Support using onnxruntime 1.16.0 with CUDA 11.4 on Jetson Orin NX (Linux arm64 GPU). (#1630)

* Support using onnxruntime 1.16.0 with CUDA 11.4 on Jetson Orin NX.

The pre-built onnxruntime libs are provided by the community
using the following command:

```bash
./build.sh --build_shared_lib --config Release --update \
  --build --parallel --use_cuda \
  --cuda_home /usr/local/cuda \
  --cudnn_home /usr/lib/aarch64-linux-gnu 2>&1 | tee my-log.txt
```

See also https://github.com/microsoft/onnxruntime/discussions/11226

---

Info about the board:

```
Model: NVIDIA Orin NX T801-16GB - Jetpack 5.1.4 [L4T 35.6.0]
```

```
nvidia@nvidia-desktop:~/Downloads$ head -n 1 /etc/nv_tegra_release
# R35 (release), REVISION: 6.0, GCID: 37391689, BOARD: t186ref, EABI: aarch64, DATE: Wed Aug 28 09:12:27 UTC 2024

nvidia@nvidia-desktop:~/Downloads$ uname -r
5.10.216-tegra

nvidia@nvidia-desktop:~/Downloads$ lsb_release -i -r
Distributor ID:	Ubuntu
Release:	20.04

nvidia@nvidia-desktop:~/Downloads$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:43:33_PDT_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0

nvidia@nvidia-desktop:~/Downloads$ dpkg -l libcudnn8
Desired=Unknown/Install/Remove/Purge/Hold
| Status=Not/Inst/Conf-files/Unpacked/halF-conf/Half-inst/trig-aWait/Trig-pend
|/ Err?=(none)/Reinst-required (Status,Err: uppercase=bad)
||/ Name           Version              Architecture Description
+++-==============-====================-============-=================================
ii  libcudnn8      8.6.0.166-1+cuda11.4 arm64        cuDNN runtime libraries

nvidia@nvidia-desktop:~/Downloads$ dpkg -l tensorrt
Desired=Unknown/Install/Remove/Purge/Hold
| Status=Not/Inst/Conf-files/Unpacked/halF-conf/Half-inst/trig-aWait/Trig-pend
|/ Err?=(none)/Reinst-required (Status,Err: uppercase=bad)
||/ Name           Version            Architecture Description
+++-==============-==================-============-=================================
ii  tensorrt       8.5.2.2-1+cuda11.4 arm64        Meta package for TensorRT
```

build-aarch64-linux-gnu.sh

@@ -1,4 +1,25 @@
 #!/usr/bin/env bash
+#
+# Usage of this file
+#
+# (1) Build CPU version of sherpa-onnx
+#    ./build-aarch64-linux-gnu.sh
+#
+# (2) Build GPU version of sherpa-onnx
+#
+#   (a) Make sure your board has NVIDIA GPU(s)
+#
+#   (b) For Jetson Nano B01 (using CUDA 10.2)
+#
+#       export SHERPA_ONNX_ENABLE_GPU=ON
+#       export SHERPA_ONNX_LINUX_ARM64_GPU_ONNXRUNTIME_VERSION=1.11.0
+#       ./build-aarch64-linux-gnu.sh
+#
+#   (c) For Jetson Orin NX (using CUDA 11.4)
+#
+#       export SHERPA_ONNX_ENABLE_GPU=ON
+#       export SHERPA_ONNX_LINUX_ARM64_GPU_ONNXRUNTIME_VERSION=1.16.0
+#       ./build-aarch64-linux-gnu.sh
 
 if command -v aarch64-none-linux-gnu-gcc  &> /dev/null; then
   ln -svf $(which aarch64-none-linux-gnu-gcc) ./aarch64-linux-gnu-gcc
@@ -47,11 +68,6 @@ fi
 if [[ x"$SHERPA_ONNX_ENABLE_GPU" == x"" ]]; then
   # By default, use CPU
   SHERPA_ONNX_ENABLE_GPU=OFF
-
-  # If you use GPU, then please make sure you have NVIDIA GPUs on your board.
-  # It uses onnxruntime 1.11.0.
-  #
-  # Tested on Jetson Nano B01
 fi
 
 if [[ x"$SHERPA_ONNX_ENABLE_GPU" == x"ON" ]]; then
@@ -59,6 +75,11 @@ if [[ x"$SHERPA_ONNX_ENABLE_GPU" == x"ON" ]]; then
   BUILD_SHARED_LIBS=ON
 fi
 
+if [[ x"$SHERPA_ONNX_LINUX_ARM64_GPU_ONNXRUNTIME_VERSION" == x"" ]]; then
+  # Used only when SHERPA_ONNX_ENABLE_GPU is ON
+  SHERPA_ONNX_LINUX_ARM64_GPU_ONNXRUNTIME_VERSION="1.11.0"
+fi
+
 cmake \
   -DBUILD_PIPER_PHONMIZE_EXE=OFF \
   -DBUILD_PIPER_PHONMIZE_TESTS=OFF \
@@ -75,6 +96,7 @@ cmake \
   -DSHERPA_ONNX_ENABLE_JNI=OFF \
   -DSHERPA_ONNX_ENABLE_C_API=ON \
   -DSHERPA_ONNX_ENABLE_WEBSOCKET=ON \
+  -DSHERPA_ONNX_LINUX_ARM64_GPU_ONNXRUNTIME_VERSION=$SHERPA_ONNX_LINUX_ARM64_GPU_ONNXRUNTIME_VERSION \
   -DCMAKE_TOOLCHAIN_FILE=../toolchains/aarch64-linux-gnu.toolchain.cmake \
   ..