You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In order to be able to run whisper-tiny on my Jetson Nano for real time voice recognition, ChatGPT recommended for me to build a specific version which is 1.11.0.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hello there,
In order to be able to run whisper-tiny on my Jetson Nano for real time voice recognition, ChatGPT recommended for me to build a specific version which is 1.11.0.
My current setup is:
lsb_release -a: Ubuntu 22.04.5 LTS (GNU/Linux 4.9.337-tegra aarch64)
gcc --version: gcc (GCC) 8.4.0, I also have version 11
g++ --version: g++ (GCC) 8.4.0, I also have version 11
nvcc --version:
Build cuda_10.2_r440.TC440_70.29663091_0
cat /usr/include/cudnn_version.h | grep CUDNN_MAJOR -A 2: 8.5.0
python3 --version: Python 3.10.12
echo $PATH:
/usr/local/cuda/bin:/home/jetson/.local/bin:/home/jetson/gcc-8.4.0/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin
echo $LD_LIBRARY_PATH:
/home/jetson/gcc-8.4.0/lib64
Find attached a partial output log for the execution of build.py using this full command:
python3 tools/ci_build/build.py
--config Release
--build_shared_lib
--build_wheel
--use_cuda
--cuda_home /usr/local/cuda
--cudnn_home /usr/lib/aarch64-linux-gnu
--skip_tests
--parallel
--build_dir build
--cmake_extra_defines
CMAKE_CUDA_COMPILER="/usr/local/cuda/bin/nvcc"
CMAKE_CUDA_HOST_COMPILER="/home/jetson/gcc-8.4.0/bin/g++"
CMAKE_SYSTEM_PROCESSOR=aarch64
CMAKE_C_FLAGS="-march=armv8-a"
CMAKE_CXX_FLAGS="-Wno-deprecated-copy -march=armv8-a -mno-outline-atomics"
CMAKE_EXE_LINKER_FLAGS="-L/usr/lib/aarch64-linux-gnu -lstdc++"
CMAKE_VERBOSE_MAKEFILE=ON
onnxruntime_DISABLE_WARNINGS_AS_ERRORS=ON
build.py partial output.txt
I was able to reach 98 % so I am almost there.
If anyone has experience building ONNX Runtime on Jetson platforms or can point me in the right direction, I would be very grateful.
Kind regards!
Beta Was this translation helpful? Give feedback.
All reactions