Sync to latest origin repostitory

README.md

@@ -1,26 +1,7 @@
 ## About
 
-This is a demonstration for Kaldi on Android
+This demo implements offline speech recognition and speaker identification for mobile applications using Kaldi and Vosk libraries.
 
-## Usage
+## Documentation
 
-Simply import the project into Android Studio and run. It will listen for the audio and dump the transcription.
-
-To use this library in your application simply modify the demo according to your needs - add kaldi-android aar
-to dependencies, update the model and modify java UI code accodring to your needs.
-
-## Development
-
-This is just a demo project, the main setup to compile kaldi-android
-library AAR is available at [vosk-api](http://github.com/alphacep/vosk-api). Check
-compilation instructions there as well as development plans.
-
-## Languages
-
-Models for different languages (English, Chinese, Russian) are available in
-[Releases](https://github.com/alphacep/kaldi-android-demo/releases) section. To use the model unpack it into
-```kaldi-android-demo/models/src/main/assets/sync/model-android```. More languages gonna be ready soon.
-
-## Updating grammar and language model
-
-To run on android model has to be sufficiently small, we recommend to check model sizes in the demo to figure out what should be the size of the model. If you want to update the grammar or the acoustic model, check [vosk-api documentation](https://github.com/alphacep/vosk-api/blob/master/doc/models.md).
+For documentation and instructions see [Vosk Website](https://alphacephei.com/vosk/android)

app/build.gradle

@@ -2,21 +2,28 @@ apply plugin: 'com.android.application'
 
 repositories {
     google()
+    maven {
+        url  "https://dl.bintray.com/alphacep/vosk"
+    }
 }
 
 android {
     compileSdkVersion 29
     defaultConfig {
-        applicationId "org.kaldi.demo"
+        applicationId "org.vosk.demo"
         minSdkVersion 21
         targetSdkVersion 29
         versionCode 1
         versionName "1.1"
+        ndk {
+            abiFilters 'armeabi-v7a', 'arm64-v8a', 'x86_64', 'x86'
+        }
     }
 }
 
 dependencies {
-    implementation project(':aars')
-    implementation project(':models')
+    implementation 'com.alphacep:vosk-android:0.3.10'
     implementation 'androidx.appcompat:appcompat:1.1.0'
+
+    implementation project(':models')
 }

app/src/main/java/org/kaldi/demo/KaldiActivity.java

@@ -22,6 +22,8 @@
 import androidx.annotation.NonNull;
 import androidx.core.app.ActivityCompat;
 import androidx.core.content.ContextCompat;
+
+import android.text.method.ScrollingMovementMethod;
 import android.util.Log;
 import android.view.View;
 import android.widget.Button;
@@ -31,7 +33,8 @@
 import org.kaldi.KaldiRecognizer;
 import org.kaldi.Model;
 import org.kaldi.RecognitionListener;
-import org.kaldi.SpeechRecognizer;
+import org.kaldi.SpeechService;
+import org.kaldi.Vosk;
 
 import java.io.File;
 import java.io.IOException;
@@ -41,20 +44,18 @@
 public class KaldiActivity extends Activity implements
         RecognitionListener {
 
-    static {
-        System.loadLibrary("kaldi_jni");
-    }
-
     static private final int STATE_START = 0;
     static private final int STATE_READY = 1;
-    static private final int STATE_FILE = 2;
-    static private final int STATE_MIC  = 3;
+    static private final int STATE_DONE = 2;
+    static private final int STATE_FILE = 3;
+    static private final int STATE_MIC  = 4;
 
     /* Used to handle permission request */
     private static final int PERMISSIONS_REQUEST_RECORD_AUDIO = 1;
 
+
     private Model model;
-    private SpeechRecognizer recognizer;
+    private SpeechService speechService;
     TextView resultView;
 
     @Override
@@ -103,7 +104,10 @@ protected Exception doInBackground(Void... params) {
             try {
                 Assets assets = new Assets(activityReference.get());
                 File assetDir = assets.syncAssets();
-                Log.d("!!!!", assetDir.toString());
+                Log.d("KaldiDemo", "Sync files in the folder " + assetDir.toString());
+
+                Vosk.SetLogLevel(0);
+
                 activityReference.get().model = new Model(assetDir.toString() + "/model-android");
             } catch (IOException e) {
                 return e;
@@ -136,7 +140,7 @@ protected String doInBackground(Void... params) {
             long startTime = System.currentTimeMillis();
             StringBuilder result = new StringBuilder();
             try {
-                rec = new KaldiRecognizer(activityReference.get().model, 16000.f);
+                rec = new KaldiRecognizer(activityReference.get().model, 16000.f, "oh zero one two three four five six seven eight nine");
 
