-
Notifications
You must be signed in to change notification settings - Fork 508
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
47 changed files
with
1,311 additions
and
2 deletions.
There are no files selected for viewing
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,15 @@ | ||
*.iml | ||
.gradle | ||
/local.properties | ||
/.idea/caches | ||
/.idea/libraries | ||
/.idea/modules.xml | ||
/.idea/workspace.xml | ||
/.idea/navEditor.xml | ||
/.idea/assetWizardSettings.xml | ||
.DS_Store | ||
/build | ||
/captures | ||
.externalNativeBuild | ||
.cxx | ||
local.properties |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
/build |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,44 @@ | ||
plugins { | ||
id 'com.android.application' | ||
id 'org.jetbrains.kotlin.android' | ||
} | ||
|
||
android { | ||
namespace 'com.k2fsa.sherpa.onnx' | ||
compileSdk 32 | ||
|
||
defaultConfig { | ||
applicationId "com.k2fsa.sherpa.onnx" | ||
minSdk 21 | ||
targetSdk 32 | ||
versionCode 1 | ||
versionName "1.0" | ||
|
||
testInstrumentationRunner "androidx.test.runner.AndroidJUnitRunner" | ||
} | ||
|
||
buildTypes { | ||
release { | ||
minifyEnabled false | ||
proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro' | ||
} | ||
} | ||
compileOptions { | ||
sourceCompatibility JavaVersion.VERSION_1_8 | ||
targetCompatibility JavaVersion.VERSION_1_8 | ||
} | ||
kotlinOptions { | ||
jvmTarget = '1.8' | ||
} | ||
} | ||
|
||
dependencies { | ||
|
||
implementation 'androidx.core:core-ktx:1.7.0' | ||
implementation 'androidx.appcompat:appcompat:1.5.1' | ||
implementation 'com.google.android.material:material:1.7.0' | ||
implementation 'androidx.constraintlayout:constraintlayout:2.1.4' | ||
testImplementation 'junit:junit:4.13.2' | ||
androidTestImplementation 'androidx.test.ext:junit:1.1.4' | ||
androidTestImplementation 'androidx.test.espresso:espresso-core:3.5.0' | ||
} |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,21 @@ | ||
# Add project specific ProGuard rules here. | ||
# You can control the set of applied configuration files using the | ||
# proguardFiles setting in build.gradle. | ||
# | ||
# For more details, see | ||
# http://developer.android.com/guide/developing/tools/proguard.html | ||
|
||
# If your project uses WebView with JS, uncomment the following | ||
# and specify the fully qualified class name to the JavaScript interface | ||
# class: | ||
#-keepclassmembers class fqcn.of.javascript.interface.for.webview { | ||
# public *; | ||
#} | ||
|
||
# Uncomment this to preserve the line number information for | ||
# debugging stack traces. | ||
#-keepattributes SourceFile,LineNumberTable | ||
|
||
# If you keep the line number information, uncomment this to | ||
# hide the original source file name. | ||
#-renamesourcefileattribute SourceFile |
24 changes: 24 additions & 0 deletions
24
...d/SherpaOnnxKws/app/src/androidTest/java/com/k2fsa/sherpa/onnx/ExampleInstrumentedTest.kt
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,24 @@ | ||
package com.k2fsa.sherpa.onnx | ||
|
||
import androidx.test.platform.app.InstrumentationRegistry | ||
import androidx.test.ext.junit.runners.AndroidJUnit4 | ||
|
||
import org.junit.Test | ||
import org.junit.runner.RunWith | ||
|
||
import org.junit.Assert.* | ||
|
||
/** | ||
* Instrumented test, which will execute on an Android device. | ||
* | ||
* See [testing documentation](http://d.android.com/tools/testing). | ||
*/ | ||
@RunWith(AndroidJUnit4::class) | ||
class ExampleInstrumentedTest { | ||
@Test | ||
fun useAppContext() { | ||
// Context of the app under test. | ||
val appContext = InstrumentationRegistry.getInstrumentation().targetContext | ||
assertEquals("com.k2fsa.sherpa.onnx", appContext.packageName) | ||
} | ||
} |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,32 @@ | ||
<?xml version="1.0" encoding="utf-8"?> | ||
<manifest xmlns:android="http://schemas.android.com/apk/res/android" | ||
xmlns:tools="http://schemas.android.com/tools"> | ||
|
||
<uses-permission android:name="android.permission.RECORD_AUDIO" /> | ||
|
||
<application | ||
android:allowBackup="true" | ||
android:dataExtractionRules="@xml/data_extraction_rules" | ||
android:fullBackupContent="@xml/backup_rules" | ||
android:icon="@mipmap/ic_launcher" | ||
android:label="@string/app_name" | ||
android:roundIcon="@mipmap/ic_launcher_round" | ||
android:supportsRtl="true" | ||
android:theme="@style/Theme.SherpaOnnx" | ||
tools:targetApi="31"> | ||
<activity | ||
android:name=".MainActivity" | ||
android:exported="true"> | ||
<intent-filter> | ||
<action android:name="android.intent.action.MAIN" /> | ||
|
||
<category android:name="android.intent.category.LAUNCHER" /> | ||
</intent-filter> | ||
|
||
<meta-data | ||
android:name="android.app.lib_name" | ||
android:value="" /> | ||
</activity> | ||
</application> | ||
|
||
</manifest> |
Empty file.
