Building DeepSpeech native client for Windows

Now we can build the native client of DeepSpeech and run inference on Windows using the C# client, to do that we need to compile the native_client.

Table of Contents


Inside the Visual Studio Installer enable MS Build Tools and VC++ 2019 v16.00 (v160) toolset for desktop.

If you want to enable CUDA support you need to follow the steps in the TensorFlow docs for building on Windows with CUDA.

We highly recommend sticking to the recommended versions of CUDA/cuDNN in order to avoid compilation errors caused by incompatible versions. We only test with the versions recommended by TensorFlow.

Getting the code

We need to clone mozilla/DeepSpeech.

git clone
git submodule sync tensorflow/
git submodule update --init tensorflow/

Configuring the paths

There should already be a symbolic link, for this example let’s suppose that we cloned into D:\cloned and now the structure looks like:

├── D:\
│   ├── cloned                 # Contains DeepSpeech and tensorflow side by side
│   │   └── DeepSpeech         # Root of the cloned DeepSpeech
│   │       ├── tensorflow     # Root of the cloned mozilla/tensorflow
└── ...

Change your path accordingly to your path structure, for the structure above we are going to use the following command if the symbolic link does not exists:

mklink /d "D:\cloned\DeepSpeech\tensorflow\native_client" "D:\cloned\DeepSpeech\native_client"

Adding environment variables

After you have installed the requirements there are few environment variables that we need to add to our PATH variable of the system variables.

MSYS2 paths

For MSYS2 we need to add bin directory, if you installed in the default route the path that we need to add should looks like C:\msys64\usr\bin. Now we can run pacman:

pacman -Syu
pacman -Su
pacman -S patch unzip

BAZEL path

For BAZEL we need to add the path to the executable, make sure you rename the executable to bazel.

To check the version installed you can run:

bazel version


Add your python.exe path to the PATH variable.

CUDA paths

If you run CUDA enabled native_client we need to add the following to the PATH variable.

C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.1\bin

Building the native_client

There’s one last command to run before building, you need to run the inside tensorflow cloned directory.

At this point we are ready to start building the native_client, go to tensorflow sub-directory, following our examples should be D:\cloned\DeepSpeech\tensorflow.


We will add AVX/AVX2 support in the command, please make sure that your CPU supports these instructions before adding the flags, if not you can remove them.

bazel build --workspace_status_command="bash native_client/" -c opt --copt=/arch:AVX --copt=/arch:AVX2 //


If you enabled CUDA in configuration command now you can add --config=cuda to compile with CUDA support.

bazel build --workspace_status_command="bash native_client/" -c opt --config=cuda --copt=/arch:AVX --copt=/arch:AVX2 //

Be patient, if you enabled AVX/AVX2 and CUDA it will take a long time. Finally you should see it stops and shows the path to the generated

Using the generated library

As for now we can only use the generated with the C# clients, go to native_client/dotnet/ in your DeepSpeech directory and open the Visual Studio solution, then we need to build in debug or release mode, finally we just need to copy to the generated x64/Debug or x64/Release directory.