cjac
diff --git a/‎speech/README.md‎
Lines changed: 0 additions & 3 deletions b/‎speech/README.md‎
Lines changed: 0 additions & 3 deletions
diff --git a/‎speech/pom.xml‎
Lines changed: 75 additions & 0 deletions b/‎speech/pom.xml‎
Lines changed: 75 additions & 0 deletions
diff --git a/‎speech/resources/Google_Gnome.wav‎
1.7 MB b/‎speech/resources/Google_Gnome.wav‎
1.7 MB
diff --git a/‎speech/resources/audio.raw‎
56.6 KB b/‎speech/resources/audio.raw‎
56.6 KB
diff --git a/‎speech/resources/commercial_mono.wav‎
708 KB b/‎speech/resources/commercial_mono.wav‎
708 KB
diff --git a/‎speech/resources/commercial_stereo.wav‎
6.01 MB b/‎speech/resources/commercial_stereo.wav‎
6.01 MB
diff --git a/‎speech/src/main/java/com/example/speech/InfiniteStreamRecognize.java‎
Lines changed: 302 additions & 0 deletions b/‎speech/src/main/java/com/example/speech/InfiniteStreamRecognize.java‎
Lines changed: 302 additions & 0 deletions
@@ -0,0 +1,75 @@
+<?xml version='1.0' encoding='UTF-8'?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+  <modelVersion>4.0.0</modelVersion>
+  <groupId>com.example.speech</groupId>
+  <artifactId>google-cloud-speech-snippets</artifactId>
+  <packaging>jar</packaging>
+  <name>Google Cloud Speech Snippets</name>
+  <url>https://github.com/GoogleCloudPlatform/java-docs-samples/tree/main/speech</url>
+
+  <!--
+    The parent pom defines common style checks and testing strategies for our samples.
+    Removing or replacing it should not affect the execution of the samples in anyway.
+  -->
+  <parent>
+    <groupId>com.google.cloud.samples</groupId>
+    <artifactId>shared-configuration</artifactId>
+    <version>1.2.0</version>
+  </parent>
+
+  <properties>
+    <maven.compiler.target>1.8</maven.compiler.target>
+    <maven.compiler.source>1.8</maven.compiler.source>
+    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+  </properties>
+
+
+  <!-- [START speech_install_with_bom] -->
+  <dependencyManagement>
+    <dependencies>
+      <dependency>
+        <groupId>com.google.cloud</groupId>
+        <artifactId>libraries-bom</artifactId>
+        <version>26.1.3</version>
+        <type>pom</type>
+        <scope>import</scope>
+      </dependency>
+    </dependencies>
+  </dependencyManagement>
+
+  <dependencies>
+    <dependency>
+        <groupId>org.json</groupId>
+        <artifactId>json</artifactId>
+        <version>20220924</version>
+    </dependency>
+    <dependency>
+      <groupId>com.google.cloud</groupId>
+      <artifactId>google-cloud-speech</artifactId>
+    </dependency>
+    <!-- [START_EXCLUDE] -->
+    <dependency>
+      <groupId>com.google.cloud</groupId>
+      <artifactId>google-cloud-storage</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>commons-cli</groupId>
+      <artifactId>commons-cli</artifactId>
+      <version>1.5.0</version>
+    </dependency>
+    <dependency>
+      <groupId>junit</groupId>
+      <artifactId>junit</artifactId>
+      <version>4.13.2</version>
+      <scope>test</scope>
+    </dependency>
+    <dependency>
+      <groupId>com.google.truth</groupId>
+      <artifactId>truth</artifactId>
+      <version>1.1.3</version>
+      <scope>test</scope>
+    </dependency>
+    <!-- [END_EXCLUDE] -->
+  </dependencies>
+  <!-- [END speech_install_with_bom] -->
+</project>
@@ -0,0 +1,302 @@
+/*
+ * Copyright 2018 Google LLC
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package com.example.speech;
+
+// [START speech_transcribe_infinite_streaming]
+
+import com.google.api.gax.rpc.ClientStream;
+import com.google.api.gax.rpc.ResponseObserver;
+import com.google.api.gax.rpc.StreamController;
+import com.google.cloud.speech.v1p1beta1.RecognitionConfig;
+import com.google.cloud.speech.v1p1beta1.SpeechClient;
+import com.google.cloud.speech.v1p1beta1.SpeechRecognitionAlternative;
+import com.google.cloud.speech.v1p1beta1.StreamingRecognitionConfig;
+import com.google.cloud.speech.v1p1beta1.StreamingRecognitionResult;
+import com.google.cloud.speech.v1p1beta1.StreamingRecognizeRequest;
+import com.google.cloud.speech.v1p1beta1.StreamingRecognizeResponse;
+import com.google.protobuf.ByteString;
+import com.google.protobuf.Duration;
+import java.text.DecimalFormat;
+import java.util.ArrayList;
+import java.util.concurrent.BlockingQueue;
+import java.util.concurrent.LinkedBlockingQueue;
+import java.util.concurrent.TimeUnit;
+import javax.sound.sampled.AudioFormat;
+import javax.sound.sampled.AudioSystem;
+import javax.sound.sampled.DataLine;
+import javax.sound.sampled.DataLine.Info;
+import javax.sound.sampled.TargetDataLine;
+
+public class InfiniteStreamRecognize {
+
+  private static final int STREAMING_LIMIT = 290000; // ~5 minutes
+
+  public static final String RED = "\033[0;31m";
+  public static final String GREEN = "\033[0;32m";
+  public static final String YELLOW = "\033[0;33m";
+
+  // Creating shared object
