goxr3plus/java-google-speech-api

Official Google Cloud Speech API code

goxr3plus opened this issue · 6 comments

goxr3plus commented

@DeathStrokeAlpha @Twister21 Hello my friends , i am working with Google Cloud Speech Library so :

Here is working code Google Cloud Speech Official

Any problems you might have about setting the credentials check this stackoverflow question i did :

For some reason it has the same problem as this library , stopping after 65 seconds , google has made it like this .... gonna find a work around soon

Check this -> googleapis/google-cloud-java#3188

package googleSpeech;

import java.io.IOException;
import java.sql.Date;
import java.time.LocalDate;
import java.util.Arrays;
import java.util.HashMap;

import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.DataLine;
import javax.sound.sampled.Line;
import javax.sound.sampled.LineUnavailableException;
import javax.sound.sampled.Mixer;
import javax.sound.sampled.TargetDataLine;

import com.google.api.gax.rpc.ClientStream;
import com.google.api.gax.rpc.ResponseObserver;
import com.google.api.gax.rpc.StreamController;
import com.google.auth.oauth2.AccessToken;
import com.google.auth.oauth2.GoogleCredentials;
import com.google.cloud.speech.v1.RecognitionConfig;
import com.google.cloud.speech.v1.SpeechClient;
import com.google.cloud.speech.v1.StreamingRecognitionConfig;
import com.google.cloud.speech.v1.StreamingRecognizeRequest;
import com.google.cloud.speech.v1.StreamingRecognizeResponse;
import com.google.protobuf.ByteString;

public class GoogleSpeechTest {
	
	public GoogleSpeechTest() {
		
		//Set credentials?
		//	GoogleCredentials credentials = GoogleCredentials.create(new AccessToken("AIzaSyCtrBlhBiqNd7kI4BiOn2kWiCYlwp1azVM",Date.valueOf(LocalDate.now())));
		//	System.out.print(credentials.getAccessToken());
		
		//Target data line
		TargetDataLine microphone;
		AudioInputStream audio = null;
		
		//Check if Microphone is Supported
		checkMicrophoneAvailability();
		
		//Print available mixers
		//printAvailableMixers();
		
		//Capture Microphone Audio Data
		try {
			
			// Signed PCM AudioFormat with 16kHz, 16 bit sample size, mono
			AudioFormat format = new AudioFormat(16000, 16, 1, true, false);
			DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);
			
			//Check if Microphone is Supported
			if (!AudioSystem.isLineSupported(info)) {
				System.out.println("Microphone is not available");
				System.exit(0);
			}
			
			//Get the target data line
			microphone = (TargetDataLine) AudioSystem.getLine(info);
			microphone.open(format);
			microphone.start();
			
			//Audio Input Stream
			audio = new AudioInputStream(microphone);
			
		} catch (Exception ex) {
			ex.printStackTrace();
		}
		
		//Send audio from Microphone to Google Servers and return Text
		try (SpeechClient client = SpeechClient.create()) {
			
			ResponseObserver<StreamingRecognizeResponse> responseObserver = new ResponseObserver<StreamingRecognizeResponse>() {
				
				public void onStart(StreamController controller) {
					System.out.println("Started....");
				}
				
				public void onResponse(StreamingRecognizeResponse response) {
					System.out.println(response.getResults(0));
				}
				
				public void onComplete() {
					System.out.println("Complete");
				}
				
				public void onError(Throwable t) {
					System.err.println(t);
				}
			};
			
			ClientStream<StreamingRecognizeRequest> clientStream = client.streamingRecognizeCallable().splitCall(responseObserver);
			
			RecognitionConfig recConfig = RecognitionConfig.newBuilder().setEncoding(RecognitionConfig.AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(16000)
					.build();
			StreamingRecognitionConfig config = StreamingRecognitionConfig.newBuilder().setConfig(recConfig).build();
			
			StreamingRecognizeRequest request = StreamingRecognizeRequest.newBuilder().setStreamingConfig(config).build(); // The first request in a streaming call has to be a config
			
			clientStream.send(request);
			
			//Infinity loop from microphone
			while (true) {
				byte[] data = new byte[10];
				try {
					audio.read(data);
				} catch (IOException e) {
					System.out.println(e);
				}
				request = StreamingRecognizeRequest.newBuilder().setAudioContent(ByteString.copyFrom(data)).build();
				clientStream.send(request);
			}
		} catch (Exception e) {
			System.out.println(e);
		}
		
	}
	
	/**
	 * Checks if the Microphone is available
	 */
	public static void checkMicrophoneAvailability() {
		enumerateMicrophones().forEach((string , info) -> {
			System.out.println("Name :" + string);
		});
	}
	
