Use piper-phonemize to convert text to token IDs (#453)

kotlin-api-examples/Main.kt

@@ -8,20 +8,22 @@ fun main() {
 }
 
 fun testTts() {
+  // see https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
+  // https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2
   var config = OfflineTtsConfig(
     model=OfflineTtsModelConfig(
       vits=OfflineTtsVitsModelConfig(
-        model="./vits-zh-aishell3/vits-aishell3.onnx",
-        lexicon="./vits-zh-aishell3/lexicon.txt",
-        tokens="./vits-zh-aishell3/tokens.txt",
+        model="./vits-piper-en_US-amy-low/en_US-amy-low.onnx",
+        tokens="./vits-piper-en_US-amy-low/tokens.txt",
+        dataDir="./vits-piper-en_US-amy-low/espeak-ng-data",
       ),
       numThreads=1,
       debug=true,
     )
   )
   val tts = OfflineTts(config=config)
-  val audio = tts.generate(text="林美丽最美丽!", sid=99, speed=1.2f)
-  audio.save(filename="99.wav")
+  val audio = tts.generate(text="“Today as always, men fall into two groups: slaves and free men. Whoever does not have two-thirds of his day for himself, is a slave, whatever he may be: a statesman, a businessman, an official, or a scholar.”")
+  audio.save(filename="test-en.wav")
 }
 
 fun testAsr() {

kotlin-api-examples/run.sh

@@ -34,9 +34,10 @@ if [ ! -f ./sherpa-onnx-streaming-zipformer-en-2023-02-21/tokens.txt ]; then
   git clone https://huggingface.co/csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-02-21
 fi
 
-if [ ! -f ./vits-zh-aishell3/tokens.txt ]; then
-  git lfs install
-  git clone https://huggingface.co/csukuangfj/vits-zh-aishell3
+if [ ! -f ./vits-piper-en_US-amy-low/en_US-amy-low.onnx ]; then
+  wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2
+  tar xf vits-piper-en_US-amy-low.tar.bz2
+  rm vits-piper-en_US-amy-low.tar.bz2
 fi
 
 kotlinc-jvm -include-runtime -d main.jar Main.kt WaveReader.kt SherpaOnnx.kt faked-asset-manager.kt Tts.kt