189 changes: 189 additions & 0 deletions
189
android/SherpaOnnxKws/app/src/main/java/com/k2fsa/sherpa/onnx/MainActivity.kt
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,189 @@ | ||
package com.k2fsa.sherpa.onnx | ||
|
||
import android.Manifest | ||
import android.content.pm.PackageManager | ||
import android.media.AudioFormat | ||
import android.media.AudioRecord | ||
import android.media.MediaRecorder | ||
import android.os.Bundle | ||
import android.text.method.ScrollingMovementMethod | ||
import android.util.Log | ||
import android.widget.Button | ||
import android.widget.TextView | ||
import androidx.appcompat.app.AppCompatActivity | ||
import androidx.core.app.ActivityCompat | ||
import com.k2fsa.sherpa.onnx.* | ||
import kotlin.concurrent.thread | ||
|
||
private const val TAG = "sherpa-onnx" | ||
private const val REQUEST_RECORD_AUDIO_PERMISSION = 200 | ||
|
||
class MainActivity : AppCompatActivity() { | ||
private val permissions: Array<String> = arrayOf(Manifest.permission.RECORD_AUDIO) | ||
|
||
private lateinit var model: SherpaOnnxKws | ||
private var audioRecord: AudioRecord? = null | ||
private lateinit var recordButton: Button | ||
private lateinit var textView: TextView | ||
private var recordingThread: Thread? = null | ||
|
||
private val audioSource = MediaRecorder.AudioSource.MIC | ||
private val sampleRateInHz = 16000 | ||
private val channelConfig = AudioFormat.CHANNEL_IN_MONO | ||
|
||
// Note: We don't use AudioFormat.ENCODING_PCM_FLOAT | ||
// since the AudioRecord.read(float[]) needs API level >= 23 | ||
// but we are targeting API level >= 21 | ||
private val audioFormat = AudioFormat.ENCODING_PCM_16BIT | ||
private var idx: Int = 0 | ||
private var lastText: String = "" | ||
|
||
@Volatile | ||
private var isRecording: Boolean = false | ||
|
||
override fun onRequestPermissionsResult( | ||
requestCode: Int, permissions: Array<String>, grantResults: IntArray | ||
) { | ||
super.onRequestPermissionsResult(requestCode, permissions, grantResults) | ||
val permissionToRecordAccepted = if (requestCode == REQUEST_RECORD_AUDIO_PERMISSION) { | ||
grantResults[0] == PackageManager.PERMISSION_GRANTED | ||
} else { | ||
false | ||
} | ||
|
||
if (!permissionToRecordAccepted) { | ||
Log.e(TAG, "Audio record is disallowed") | ||
finish() | ||
} | ||
|
||
Log.i(TAG, "Audio record is permitted") | ||
} | ||
|
||
override fun onCreate(savedInstanceState: Bundle?) { | ||
super.onCreate(savedInstanceState) | ||
setContentView(R.layout.activity_main) | ||
|
||
ActivityCompat.requestPermissions(this, permissions, REQUEST_RECORD_AUDIO_PERMISSION) | ||
|
||
Log.i(TAG, "Start to initialize model") | ||
initModel() | ||
Log.i(TAG, "Finished initializing model") | ||
|
||
recordButton = findViewById(R.id.record_button) | ||
recordButton.setOnClickListener { onclick() } | ||
|
||
textView = findViewById(R.id.my_text) | ||
textView.movementMethod = ScrollingMovementMethod() | ||
} | ||
|
||
private fun onclick() { | ||
if (!isRecording) { | ||
