v2.0 java (#295)

.github/workflows/java-demos.yml

@@ -26,14 +26,15 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
+        java-version: ['11', '17', '19']
 
     steps:
     - uses: actions/checkout@v3
 
-    - name: Set up JDK 11
+    - name: Set up JDK ${{ matrix.java-version }}
       uses: actions/setup-java@v3
       with:
-        java-version: '11'
+        java-version: ${{ matrix.java-version }}
         distribution: 'temurin'
 
     - name: Build

.github/workflows/java-perf.yml

@@ -31,13 +31,13 @@ jobs:
         os: [ubuntu-latest, macos-latest, windows-latest]
         include:
         - os: ubuntu-latest
-          init_performance_threshold_sec: 2.0
-          proc_performance_threshold_sec: 0.7
-        - os: windows-latest
-          init_performance_threshold_sec: 2.5
+          init_performance_threshold_sec: 4.0
           proc_performance_threshold_sec: 0.9
         - os: macos-latest
-          init_performance_threshold_sec: 2.4
+          init_performance_threshold_sec: 4.5
+          proc_performance_threshold_sec: 1.9
+        - os: windows-latest
+          init_performance_threshold_sec: 4.0
           proc_performance_threshold_sec: 0.9
 
     steps:
@@ -64,20 +64,20 @@ jobs:
         machine: [rpi3-32, rpi3-64, rpi4-32, rpi4-64, jetson]
         include:
         - machine: rpi3-32
-          init_performance_threshold_sec: 7.6
-          proc_performance_threshold_sec: 3.3
+          init_performance_threshold_sec: 16.0
+          proc_performance_threshold_sec: 6.0
         - machine: rpi3-64
-          init_performance_threshold_sec: 8.4
-          proc_performance_threshold_sec: 3.3
+          init_performance_threshold_sec: 14.0
+          proc_performance_threshold_sec: 5.5
         - machine: rpi4-32
-          init_performance_threshold_sec: 5.7
-          proc_performance_threshold_sec: 2.1
+          init_performance_threshold_sec: 7.0
+          proc_performance_threshold_sec: 2.5
         - machine: rpi4-64
-          init_performance_threshold_sec: 5.1
-          proc_performance_threshold_sec: 2.0
+          init_performance_threshold_sec: 7.0
+          proc_performance_threshold_sec: 2.5
         - machine: jetson
-          init_performance_threshold_sec: 5.1
-          proc_performance_threshold_sec: 2.0
+          init_performance_threshold_sec: 7.0
+          proc_performance_threshold_sec: 2.6
 
     steps:
     - uses: actions/checkout@v3

.github/workflows/java.yml

@@ -34,14 +34,15 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
+        java-version: ['11', '17', '19']
 
     steps:
     - uses: actions/checkout@v3
 
-    - name: Set up JDK 11
+    - name: Set up JDK ${{ matrix.java-version }}
       uses: actions/setup-java@v3
       with:
-        java-version: '11'
+        java-version: ${{ matrix.java-version }}
         distribution: 'temurin'
 
     - name: Build

binding/java/build.gradle

@@ -7,7 +7,7 @@ plugins {
 
 ext {
     PUBLISH_GROUP_ID = 'ai.picovoice'
-    PUBLISH_VERSION = '1.2.0'
+    PUBLISH_VERSION = '2.0.0'
     PUBLISH_ARTIFACT_ID = 'leopard-java'
 }
 

binding/java/gradle/wrapper/gradle-wrapper.properties

@@ -1,5 +1,5 @@
 distributionBase=GRADLE_USER_HOME
 distributionPath=wrapper/dists
-distributionUrl=https\://services.gradle.org/distributions/gradle-7.3.2-bin.zip
+distributionUrl=https\://services.gradle.org/distributions/gradle-7.6.1-bin.zip
 zipStoreBase=GRADLE_USER_HOME
 zipStorePath=wrapper/dists

binding/java/src/ai/picovoice/leopard/Leopard.java

@@ -13,7 +13,7 @@
 package ai.picovoice.leopard;
 
 import java.io.File;
-import java.util.Arrays;
+import java.util.List;
 