+  private static volatile BlockingQueue<byte[]> sharedQueue = new LinkedBlockingQueue();
+  private static TargetDataLine targetDataLine;
+  private static int BYTES_PER_BUFFER = 6400; // buffer size in bytes
+
+  private static int restartCounter = 0;
+  private static ArrayList<ByteString> audioInput = new ArrayList<ByteString>();
+  private static ArrayList<ByteString> lastAudioInput = new ArrayList<ByteString>();
+  private static int resultEndTimeInMS = 0;
+  private static int isFinalEndTime = 0;
+  private static int finalRequestEndTime = 0;
+  private static boolean newStream = true;
+  private static double bridgingOffset = 0;
+  private static boolean lastTranscriptWasFinal = false;
+  private static StreamController referenceToStreamController;
+  private static ByteString tempByteString;
+
+  public static void main(String... args) {
+    InfiniteStreamRecognizeOptions options = InfiniteStreamRecognizeOptions.fromFlags(args);
+    if (options == null) {
+      // Could not parse.
+      System.out.println("Failed to parse options.");
+      System.exit(1);
+    }
+
+    try {
+      infiniteStreamingRecognize(options.langCode);
+    } catch (Exception e) {
+      System.out.println("Exception caught: " + e);
+    }
+  }
+
+  public static String convertMillisToDate(double milliSeconds) {
+    long millis = (long) milliSeconds;
+    DecimalFormat format = new DecimalFormat();
+    format.setMinimumIntegerDigits(2);
+    return String.format(
+        "%s:%s /",
+        format.format(TimeUnit.MILLISECONDS.toMinutes(millis)),
+        format.format(
+            TimeUnit.MILLISECONDS.toSeconds(millis)
+                - TimeUnit.MINUTES.toSeconds(TimeUnit.MILLISECONDS.toMinutes(millis))));
+  }
+
+  /** Performs infinite streaming speech recognition */
+  public static void infiniteStreamingRecognize(String languageCode) throws Exception {
+
+    // Microphone Input buffering
+    class MicBuffer implements Runnable {
+
+      @Override
+      public void run() {
+        System.out.println(YELLOW);
+        System.out.println("Start speaking...Press Ctrl-C to stop");
+        targetDataLine.start();
+        byte[] data = new byte[BYTES_PER_BUFFER];
+        while (targetDataLine.isOpen()) {
+          try {
+            int numBytesRead = targetDataLine.read(data, 0, data.length);
+            if ((numBytesRead <= 0) && (targetDataLine.isOpen())) {
+              continue;
+            }
+            sharedQueue.put(data.clone());
+          } catch (InterruptedException e) {
+            System.out.println("Microphone input buffering interrupted : " + e.getMessage());
+          }
+        }
+      }
+    }
+
+    // Creating microphone input buffer thread
+    MicBuffer micrunnable = new MicBuffer();
+    Thread micThread = new Thread(micrunnable);
+    ResponseObserver<StreamingRecognizeResponse> responseObserver = null;
+    try (SpeechClient client = SpeechClient.create()) {
+      ClientStream<StreamingRecognizeRequest> clientStream;
+      responseObserver =
+          new ResponseObserver<StreamingRecognizeResponse>() {
+
+            ArrayList<StreamingRecognizeResponse> responses = new ArrayList<>();
+
+            public void onStart(StreamController controller) {
+              referenceToStreamController = controller;
+            }
+
+            public void onResponse(StreamingRecognizeResponse response) {
+              responses.add(response);
+              StreamingRecognitionResult result = response.getResultsList().get(0);
+              Duration resultEndTime = result.getResultEndTime();
+              resultEndTimeInMS =
+                  (int)
+                      ((resultEndTime.getSeconds() * 1000) + (resultEndTime.getNanos() / 1000000));
+              double correctedTime =
+                  resultEndTimeInMS - bridgingOffset + (STREAMING_LIMIT * restartCounter);
+
+              SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
+              if (result.getIsFinal()) {
+                System.out.print(GREEN);
+                System.out.print("\033[2K\r");
+                System.out.printf(
+                    "%s: %s [confidence: %.2f]\n",
+                    convertMillisToDate(correctedTime),
+                    alternative.getTranscript(),
+                    alternative.getConfidence());
+                isFinalEndTime = resultEndTimeInMS;
+                lastTranscriptWasFinal = true;
+              } else {
+                System.out.print(RED);
+                System.out.print("\033[2K\r");
+                System.out.printf(
+                    "%s: %s", convertMillisToDate(correctedTime), alternative.getTranscript());
+                lastTranscriptWasFinal = false;
+              }
+            }
+
+            public void onComplete() {}
+
+            public void onError(Throwable t) {}
+          };
+      clientStream = client.streamingRecognizeCallable().splitCall(responseObserver);
