Build an ML framework for Arm

The framework you choose may depend on the application you wish to run. This example uses Baidu's DeepSpeech 2, a state-of-the-art speech recognition system that provides very high-quality models for both English and Chinese.

DeepSpeech 2 is built on Baidu's PaddlePaddle framework. Although less well-known than TensorFlow, it is just as easy to build and configure on an Armv8 system.

The instructions provided here work on Ubuntu 16.04 LTS running on a type 2A server. For reference, the official guide for building PaddlePaddle from source is here:

Install dependencies

Most dependencies are already pre-built for Armv8. Logged in to the server, enter the following to a command line to obtain and install the dependencies from standard repositories:

apt-get update
apt-get -y install python-dev python-pip python-numpy python-scipy python-wheel git cmake swig golang libfreetype6-dev libpng12-dev libopenblas-dev
pip install protobuf
git clone
cd recordio/python
pip install -e .
cd ../..

Build PaddlePaddle

Building from source can take several hours. Once complete, you can copy the *.whl file and deploy it directly onto subsequent servers. To build from source:

git clone
cd Paddle
mkdir build
cd build
make -j96
cd ../.. 

Install PaddlePaddle

Installing the built package is straightforward.

  1. Display the contents of the python/dist directory by entering the ls command. Note the version number in the name of the .whl file.
  2. Enter this command and add the version number that you noted in step 1:

    pip install Paddle/build/python/dist/paddlepaddle*.whl
Previous Next