Skip to main content
Version: 4.0.0-rc1

Deployment to Proxmox

To deploy the Phonexia Speech Platform 4 Virtual Appliance, you need these two ZIP files, downloaded from Phonexia:
Virtual Appliance ZIP file
Licensed models ZIP file

Step 1: Import Virtual Appliance
  1. Extract the content of Speech Platform Virtual Appliance ZIP file.
  2. To import the virtual appliance to Proxmox via the web-based management interface, you need a file-based storage with import content type configured in Proxmox. On this storage, there will be an import folder - put the extracted OVF and VMDK files to this folder:
    speech-platform.vmware.ovf
    speech-platform-disk001.vmdk
    speech-platform-disk002.vmdk
    (You can upload the files there via the web interface - select the storage in the tree in the left pane, then select the Import item and click the Upload menu button).
  3. In the import storage, select the speech-platform.vmware.ovf file and click the Import menu button
  4. In the Import Guest dialog
    • on the General tab
      • make sure there are at least 4 cores and 32768 MB memory
      • keep the Format set to "QEMU image format (qcow2)"
      • depending on your hardware, you might want to set the CPU Type to "host"
    • on the Advanced tab
      • verify that the Disks section lists both source VMDK disks
      • change the SCSI Controller to "VirtIO SCSI single"
      • in the Network Interfaces section, change the interface Model to "VirtIO (paravirtualized)"
    • on the Resulting Config tab, verify the import parameters
  5. Click the Import button and watch the import progress in the Task viewer window.
    When the import is finished, close the Task viewer window.
 

After importing the virtual machine to Proxmox it's necessary to further change some of its parameters.

  1. Select the imported virtual machine in the tree in the left pane and select the Hardware section.
  2. Change the Machine to "q35" (for better performance and GPU Passthrough) and set the Version to "Latest".

Additional changes are required for GPU Passthrough:

  1. Still in the Hardware section, click the Add button and select PCI Device from the drop down list.
  2. In the Add: PCI Device dialog, select the Raw Device radio button and from the Device drop down list select the GPU. Then set the PCI-Express check box, so that the GPU is seen as PCIe device inside the virtual machine.
  3. Click Add to add the GPU device to the virtual machine configuration.

The virtual appliance is now ready and you can start it.

Step 2: Run Virtual Appliance

After you have imported and configured the setting of the virtual appliance, you can finally start it.

The console displays the boot log with various messages as startup tasks are completed. This typically takes several minutes.

When the system is fully up and running, the console shows a screen similar to this:

Rocky Linux 9.5 (Blue Onyx)
Kernel 5.14.0-503.14.1.e19_5-x86_64 on an x86_64

Welcome to Phonexia Speech Platform 3.7.0
.
.
.

speech-platform login:
Step 3: Upload licensed models and configure the platform

The virtual appliance distribution contains only the bare Speech Platform system. To actually breathe life into the system it's necessary to upload the licensed models to the appliance and configure the technologies.

These steps can be done either semi-automatically via the platform GUI, or manually via SSH access to the platform console.

The Virtual Appliance contains a Filebrowser tool, which simplifies some management tasks like uploading the models and accessing and editing the appliance configuration files.
The Filebrowser is accessible at http://<virtual appliance IP address>/filebrowser.

Open the Filebrowser and click on the upload icon in the top right corner, then click on the "File" option, browse for the licensed models ZIP file (licensed-models.zip). A small pop-up window in the bottom right corner will show the upload progress. You can also click on the up arrow to show the graphical progress bar.

When the upload is finished (progress is at 100 %), Filebrowser automatically starts extracting the uploaded ZIP file and then runs the automatic configuration script. While these processes are executed, the upload progress pop-up remains visible at 100%, seemingly doing nothing — don't worry, this indicates that background tasks are still running.

When the the progress pop-up disappears, it means that the extraction and configuration is finished and the system is ready for use.

The automatic configuration detects which models and licenses were extracted from the ZIP file and automatically turns on the corresponding technologies and configures them to use the provided models, and also detects the hardware — if a GPU is present, it enables GPU processing.