Inverse text normalization API for other programming languages (#1019)

java-api-examples/InverseTextNormalizationNonStreamingParaformer.java

@@ -0,0 +1,54 @@
+// Copyright 2024 Xiaomi Corporation
+
+// This file shows how to use an offline paraformer, i.e., non-streaming paraformer,
+// to decode files with inverse text normalization.
+import com.k2fsa.sherpa.onnx.*;
+
+public class InverseTextNormalizationNonStreamingParaformer {
+  public static void main(String[] args) {
+    // please refer to
+    // https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-paraformer/paraformer-models.html#csukuangfj-sherpa-onnx-paraformer-zh-2023-03-28-chinese-english
+    // to download model files
+    String model = "./sherpa-onnx-paraformer-zh-2023-03-28/model.int8.onnx";
+    String tokens = "./sherpa-onnx-paraformer-zh-2023-03-28/tokens.txt";
+
+    // https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/itn-zh-number.wav
+    String waveFilename = "./itn-zh-number.wav";
+
+    // https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/itn_zh_number.fst
+    String ruleFsts = "./itn_zh_number.fst";
+
+    WaveReader reader = new WaveReader(waveFilename);
+
+    OfflineParaformerModelConfig paraformer =
+        OfflineParaformerModelConfig.builder().setModel(model).build();
+
+    OfflineModelConfig modelConfig =
+        OfflineModelConfig.builder()
+            .setParaformer(paraformer)
+            .setTokens(tokens)
+            .setNumThreads(1)
+            .setDebug(true)
+            .build();
+
+    OfflineRecognizerConfig config =
+        OfflineRecognizerConfig.builder()
+            .setOfflineModelConfig(modelConfig)
+            .setDecodingMethod("greedy_search")
+            .setRuleFsts(ruleFsts)
+            .build();
+
+    OfflineRecognizer recognizer = new OfflineRecognizer(config);
+    OfflineStream stream = recognizer.createStream();
+    stream.acceptWaveform(reader.getSamples(), reader.getSampleRate());
+
+    recognizer.decode(stream);
+
+    String text = recognizer.getResult(stream).getText();
+
+    System.out.printf("filename:%s\nresult:%s\n", waveFilename, text);
+
+    stream.release();
+    recognizer.release();
+  }
+}

java-api-examples/run-inverse-text-normalization-paraformer.sh

@@ -0,0 +1,46 @@
+#!/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 ./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 ./itn-zh-number.wav ]; then
+  curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/itn-zh-number.wav
+fi
+
+if [ ! -f ./itn_zh_number.fst ]; then
+  curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/itn_zh_number.fst
+fi
+
+java \
+  -Djava.library.path=$PWD/../build/lib \
+  -cp ../sherpa-onnx/java-api/build/sherpa-onnx.jar \
+  InverseTextNormalizationNonStreamingParaformer.java