val ret = initMicrophone() | ||
if (!ret) { | ||
Log.e(TAG, "Failed to initialize microphone") | ||
return | ||
} | ||
Log.i(TAG, "state: ${audioRecord?.state}") | ||
audioRecord!!.startRecording() | ||
recordButton.setText(R.string.stop) | ||
isRecording = true | ||
model.reset(true) | ||
textView.text = "" | ||
lastText = "" | ||
idx = 0 | ||
|
||
recordingThread = thread(true) { | ||
processSamples() | ||
} | ||
Log.i(TAG, "Started recording") | ||
} else { | ||
isRecording = false | ||
audioRecord!!.stop() | ||
audioRecord!!.release() | ||
audioRecord = null | ||
recordButton.setText(R.string.start) | ||
Log.i(TAG, "Stopped recording") | ||
} | ||
} | ||
|
||
private fun processSamples() { | ||
Log.i(TAG, "processing samples") | ||
|
||
val interval = 0.1 // i.e., 100 ms | ||
val bufferSize = (interval * sampleRateInHz).toInt() // in samples | ||
val buffer = ShortArray(bufferSize) | ||
|
||
while (isRecording) { | ||
val ret = audioRecord?.read(buffer, 0, buffer.size) | ||
if (ret != null && ret > 0) { | ||
val samples = FloatArray(ret) { buffer[it] / 32768.0f } | ||
model.acceptWaveform(samples, sampleRate=sampleRateInHz) | ||
while (model.isReady()) { | ||
model.decode() | ||
} | ||
|
||
val isEndpoint = model.isEndpoint() | ||
val text = model.keyword | ||
|
||
var textToDisplay = lastText; | ||
|
||
if(text.isNotBlank()) { | ||
if (lastText.isBlank()) { | ||
textToDisplay = "${idx}: ${text}" | ||
} else { | ||
textToDisplay = "${lastText}\n${idx}: ${text}" | ||
} | ||
lastText = "${lastText}\n${idx}: ${text}" | ||
idx += 1 | ||
} | ||
|
||
runOnUiThread { | ||
textView.text = textToDisplay | ||
} | ||
} | ||
} | ||
} | ||
|
||
private fun initMicrophone(): Boolean { | ||
if (ActivityCompat.checkSelfPermission( | ||
this, Manifest.permission.RECORD_AUDIO | ||
) != PackageManager.PERMISSION_GRANTED | ||
) { | ||
ActivityCompat.requestPermissions(this, permissions, REQUEST_RECORD_AUDIO_PERMISSION) | ||
return false | ||
} | ||
|
||
val numBytes = AudioRecord.getMinBufferSize(sampleRateInHz, channelConfig, audioFormat) | ||
Log.i( | ||
TAG, "buffer size in milliseconds: ${numBytes * 1000.0f / sampleRateInHz}" | ||
) | ||
|
||
audioRecord = AudioRecord( | ||
audioSource, | ||
sampleRateInHz, | ||
channelConfig, | ||
audioFormat, | ||
numBytes * 2 // a sample has two bytes as we are using 16-bit PCM | ||
) | ||
return true | ||
} | ||
|
||
private fun initModel() { | ||
// Please change getModelConfig() to add new models | ||
// See https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html | ||
// for a list of available models | ||
val type = 0 | ||
println("Select model type ${type}") | ||
val config = KeywordSpotterConfig( | ||
featConfig = getFeatureConfig(sampleRate = sampleRateInHz, featureDim = 80), | ||
modelConfig = getModelConfig(type = type)!!, | ||
endpointConfig = getEndpointConfig(), | ||
enableEndpoint = true, | ||
) | ||
|
||
model = SherpaOnnxKws( | ||
assetManager = application.assets, | ||
config = config, | ||
) | ||
} | ||
} |
Oops, something went wrong.