decoder for open vocabulary keyword spotting (k2-fsa#505)

* various fixes to ContextGraph to support open vocabulary keywords decoder

* Add keyword spotter runtime

* Add binary

* First version works

* Minor fixes

* update text2token

* default values

* Add jni for kws

* add kws android project

* Minor fixes

* Remove unused interface

* Minor fixes

* Add workflow

* handle extra info in texts

* Minor fixes

* Add more comments

* Fix ci

* fix cpp style

* Add input box in android demo so that users can specify their keywords

* Fix cpp style

* Fix comments

* Minor fixes

* Minor fixes

* minor fixes

* Minor fixes

* Minor fixes

* Add CI

* Fix code style

* cpplint

* Fix comments

* Fix error

.github/scripts/test-kws.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+
+set -e
+
+log() {
+  # This function is from espnet
+  local fname=${BASH_SOURCE[1]##*/}
+  echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+
+echo "EXE is $EXE"
+echo "PATH: $PATH"
+
+which $EXE
+
+log "------------------------------------------------------------"
+log "Run Chinese keyword spotting (Wenetspeech）"
+log "------------------------------------------------------------"
+
+repo_url=https://www.modelscope.cn/pkufool/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.git
+log "Start testing ${repo_url}"
+repo=sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
+log "Download pretrained model and test-data from $repo_url"
+
+GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
+pushd $repo
+git lfs pull --include "*.onnx"
+ls -lh *.onnx
+popd
+
+time $EXE \
+  --tokens=$repo/tokens.txt \
+  --encoder=$repo/encoder-epoch-12-avg-2-chunk-16-left-64.onnx \
+  --decoder=$repo/decoder-epoch-12-avg-2-chunk-16-left-64.onnx \
+  --joiner=$repo/joiner-epoch-12-avg-2-chunk-16-left-64.onnx \
+  --keywords-file=$repo/test_wavs/test_keywords.txt \
+  --max-active-paths=4 \
+  --num-threads=4 \
+  $repo/test_wavs/3.wav $repo/test_wavs/4.wav $repo/test_wavs/5.wav $repo/test_wavs/6.wav
+
+rm -rf $repo
+
+log "------------------------------------------------------------"
+log "Run English keyword spotting (Gigaspeech）"
+log "------------------------------------------------------------"
+
+repo_url=https://www.modelscope.cn/pkufool/sherpa-onnx-kws-zipformer-gigaspeech-3.3M-2024-01-01.git
+log "Start testing ${repo_url}"
+repo=sherpa-onnx-kws-zipformer-gigaspeech-3.3M-2024-01-01
+log "Download pretrained model and test-data from $repo_url"
+
+GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
+pushd $repo
+git lfs pull --include "*.onnx"
+ls -lh *.onnx
+popd
+
+time $EXE \
+  --tokens=$repo/tokens.txt \
+  --encoder=$repo/encoder-epoch-12-avg-2-chunk-16-left-64.onnx \
+  --decoder=$repo/decoder-epoch-12-avg-2-chunk-16-left-64.onnx \
+  --joiner=$repo/joiner-epoch-12-avg-2-chunk-16-left-64.onnx \
+  --keywords-file=$repo/test_wavs/test_keywords.txt \
+  --max-active-paths=4 \
+  --num-threads=4 \
+  $repo/test_wavs/0.wav $repo/test_wavs/1.wav
+
+rm -rf $repo

.github/workflows/apk-kws.yaml

@@ -0,0 +1,67 @@
+name: apk-kws
+
+on:
+  push:
+    branches:
+      - apk-kws
+    tags:
+      - '*'
+
+  workflow_dispatch:
+
+concurrency:
+  group: apk-kws-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: write
+
+jobs:
+  apk:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: ccache
+        uses: hendrikmuhs/ccache-action@v1.2
+        with:
+          key: ${{ matrix.os }}-android
+
+      - name: Display NDK HOME
+        shell: bash
+        run: |
+          echo "ANDROID_NDK_LATEST_HOME: ${ANDROID_NDK_LATEST_HOME}"
+          ls -lh ${ANDROID_NDK_LATEST_HOME}
+
+      - name: build APK
+        shell: bash
+        run: |
+          export CMAKE_CXX_COMPILER_LAUNCHER=ccache
+          export PATH="/usr/lib/ccache:/usr/local/opt/ccache/libexec:$PATH"
+          cmake --version
+
+          export ANDROID_NDK=$ANDROID_NDK_LATEST_HOME
+          ./build-kws-apk.sh
+
+      - name: Display APK
+        shell: bash
+        run: |
+          ls -lh ./apks/
+
+      - uses: actions/upload-artifact@v3
+        with:
+          path: ./apks/*.apk
+
+      - name: Release APK
+        uses: svenstaro/upload-release-action@v2
+        with:
+          file_glob: true
+          file: apks/*.apk
+          overwrite: true

.github/workflows/linux.yaml

@@ -107,6 +107,14 @@ jobs:
           name: release-static
           path: build/bin/*
 
+      - name: Test transducer kws
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin:$PATH
+          export EXE=sherpa-onnx-keyword-spotter
+
+          .github/scripts/test-kws.sh
+
       - name: Test online CTC
         shell: bash
         run: |

.github/workflows/macos.yaml

@@ -98,6 +98,14 @@ jobs:
           otool -L build/bin/sherpa-onnx
           otool -l build/bin/sherpa-onnx
 
+      - name: Test transducer kws
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin:$PATH
+          export EXE=sherpa-onnx-keyword-spotter
+
+          .github/scripts/test-kws.sh
+
       - name: Test online CTC
         shell: bash
         run: |
@@ -106,7 +114,6 @@ jobs:
 
           .github/scripts/test-online-ctc.sh
 
-
       - name: Test offline TTS
         shell: bash
         run: |

.github/workflows/run-python-test.yaml

@@ -62,7 +62,7 @@ jobs:
       - name: Install Python dependencies
         shell: bash
         run: |
-          python3 -m pip install --upgrade pip numpy sentencepiece==0.1.96 soundfile
+          python3 -m pip install --upgrade pip numpy pypinyin sentencepiece==0.1.96 soundfile
 
       - name: Install sherpa-onnx
         shell: bash

.github/workflows/test-python-offline-websocket-server.yaml

@@ -45,7 +45,7 @@ jobs:
       - name: Install Python dependencies
         shell: bash
         run: |
-          python3 -m pip install --upgrade pip numpy sentencepiece
+          python3 -m pip install --upgrade pip numpy pypinyin sentencepiece
 
       - name: Install sherpa-onnx
         shell: bash

.github/workflows/test-python-online-websocket-server.yaml

@@ -45,7 +45,7 @@ jobs:
       - name: Install Python dependencies
         shell: bash
         run: |
-          python3 -m pip install --upgrade pip numpy sentencepiece
+          python3 -m pip install --upgrade pip numpy pypinyin sentencepiece
 
       - name: Install sherpa-onnx
         shell: bash

android/SherpaOnnxKws/.gitignore

@@ -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

android/SherpaOnnxKws/app/.gitignore

@@ -0,0 +1 @@
+/build

android/SherpaOnnxKws/app/build.gradle

@@ -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'
+}

android/SherpaOnnxKws/app/proguard-rules.pro

@@ -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

android/SherpaOnnxKws/app/src/androidTest/java/com/k2fsa/sherpa/onnx/ExampleInstrumentedTest.kt

@@ -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)
+    }
+}

android/SherpaOnnxKws/app/src/main/AndroidManifest.xml

@@ -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>