Add CTC HLG decoding for JNI (#810)

kotlin-api-examples/run.sh

@@ -69,6 +69,12 @@ function testOnlineAsr() {
     rm sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
   fi
 
+  if [ ! -d ./sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18 ]; then
+    curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18.tar.bz2
+    tar xvf sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18.tar.bz2
+    rm sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18.tar.bz2
+  fi
+
   out_filename=test_online_asr.jar
   kotlinc-jvm -include-runtime -d $out_filename \
     test_online_asr.kt \
@@ -160,6 +166,24 @@ function testOfflineAsr() {
     rm sherpa-onnx-whisper-tiny.en.tar.bz2
   fi
 
+  if [ ! -f ./sherpa-onnx-nemo-ctc-en-citrinet-512/tokens.txt ]; then
+    curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-ctc-en-citrinet-512.tar.bz2
+    tar xvf sherpa-onnx-nemo-ctc-en-citrinet-512.tar.bz2
+    rm sherpa-onnx-nemo-ctc-en-citrinet-512.tar.bz2
+  fi
+
+  if [ ! -f ./sherpa-onnx-paraformer-zh-2023-03-28/tokens.txt ]; then
+    curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-paraformer-zh-2023-03-28.tar.bz2
+    tar xvf sherpa-onnx-paraformer-zh-2023-03-28.tar.bz2
+    rm sherpa-onnx-paraformer-zh-2023-03-28.tar.bz2
+  fi
+
+  if [ ! -f ./sherpa-onnx-zipformer-multi-zh-hans-2023-9-2/tokens.txt ]; then
+    curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-multi-zh-hans-2023-9-2.tar.bz2
+    tar xvf sherpa-onnx-zipformer-multi-zh-hans-2023-9-2.tar.bz2
+    rm sherpa-onnx-zipformer-multi-zh-hans-2023-9-2.tar.bz2
+  fi
+
   out_filename=test_offline_asr.jar
   kotlinc-jvm -include-runtime -d $out_filename \
     test_offline_asr.kt \

kotlin-api-examples/test_offline_asr.kt

@@ -1,12 +1,25 @@
 package com.k2fsa.sherpa.onnx
 
 fun main() {
-  val recognizer = createOfflineRecognizer()
+  val types = arrayOf(0, 2, 5, 6)
+  for (type in types) {
+    test(type)
+  }
+}
 
-  val waveFilename = "./sherpa-onnx-streaming-zipformer-en-20M-2023-02-17/test_wavs/0.wav"
+fun test(type: Int) {
+  val recognizer = createOfflineRecognizer(type)
+
+  val waveFilename = when (type) {
+    0 -> "./sherpa-onnx-paraformer-zh-2023-03-28/test_wavs/0.wav"
+    2 -> "./sherpa-onnx-whisper-tiny.en/test_wavs/0.wav"
+    5 -> "./sherpa-onnx-zipformer-multi-zh-hans-2023-9-2/test_wavs/1.wav"
+    6 -> "./sherpa-onnx-nemo-ctc-en-citrinet-512/test_wavs/8k.wav"
+    else -> null
+  }
 
   val objArray = WaveReader.readWaveFromFile(
-      filename = waveFilename,
+      filename = waveFilename!!,
   )
   val samples: FloatArray = objArray[0] as FloatArray
   val sampleRate: Int = objArray[1] as Int
@@ -22,10 +35,10 @@ fun main() {
   recognizer.release()
 }
 
-fun createOfflineRecognizer(): OfflineRecognizer {
+fun createOfflineRecognizer(type: Int): OfflineRecognizer {
   val config = OfflineRecognizerConfig(
       featConfig = getFeatureConfig(sampleRate = 16000, featureDim = 80),
-      modelConfig = getOfflineModelConfig(type = 2)!!,
+      modelConfig = getOfflineModelConfig(type = type)!!,
   )
 
   return OfflineRecognizer(config = config)

kotlin-api-examples/test_online_asr.kt

@@ -3,6 +3,7 @@ package com.k2fsa.sherpa.onnx
 fun main() {
   testOnlineAsr("transducer")
   testOnlineAsr("zipformer2-ctc")
+  testOnlineAsr("ctc-hlg")
 }
 
 fun testOnlineAsr(type: String) {
@@ -11,6 +12,7 @@ fun testOnlineAsr(type: String) {
         featureDim = 80,
     )
 
+    var ctcFstDecoderConfig  = OnlineCtcFstDecoderConfig()
     val waveFilename: String
     val modelConfig: OnlineModelConfig = when (type) {
       "transducer" -> {
@@ -40,6 +42,18 @@ fun testOnlineAsr(type: String) {
             debug = false,
         )
       }
+      "ctc-hlg" -> {
+        waveFilename = "./sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18/test_wavs/1.wav"
+        ctcFstDecoderConfig.graph = "./sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18/HLG.fst"
+        OnlineModelConfig(
+            zipformer2Ctc = OnlineZipformer2CtcModelConfig(
+                model = "./sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18/ctc-epoch-30-avg-3-chunk-16-left-128.int8.onnx",
+            ),
+            tokens = "./sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18/tokens.txt",
+            numThreads = 1,
+            debug = false,
+        )
+      }
       else -> throw IllegalArgumentException(type)
     }
 
@@ -51,6 +65,7 @@ fun testOnlineAsr(type: String) {
         modelConfig = modelConfig,
         lmConfig = lmConfig,
         featConfig = featConfig,
+        ctcFstDecoderConfig=ctcFstDecoderConfig,
         endpointConfig = endpointConfig,
         enableEndpoint = true,
         decodingMethod = "greedy_search",