ROS 2 inference for whisper.cpp.

• Install pyaudio, see install instructions.
• Build this repository, do

mkdir -p ros-ai/src && cd ros-ai/src && \
git clone https://github.com/gribes02/voice_command_robot.git && cd .. && \
colcon build --symlink-install --cmake-args -DWHISPER_CUDA=On --no-warn-unused-cli

Run the inference action server (this will download models to $HOME/.cache/whisper.cpp):

ros2 launch whisper_bringup bringup.launch.py

Run a client node (activated on space bar press):

ros2 run whisper_demos whisper_on_key

Ensure you have turtlebot3 downloaded to run the following command

ros2 launch turtlebot3_gazebo turtlebot3_world.launch.py 

Configure whisper parameters in whisper.yaml.

Action server under topic inference of type Inference.action.

• Encoder inference time: ggerganov/whisper.cpp#10 (comment)
• Compile with GPU support (might differ between platforms): https://github.com/ggerganov/whisper.cpp#nvidia-gpu-support-via-cublas WHISPER_CUBLAS=On