 16000; | |
public SpeechClient(String authToken) { | |
super("https://speech.googleapis.com/v1beta1/", null, authToken, Auth.Token); | |
} | |
public Object recordAndSyncrecognize(int seconds) throws IOException { | |
countDown(seconds); | |
return syncrecognize(Codecs.toBase64(record(seconds))); | |
} | |
public Object syncrecognize(byte[] rawAudioData) throws IOException { | |
return syncrecognize(Codecs.toBase64(rawAudioData)); | |
} | |
public Object syncrecognize(String base64StringOfRawAudioData) throws IOException { | |
List<String> phrases = new ArrayList<>(); | |
phrases.add("ctree"); | |
phrases.add("please"); | |
phrases.add("create"); | |
phrases.add("database"); | |
phrases.add("called"); | |
phrases.add("test"); | |
String phrases2 = "ctree please create database called test"; | |
HashMap<String, Object> speechContext = new HashMap<>(); | |
speechContext.put("phrases", phrases2); | |
HashMap<String, Object> config = new HashMap<>(); | |
config.put("encoding", "LINEAR16"); | |
config.put("sampleRate", 16000); | |
config.put("languageCode", "en-US"); | |
config.put("speechContext", speechContext); | |
HashMap<String, Object> audio = new HashMap<>(); | |
audio.put("content", base64StringOfRawAudioData); | |
HashMap<String, Object> request = new HashMap<>(); | |
request.put("config", config); | |
request.put("audio", audio); | |
System.out.println(Json.toJsonString(request)); | |
return postData("POST", "speech:syncrecognize", Json.toJsonString(request)); | |
} | |
public static byte[] record(int seconds) { | |
try { | |
AudioFormat googleSpeechAudioFormat = new AudioFormat(SAMPLE_RATE, 16, 1, true, false); // https://cloud.google.com/speech/reference/rest/Shared.Types/AudioEncoding | |
DataLine.Info info = new DataLine.Info(TargetDataLine.class, googleSpeechAudioFormat); | |
// checks if system supports the data line | |
if (!AudioSystem.isLineSupported(info)) { | |
System.out.println("Line not supported"); | |
System.exit(0); | |
} | |
TargetDataLine line = (TargetDataLine) AudioSystem.getLine(info); | |
line.open(googleSpeechAudioFormat); | |
line.start(); | |
AudioInputStream ais = new AudioInputStream(line); | |
byte[] b = new byte[SAMPLE_RATE * 2 * seconds]; | |
int read = ais.read(b); | |
if (read != b.length) | |
System.out.println("read != " + b.length + " " + read); | |
line.close(); | |
return b; | |
} catch (LineUnavailableException ex) { | |
ex.printStackTrace(); | |
} catch (IOException ioe) { | |
ioe.printStackTrace(); | |
} | |
return null; | |
} | |
public static void countDown(int seconds) { | |
new Thread(new Runnable() { | |
@Override | |
public void run() { | |
for(int i=seconds; i>0; i--) { | |
System.out.println(i); | |
try { | |
Thread.sleep(1000); | |
} catch (InterruptedException e) { | |
System.err.println(e.getMessage()); | |
} | |
} | |
} | |
}).start(); | |
} | |
public static void main(String[] args) throws IOException { | |
SpeechClient nlc = new SpeechClient("yourAuthToken"); | |
Object result = nlc.recordAndSyncrecognize(5); | |
System.out.println(result); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment