Add Java and Kotlin API for NeMo Canary models (#2359)

Add support for the NeMo Canary model in both Java and Kotlin APIs, wiring it through
JNI and updating examples and CI.

- Introduce OfflineCanaryModelConfig in Kotlin and Java with builder patterns
- Extend OfflineRecognizer to accept and apply the new canary config via setConfig
- Update JNI binding (GetOfflineConfig) and getOfflineModelConfig mapping (type 32), 
   plus examples and CI workflows

java-api-examples/NonStreamingDecodeFileNemoCanary.java

@@ -0,0 +1,56 @@
+// Copyright 2024 Xiaomi Corporation
+
+// This file shows how to use an offline NeMo Canary model, i.e.,
+// non-streaming NeMo Canary model, to decode files.
+import com.k2fsa.sherpa.onnx.*;
+
+public class NonStreamingDecodeFileNemoCanary {
+  public static void main(String[] args) {
+    // please refer to
+    // https://k2-fsa.github.io/sherpa/onnx/nemo/canary.html
+    // to download model files
+    String encoder = "./sherpa-onnx-nemo-canary-180m-flash-en-es-de-fr-int8/encoder.int8.onnx";
+    String decoder = "./sherpa-onnx-nemo-canary-180m-flash-en-es-de-fr-int8/decoder.int8.onnx";
+    String tokens = "./sherpa-onnx-nemo-canary-180m-flash-en-es-de-fr-int8/tokens.txt";
+
+    String waveFilename = "./sherpa-onnx-nemo-canary-180m-flash-en-es-de-fr-int8/test_wavs/en.wav";
+
+    WaveReader reader = new WaveReader(waveFilename);
+
+    OfflineCanaryModelConfig canary =
+        OfflineCanaryModelConfig.builder()
+            .setEncoder(encoder)
+            .setDecoder(decoder)
+            .setSrcLang("en")
+            .setTgtLang("en")
+            .setUsePnc(true)
+            .build();
+
+    OfflineModelConfig modelConfig =
+        OfflineModelConfig.builder()
+            .setCanary(canary)
+            .setTokens(tokens)
+            .setNumThreads(1)
+            .setDebug(true)
+            .build();
+
+    OfflineRecognizerConfig config =
+        OfflineRecognizerConfig.builder()
+            .setOfflineModelConfig(modelConfig)
+            .setDecodingMethod("greedy_search")
+            .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(English):%s\n", waveFilename, text);
+
+    stream.release();
+    recognizer.release();
+  }
+}

java-api-examples/README.md

@@ -24,11 +24,18 @@ This directory contains examples for the JAVA API of sherpa-onnx.
 
 ```bash
 ./run-non-streaming-decode-file-dolphin-ctc.sh
+./run-non-streaming-decode-file-fire-red-asr.sh
+./run-non-streaming-decode-file-moonshine.sh
+./run-non-streaming-decode-file-nemo-canary.sh
+./run-non-streaming-decode-file-nemo.sh
 ./run-non-streaming-decode-file-paraformer.sh
 ./run-non-streaming-decode-file-sense-voice.sh
+./run-non-streaming-decode-file-tele-speech-ctc.sh
+./run-non-streaming-decode-file-transducer-hotwords.sh
 ./run-non-streaming-decode-file-transducer.sh
+./run-non-streaming-decode-file-whisper-multiple.sh
 ./run-non-streaming-decode-file-whisper.sh
-./run-non-streaming-decode-file-nemo.sh
+./run-non-streaming-decode-file-zipformer-ctc.sh
 ```
 
 ## Non-Streaming Speech recognition with homophone replacer

java-api-examples/run-non-streaming-decode-file-nemo-canary.sh

@@ -0,0 +1,37 @@
+#!/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-nemo-canary-180m-flash-en-es-de-fr-int8/encoder.int8.onnx ]; then
+  curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-canary-180m-flash-en-es-de-fr-int8.tar.bz2
+  tar xvf sherpa-onnx-nemo-canary-180m-flash-en-es-de-fr-int8.tar.bz2
+  rm sherpa-onnx-nemo-canary-180m-flash-en-es-de-fr-int8.tar.bz2
+fi
+
+java \
+  -Djava.library.path=$PWD/../build/lib \
+  -cp ../sherpa-onnx/java-api/build/sherpa-onnx.jar \
+  NonStreamingDecodeFileNemoCanary.java