+
+      RecognitionConfig recognitionConfig =
+          RecognitionConfig.newBuilder()
+              .setEncoding(RecognitionConfig.AudioEncoding.LINEAR16)
+              .setLanguageCode(languageCode)
+              .setSampleRateHertz(16000)
+              .build();
+
+      StreamingRecognitionConfig streamingRecognitionConfig =
+          StreamingRecognitionConfig.newBuilder()
+              .setConfig(recognitionConfig)
+              .setInterimResults(true)
+              .build();
+
+      StreamingRecognizeRequest request =
+          StreamingRecognizeRequest.newBuilder()
+              .setStreamingConfig(streamingRecognitionConfig)
+              .build(); // The first request in a streaming call has to be a config
+
+      clientStream.send(request);
+
+      try {
+        // SampleRate:16000Hz, SampleSizeInBits: 16, Number of channels: 1, Signed: true,
+        // bigEndian: false
+        AudioFormat audioFormat = new AudioFormat(16000, 16, 1, true, false);
+        DataLine.Info targetInfo =
+            new Info(
+                TargetDataLine.class,
+                audioFormat); // Set the system information to read from the microphone audio
+        // stream
+
+        if (!AudioSystem.isLineSupported(targetInfo)) {
+          System.out.println("Microphone not supported");
+          System.exit(0);
+        }
+        // Target data line captures the audio stream the microphone produces.
+        targetDataLine = (TargetDataLine) AudioSystem.getLine(targetInfo);
+        targetDataLine.open(audioFormat);
+        micThread.start();
+
+        long startTime = System.currentTimeMillis();
+
+        while (true) {
+
+          long estimatedTime = System.currentTimeMillis() - startTime;
+
+          if (estimatedTime >= STREAMING_LIMIT) {
+
+            clientStream.closeSend();
+            referenceToStreamController.cancel(); // remove Observer
+
+            if (resultEndTimeInMS > 0) {
+              finalRequestEndTime = isFinalEndTime;
+            }
+            resultEndTimeInMS = 0;
+
+            lastAudioInput = null;
+            lastAudioInput = audioInput;
+            audioInput = new ArrayList<ByteString>();
+
+            restartCounter++;
+
+            if (!lastTranscriptWasFinal) {
+              System.out.print('\n');
+            }
+
+            newStream = true;
+
+            clientStream = client.streamingRecognizeCallable().splitCall(responseObserver);
+
+            request =
+                StreamingRecognizeRequest.newBuilder()
+                    .setStreamingConfig(streamingRecognitionConfig)
+                    .build();
+
+            System.out.println(YELLOW);
+            System.out.printf("%d: RESTARTING REQUEST\n", restartCounter * STREAMING_LIMIT);
+
+            startTime = System.currentTimeMillis();
+
+          } else {
+
+            if ((newStream) && (lastAudioInput.size() > 0)) {
+              // if this is the first audio from a new request
+              // calculate amount of unfinalized audio from last request
+              // resend the audio to the speech client before incoming audio
+              double chunkTime = STREAMING_LIMIT / lastAudioInput.size();
+              // ms length of each chunk in previous request audio arrayList
+              if (chunkTime != 0) {
+                if (bridgingOffset < 0) {
+                  // bridging Offset accounts for time of resent audio
+                  // calculated from last request
+                  bridgingOffset = 0;
+                }
+                if (bridgingOffset > finalRequestEndTime) {
+                  bridgingOffset = finalRequestEndTime;
+                }
+                int chunksFromMs =
+                    (int) Math.floor((finalRequestEndTime - bridgingOffset) / chunkTime);
+                // chunks from MS is number of chunks to resend
+                bridgingOffset =
+                    (int) Math.floor((lastAudioInput.size() - chunksFromMs) * chunkTime);
+                // set bridging offset for next request
+                for (int i = chunksFromMs; i < lastAudioInput.size(); i++) {
+                  request =
+                      StreamingRecognizeRequest.newBuilder()
+                          .setAudioContent(lastAudioInput.get(i))
+                          .build();
+                  clientStream.send(request);
+                }
+              }
+              newStream = false;
+            }
+
+            tempByteString = ByteString.copyFrom(sharedQueue.take());
+
+            request =
+                StreamingRecognizeRequest.newBuilder().setAudioContent(tempByteString).build();
+
+            audioInput.add(tempByteString);
+          }
+
+          clientStream.send(request);
+        }
+      } catch (Exception e) {
+        System.out.println(e);
+      }
+    }
+  }
+}
+// [END speech_transcribe_infinite_streaming]