Add Java and Kotlin API for punctuation models (#818)

java-api-examples/AddPunctuation.java

@@ -0,0 +1,40 @@
+// Copyright 2024 Xiaomi Corporation
+
+// This file shows how to use a punctuation model to add punctuations to text.
+//
+// The model supports both English and Chinese.
+import com.k2fsa.sherpa.onnx.*;
+
+public class AddPunctuation {
+  public static void main(String[] args) {
+    // please download the model from
+    // https://github.com/k2-fsa/sherpa-onnx/releases/tag/punctuation-models
+    String model = "./sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12/model.onnx";
+    OfflinePunctuationModelConfig modelConfig =
+        OfflinePunctuationModelConfig.builder()
+            .setCtTransformer(model)
+            .setNumThreads(1)
+            .setDebug(true)
+            .build();
+    OfflinePunctuationConfig config =
+        OfflinePunctuationConfig.builder().setModel(modelConfig).build();
+
+    OfflinePunctuation punct = new OfflinePunctuation(config);
+
+    String[] sentences =
+        new String[] {
+          "这是一个测试你好吗How are you我很好thank you are you ok谢谢你",
+          "我们都是木头人不会说话不会动",
+          "The African blogosphere is rapidly expanding bringing more voices online in the form of"
+              + " commentaries opinions analyses rants and poetry",
+        };
+
+    System.out.println("---");
+    for (String text : sentences) {
+      String out = punct.addPunctuation(text);
+      System.out.printf("Input: %s\n", text);
+      System.out.printf("Output: %s\n", out);
+      System.out.println("---");
+    }
+  }
+}

java-api-examples/README.md

@@ -35,3 +35,11 @@ This directory contains examples for the JAVA API of sherpa-onnx.
 ```bash
 ./run-spoken-language-identification-whisper.sh
 ```
+
+## Add puncutations to text
+
+The punctuation model supports both English and Chinese.
+
+```bash
+./run-add-punctuation-zh-en.sh
+```

java-api-examples/run-add-punctuation-zh-en.sh

@@ -0,0 +1,51 @@
+#!/usr/bin/env bash
+
+set -ex
+
+if [[ ! -f ../build/lib/libsherpa-onnx-jni.dylib  && ! -f ../build/lib/libsherpa-onnx-jni.so ]]; then
+  mkdir -p ../build
+  pushd ../build
+  cmake \
+    -DSHERPA_ONNX_ENABLE_PYTHON=OFF \
+    -DSHERPA_ONNX_ENABLE_TESTS=OFF \
+    -DSHERPA_ONNX_ENABLE_CHECK=OFF \
+    -DBUILD_SHARED_LIBS=ON \
+    -DSHERPA_ONNX_ENABLE_PORTAUDIO=OFF \
+    -DSHERPA_ONNX_ENABLE_JNI=ON \
+    ..
+
+  make -j4
+  ls -lh lib
+  popd
+fi
+
+if [ ! -f ../sherpa-onnx/java-api/build/sherpa-onnx.jar ]; then
+  pushd ../sherpa-onnx/java-api
+  make
+  popd
+fi
+
+if [[ ! -f ../build/lib/libsherpa-onnx-jni.dylib  && ! -f ../build/lib/libsherpa-onnx-jni.so ]]; then
+  cmake \
+    -DSHERPA_ONNX_ENABLE_PYTHON=OFF \
+    -DSHERPA_ONNX_ENABLE_TESTS=OFF \
+    -DSHERPA_ONNX_ENABLE_CHECK=OFF \
+    -DBUILD_SHARED_LIBS=ON \
+    -DSHERPA_ONNX_ENABLE_PORTAUDIO=OFF \
+    -DSHERPA_ONNX_ENABLE_JNI=ON \
+    ..
+
+  make -j4
+  ls -lh lib
+fi
+
+if [ ! -f ./sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12/model.onnx ]; then
+  curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/punctuation-models/sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12.tar.bz2
+  tar xvf sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12.tar.bz2
+  rm sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12.tar.bz2
+fi
+
+java \
+  -Djava.library.path=$PWD/../build/lib \
+  -cp ../sherpa-onnx/java-api/build/sherpa-onnx.jar \
+  ./AddPunctuation.java