                 InputStream ais = activityReference.get().getAssets().open("10001-90210-01803.wav");
                 if (ais.skip(44) != 44) {
@@ -185,9 +189,9 @@ public void onRequestPermissionsResult(int requestCode,
     public void onDestroy() {
         super.onDestroy();
 
-        if (recognizer != null) {
-            recognizer.cancel();
-            recognizer.shutdown();
+        if (speechService != null) {
+            speechService.cancel();
+            speechService.shutdown();
         }
     }
 
@@ -209,15 +213,16 @@ public void onError(Exception e) {
 
     @Override
     public void onTimeout() {
-        recognizer.cancel();
-        recognizer = null;
+        speechService.cancel();
+        speechService = null;
         setUiState(STATE_READY);
     }
 
     private void setUiState(int state) {
         switch (state) {
             case STATE_START:
                 resultView.setText(R.string.preparing);
+                resultView.setMovementMethod(new ScrollingMovementMethod());
                 findViewById(R.id.recognize_file).setEnabled(false);
                 findViewById(R.id.recognize_mic).setEnabled(false);
                 break;
@@ -227,13 +232,19 @@ private void setUiState(int state) {
                 findViewById(R.id.recognize_file).setEnabled(true);
                 findViewById(R.id.recognize_mic).setEnabled(true);
                 break;
+            case STATE_DONE:
+                ((Button) findViewById(R.id.recognize_mic)).setText(R.string.recognize_microphone);
+                findViewById(R.id.recognize_file).setEnabled(true);
+                findViewById(R.id.recognize_mic).setEnabled(true);
+                break;
             case STATE_FILE:
-                resultView.append(getString(R.string.starting));
+                resultView.setText(getString(R.string.starting));
                 findViewById(R.id.recognize_mic).setEnabled(false);
                 findViewById(R.id.recognize_file).setEnabled(false);
                 break;
             case STATE_MIC:
                 ((Button) findViewById(R.id.recognize_mic)).setText(R.string.stop_microphone);
+                resultView.setText(getString(R.string.say_something));
                 findViewById(R.id.recognize_file).setEnabled(false);
                 findViewById(R.id.recognize_mic).setEnabled(true);
                 break;
@@ -253,16 +264,17 @@ public void recognizeFile() {
     }
 
     public void recognizeMicrophone() {
-        if (recognizer != null) {
-            setUiState(STATE_READY);
-            recognizer.cancel();
-            recognizer = null;
+        if (speechService != null) {
+            setUiState(STATE_DONE);
+            speechService.cancel();
+            speechService = null;
         } else {
             setUiState(STATE_MIC);
             try {
-                recognizer = new SpeechRecognizer(model);
-                recognizer.addListener(this);
-                recognizer.startListening();
+                KaldiRecognizer rec = new KaldiRecognizer(model, 16000.0f);
+                speechService = new SpeechService(rec, 16000.0f);
+                speechService.addListener(this);
+                speechService.startListening();
             } catch (IOException e) {
                 setErrorState(e.getMessage());
             }

app/src/main/res/values/strings.xml

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="utf-8"?>
 <resources>
 
-    <string name="app_name">Kaldi Demo</string>
+    <string name="app_name">Vosk Demo</string>
     <string name="recognize_file">Recognize File</string>
     <string name="recognize_microphone">Recognize Microphone</string>
     <string name="stop_microphone">Stop Microphone</string>
@@ -10,5 +10,6 @@
     <string name="failed">Failed to init recognizer %s\n</string>
     <string name="elapsed">Result %s elapsed %d milliseconds\n</string>
     <string name="starting">Starting\n</string>
+    <string name="say_something">Say something\n</string>
 
 </resources>

models/src/main/assets/sync/model-android/README

@@ -0,0 +1,2 @@
+US English model for android
+

models/src/main/assets/sync/model-android/conf/model.conf

@@ -0,0 +1,10 @@
+--min-active=200
+--max-active=3000
+--beam=10.0
+--lattice-beam=2.0
+--acoustic-scale=1.0
+--frame-subsampling-factor=3
+--endpoint.silence-phones=1:2:3:4:5:6:7:8:9:10
+--endpoint.rule2.min-trailing-silence=0.5
+--endpoint.rule3.min-trailing-silence=1.0
+--endpoint.rule4.min-trailing-silence=2.0

settings.gradle

@@ -1,2 +1,2 @@
-include ':models', ':aars', ':app'
+include ':models', ':app'