 /**
  * Class for the Leopard Speech-to-Text engine.
@@ -22,7 +22,9 @@ public class Leopard {
 
     public static final String LIBRARY_PATH;
     public static final String MODEL_PATH;
-    public static final String[] VALID_EXTENSIONS;
+    public static final List<String> VALID_EXTENSIONS;
+
+    private static String sdk = "java";
 
     static {
         LIBRARY_PATH = Utils.getPackagedLibraryPath();
@@ -39,19 +41,33 @@ public class Leopard {
      * @param modelPath                  Absolute path to the file containing Leopard model parameters.
      * @param libraryPath                Absolute path to the native Leopard library.
      * @param enableAutomaticPunctuation Set to `true` to enable automatic punctuation insertion.
+     * @param enableDiarization          Set to `true` to enable speaker diarization, which allows Leopard to
+     *                                   differentiate speakers as part of the transcription process. Word metadata
+     *                                   will include a `speakerTag` to identify unique speakers.
      * @throws LeopardException if there is an error while initializing Leopard.
      */
     private Leopard(
             String accessKey,
             String modelPath,
             String libraryPath,
-            boolean enableAutomaticPunctuation) throws LeopardException {
+            boolean enableAutomaticPunctuation,
+            boolean enableDiarization) throws LeopardException {
         try {
             System.load(libraryPath);
         } catch (Exception exception) {
             throw new LeopardException(exception);
         }
-        handle = LeopardNative.init(accessKey, modelPath, enableAutomaticPunctuation);
+
+        LeopardNative.setSdk(Leopard.sdk);
+        handle = LeopardNative.init(
+                accessKey,
+                modelPath,
+                enableAutomaticPunctuation,
+                enableDiarization);
+    }
+
+    public static void setSdk(String sdk) {
+        Leopard.sdk = sdk;
     }
 
     /**
@@ -106,8 +122,8 @@ public LeopardTranscript processFile(String path) throws LeopardException {
             return LeopardNative.processFile(handle, path);
         } catch (LeopardInvalidArgumentException e) {
             if (path.contains(".")) {
-                String extension = path.substring(path.lastIndexOf(".") + 1);
-                if (!Arrays.asList(VALID_EXTENSIONS).contains(extension)) {
+                String extension = path.substring(path.lastIndexOf(".") + 1).toLowerCase();
+                if (!VALID_EXTENSIONS.contains(extension)) {
                     throw new LeopardInvalidArgumentException(
                             String.format("Specified file with extension '%s' is not supported",
                                     extension));
@@ -142,8 +158,8 @@ public static class Builder {
         private String accessKey = null;
         private String libraryPath = null;
         private String modelPath = null;
-
         private boolean enableAutomaticPunctuation = false;
+        private boolean enableDiarization = false;
 
         /**
          * Setter the AccessKey.
@@ -185,6 +201,18 @@ public Builder setEnableAutomaticPunctuation(boolean enableAutomaticPunctuation)
             return this;
         }
 
+        /**
+         * Setter for enabling speaker diarization.
+         *
+         * @param enableDiarization Set to `true` to enable speaker diarization, which allows Leopard to
+         *                          differentiate speakers as part of the transcription process. Word metadata
+         *                          will include a `speakerTag` to identify unique speakers.
+         */
+        public Builder setEnableDiarization(boolean enableDiarization) {
+            this.enableDiarization = enableDiarization;
+            return this;
+        }
+
         /**
          * Creates an instance of Leopard Speech-to-Text engine.
          */
@@ -228,7 +256,12 @@ public Leopard build() throws LeopardException {
                 }
             }
 
-            return new Leopard(accessKey, modelPath, libraryPath, enableAutomaticPunctuation);
+            return new Leopard(
+                    accessKey,
+                    modelPath,
+                    libraryPath,
+                    enableAutomaticPunctuation,
+                    enableDiarization);
         }
     }
 }

binding/java/src/ai/picovoice/leopard/LeopardNative.java

@@ -1,5 +1,5 @@
 /*
-    Copyright 2022 Picovoice Inc.
+    Copyright 2022-2023 Picovoice Inc.
 
     You may not use this file except in compliance with the license. A copy of the license is
     located in the "LICENSE" file accompanying this source.
@@ -18,10 +18,13 @@ class LeopardNative {
 
     static native String getVersion();
 
+    static native void setSdk(String sdk);
+
     static native long init(
             String accessKey,
             String modelPath,
-            boolean enableAutomaticPunctuation) throws LeopardException;
+            boolean enableAutomaticPunctuation,
+            boolean enableDiarization) throws LeopardException;
 
     static native void delete(long object);
 

binding/java/src/ai/picovoice/leopard/LeopardTranscript.java

@@ -57,6 +57,7 @@ public static class Word {
         private final float confidence;
         private final float startSec;
         private final float endSec;
+        private final int speakerTag;
 
