10.AI large model offline voice assistant

1. Offline Voice Configuration

Before setting up automatic startup, we must ensure that the program itself can operate independently in an offline state. This requires modifying the configuration file.

1. Locate the Configuration File: In your project code, find and open the configuration file:

   config/yahboom.yaml

2. Modify Configuration Parameters: Please check the following parameters in the file and ensure that their values ​​match those shown below. If the parameters do not exist, add them.

   ​x
   asr:                                    #Voice node parameters
     ros__parameters:
       VAD_MODE: 2                         #VAD sensitivity
       sample_rate: 16000                  #ASR audio sampling rate
       frame_duration_ms:  30              #VAD frame size in milliseconds
       use_oline_asr: False                #Whether to use online ASR recognition (True for online, False for offline)
       mic_serial_port: "/dev/ttyUSB0"     #Microphone serial port alias
       mic_index: 0                        #Microphone index
       language: 'en'                      #ASR language
       regional_setting : "international"  #international：International Edition  China：China internal version
   ​
   model_service:                          #Model server node parameters
     ros__parameters:
       language: 'en'                      #Large Model Interface Language
       useolinetts: False                   #Whether to use online speech synthesis (True to use online, False to use offline)
   ​
        # Large model configuration
       # llm_platform: 'ollama'              # Optional platforms: 'ollama', 'tongyi', 'spark', 'qianfan', 'openrouter'
       llm_platform: 'ollama'              # Currently selected large model platform
       regional_setting : "international" 
   ​
   

   • use_oline_asr and useolinetts must be set to False.
   • llm_platform must be set to ollama.

   This setting will make everything offline.

3. Save the file and recompile the project to apply the changes:

   xxxxxxxxxx
   cd ~/yahboom_ws
   colcon build
   source install/setup.bash
   

After completing this step, the program is already a purely offline voice service.

2. Create a Startup Service (Systemd)

Now, we will create a systemd service to automatically run largemodel_control.launch.py at system startup.

2.1 Create a Startup Script

To ensure systemd can properly load the ROS2 environment, it's best to create a simple bash script to encapsulate our startup commands.

1. Create the script file:

   In the directory (~/yahboom_ws/src/largemodel/), create a file named start_largemodel.sh.

   xxxxxxxxxx
   vim ~/yahboom_ws/src/largemodel/start_largemodel.sh
   

2. Write script content: Copy and paste the following content into the script file.

   xxxxxxxxxx
   #!/bin/bash
   ​
   sleep 10
   gnome-terminal -- bash -c "export RUN_PROGRAMS='ros2 launch largemodel largemodel_control.launch.py';exec bash"
   

   IMPORTANT: Please make sure to replace /home/sunrise/ in the script with your own user home directory path.

3. Save and exit

4. Give the script execution permissions:

   xxxxxxxxxx
   chmod +x ~/yahboom_ws/src/largemodel/start_largemodel.sh
   

5. Add Execution Command to .bashrc

Open ~/.bashrc.

xxxxxxxxxx
vim ~/.bashrc

Copy the following content to the very bottom of the file.

xxxxxxxxxx
eval $RUN_PROGRAMS

Save and exit.

2.2 Creating the Startup File

1. Open the system terminal, then create and edit the start_largemodel.desktop startup file:

xxxxxxxxxx
vim ~/.config/autostart/start_largemodel.desktop

2. Copy the following content into start_largemodel.desktop, then save and exit.

xxxxxxxxxx
[Desktop Entry]
Type=Application
Exec=sh /home/jetson/yahboom_ws/src/largemodel/start_largemodel.sh
Hidden=false
NoDisplay=false
X-GNOME-Autostart-enabled=true
Name[en_US]=start_largemodel
Name=start_largemodel
Comment[en_US]=
Comment=

In the above configuration: Exec specifies the command used to execute the script; X-GNOME-Autostart-enabled determines whether the program launches automatically upon system startup; and Name specifies the display name.

Restart the system, and the startup program will automatically launch upon boot.

xxxxxxxxxx
sudo reboot

3. Startup Management

After restarting the system, a system terminal window will pop up, automatically running the voice assistant program. If you need to temporarily exit the program, press the [Ctrl+C] keys, and then close the terminal window.

3.1 Disabling the Startup Program

If you no longer require the program to launch automatically upon system startup, edit the start_largemodel.desktop startup file. Change the X-GNOME-Autostart-enabled parameter to false, then save and exit. This ensures that the program will not launch the next time the system starts up.

xxxxxxxxxx
vim ~/.config/autostart/start_largemodel.desktop

Example Content:

xxxxxxxxxx
[Desktop Entry]
Type=Application
Exec=sh /home/jetson/yahboom_ws/src/largemodel/start_largemodel.sh
Hidden=false
NoDisplay=false
X-GNOME-Autostart-enabled=false
Name[en_US]=start_largemodel
Name=start_largemodel
Comment[en_US]=
Comment=

3.2 Enabling the Startup Program

If you require the program to launch automatically upon system startup, edit the start_largemodel.desktop startup file. Change the X-GNOME-Autostart-enabled parameter to true, then save and exit. Upon restarting the system, the program will launch automatically.

xxxxxxxxxx
vim ~/.config/autostart/start_largemodel.desktop

Example Content:

xxxxxxxxxx
[Desktop Entry]
Type=Application
Exec=sh /home/jetson/yahboom_ws/src/largemodel/start_largemodel.sh
Hidden=false
NoDisplay=false
X-GNOME-Autostart-enabled=true
Name[en_US]=start_largemodel
Name=start_largemodel
Comment[en_US]=
Comment=
​