	/**
	 * Generates a hashmap to simplify the microphone selection process. The keyset is the name of the audio device's Mixer The value is the first
	 * lineInfo from that Mixer.
	 * 
	 * @author Aaron Gokaslan (Skylion)
	 * @return The generated hashmap
	 */
	public static HashMap<String,Line.Info> enumerateMicrophones() {
		HashMap<String,Line.Info> out = new HashMap<String,Line.Info>();
		Mixer.Info[] mixerInfos = AudioSystem.getMixerInfo();
		for (Mixer.Info info : mixerInfos) {
			Mixer m = AudioSystem.getMixer(info);
			Line.Info[] lineInfos = m.getTargetLineInfo();
			if (lineInfos.length >= 1 && lineInfos[0].getLineClass().equals(TargetDataLine.class))//Only adds to hashmap if it is audio input device
				out.put(info.getName(), lineInfos[0]);//Please enjoy my pun
		}
		return out;
	}
	
	/**
	 * Print available mixers
	 */
	public void printAvailableMixers() {
		
		//Get available Mixers
		Mixer.Info[] mixerInfos = AudioSystem.getMixerInfo();
		
		//Print available Mixers
		Arrays.asList(mixerInfos).forEach(info -> {
			System.err.println("\n-----------Mixer--------------");
			
			Mixer mixer = AudioSystem.getMixer(info);
			
			System.err.println("\nSource Lines");
			
			//SourceLines
			Arrays.asList(mixer.getSourceLineInfo()).forEach(lineInfo -> {
				//Line Name
				System.out.println(info.getName() + "---" + lineInfo);
				Line line = null;
				try {
					line = mixer.getLine(lineInfo);
				} catch (LineUnavailableException e) {
					// TODO Auto-generated catch block
					e.printStackTrace();
				}
				System.out.println("\t-----" + line);
			});
			
			System.err.println("\nTarget Lines");
			//TargetLines
			Arrays.asList(mixer.getTargetLineInfo()).forEach(lineInfo -> {
				
				//Line Name
				System.out.println(mixer + "---" + lineInfo);
				Line line = null;
				try {
					line = mixer.getLine(lineInfo);
				} catch (LineUnavailableException e) {
					// TODO Auto-generated catch block
					e.printStackTrace();
				}
				System.out.println("\t-----" + line);
				
			});
			
		});
	}
	
	public static void main(String[] args) {
		new GoogleSpeechTest();
	}
	
}
ghshpro commented

How to use Google Speech API on Java Servlet? I need to use this for a web app (on browser). I'm using Eclipse and Tomcat as localhost. Appreciate your help.

  • 👍1
  • ❤️1
goxr3plus commented

Hmmmm you want yo stream audio from thr microphone ? The credentials will need to be configured someway too for the Servlet. To tell the truth i am experimenting these days too, so :)

ghshpro commented

@goxr3plus I've built the JAR files from your maven project. Is there anyway to just call these JAR files from a simple Servlet code? or the whole code must be modified to be compatible with Servlet?
I'm still new to Servlet. Thanks :)

goxr3plus commented
ghshpro commented
  1. How can I call your JAVA code from SERVLET then? Let's say here's my code, what should I add to call your JAVA library? (Let's say I have all your code as a JAR file in my build path)

import java.io.IOException;
import javax.servlet.ServletException;
import javax.servlet.annotation.WebServlet;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

/**
 * Servlet implementation class Test
 */
@WebServlet("/Test")
public class Test extends HttpServlet {
	private static final long serialVersionUID = 1L;
       
    /**
     * @see HttpServlet#HttpServlet()
     */
    public Test() {
        super();
        // TODO Auto-generated constructor stub
    }

	/**
	 * @see HttpServlet#doGet(HttpServletRequest request, HttpServletResponse response)
	 */
	protected void doGet(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
		// TODO Auto-generated method stub
		response.getWriter().append("Served at: ").append(request.getContextPath());
	}

	/**
	 * @see HttpServlet#doPost(HttpServletRequest request, HttpServletResponse response)
	 */
	protected void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
		// TODO Auto-generated method stub
		doGet(request, response);
	}

}
  1. In your YouTube tutorial, you said we can search for "Speech API 'Private'" on GCP. But there is no such API on the platform anymore. There's just one Google Speech API. I found a way to obtain a JSON file from GCP which contains "private_key", which is a very veryyyy long (1000+ characters) and "private_key_id" which is a 40-character key. Both don't seem to work. Maybe I'm entering it at the wrong place? Maybe you can help update the tutorial please?

FYI, here's how to get the above JSON file:

  1. In "Create Credentials" drop down, select "Service account key".
  2. Create a "service account" if you haven't yet.
  3. Select JSON and click "Create".
    Then you'll get a JSON file containing some info.

Thanks for your help, mate.

  • 👍1
goxr3plus commented