         /**
          * Constructor.
@@ -65,12 +66,21 @@ public static class Word {
          * @param confidence Transcription confidence. It is a number within [0, 1].
          * @param startSec   Start of word in seconds.
          * @param endSec     End of word in seconds.
+         * @param speakerTag The speaker tag is `-1` if diarization is not enabled during initialization;
+         *                   otherwise, it's a non-negative integer identifying unique speakers, with `0` reserved
+         *                   for unknown speakers
          */
-        public Word(String word, float confidence, float startSec, float endSec) {
+        public Word(
+                String word,
+                float confidence,
+                float startSec,
+                float endSec,
+                int speakerTag) {
             this.word = word;
             this.confidence = confidence;
             this.startSec = startSec;
             this.endSec = endSec;
+            this.speakerTag = speakerTag;
         }
 
         /**
@@ -108,5 +118,14 @@ public float getStartSec() {
         public float getEndSec() {
             return endSec;
         }
+
+        /**
+         * Getter for the speaker tag.
+         *
+         * @return Speaker tag.
+         */
+        public int getSpeakerTag() {
+            return speakerTag;
+        }
     }
 }

binding/java/src/ai/picovoice/leopard/Utils.java

@@ -21,7 +21,9 @@
 import java.nio.file.Path;
 import java.nio.file.Paths;
 import java.nio.file.StandardCopyOption;
+import java.util.Arrays;
 import java.util.Enumeration;
+import java.util.List;
 import java.util.Locale;
 import java.util.jar.JarEntry;
 import java.util.jar.JarFile;
@@ -232,8 +234,8 @@ public static String getPackagedLibraryPath() {
         }
     }
 
-    public static String[] getValidFileExtensions() {
-        return new String[]{
+    public static List<String> getValidFileExtensions() {
+        return Arrays.asList(
                 "3gp",
                 "flac",
                 "m4a",
@@ -243,6 +245,6 @@ public static String[] getValidFileExtensions() {
                 "opus",
                 "vorbis",
                 "wav",
-                "webm"};
+                "webm");
     }
 }

binding/java/src/ai/picovoice/leopard/exception/LeopardActivationException.java

@@ -1,5 +1,5 @@
 /*
-    Copyright 2022 Picovoice Inc.
+    Copyright 2022-2023 Picovoice Inc.
 
     You may not use this file except in compliance with the license. A copy of the license is
     located in the "LICENSE" file accompanying this source.
@@ -20,4 +20,8 @@ public LeopardActivationException(Throwable cause) {
     public LeopardActivationException(String message) {
         super(message);
     }
+
+    public LeopardActivationException(String message, String[] messageStack) {
+        super(message, messageStack);
+    }
 }

binding/java/src/ai/picovoice/leopard/exception/LeopardActivationLimitException.java

@@ -1,5 +1,5 @@
 /*
-    Copyright 2022 Picovoice Inc.
+    Copyright 2022-2023 Picovoice Inc.
 
     You may not use this file except in compliance with the license. A copy of the license is
     located in the "LICENSE" file accompanying this source.
@@ -20,4 +20,8 @@ public LeopardActivationLimitException(Throwable cause) {
     public LeopardActivationLimitException(String message) {
         super(message);
     }
+
+    public LeopardActivationLimitException(String message, String[] messageStack) {
+        super(message, messageStack);
+    }
 }

binding/java/src/ai/picovoice/leopard/exception/LeopardActivationRefusedException.java

@@ -1,5 +1,5 @@
 /*
-    Copyright 2022 Picovoice Inc.
+    Copyright 2022-2023 Picovoice Inc.
 
     You may not use this file except in compliance with the license. A copy of the license is
     located in the "LICENSE" file accompanying this source.
@@ -20,4 +20,8 @@ public LeopardActivationRefusedException(Throwable cause) {
     public LeopardActivationRefusedException(String message) {
         super(message);
     }
+
+    public LeopardActivationRefusedException(String message, String[] messageStack) {
+        super(message, messageStack);
+    }
 }

binding/java/src/ai/picovoice/leopard/exception/LeopardActivationThrottledException.java

@@ -1,5 +1,5 @@
 /*
-    Copyright 2022 Picovoice Inc.
+    Copyright 2022-2023 Picovoice Inc.
 
     You may not use this file except in compliance with the license. A copy of the license is
     located in the "LICENSE" file accompanying this source.
@@ -20,4 +20,8 @@ public LeopardActivationThrottledException(Throwable cause) {
     public LeopardActivationThrottledException(String message) {
         super(message);
     }
+
+    public LeopardActivationThrottledException(String message, String[] messageStack) {
+        super(message, messageStack);
+    }
 }