Integrate Audio Transcription Virtual Appliance

It is recommended that you integrate the audio transcription virtual appliance into Sintelix prior to ingesting audio files.

Sintelix currently supports the nano version which includes Global English, and the mini version which includes Global English, German and Spanish language.

The list of requirements for the installation are as follows:

Host Requirements

The host machine must have enough resources (processor, memory and storage) to run the hypervisor; the guest Virtual Machines (VMs) you intend to host on it; plus any other processes you expect to run.

The following hypervisors are supported:

  • VMware®
  • VirtualBox
  • AWS EC2

The host machine requires a processor with the following minimum specification:

Intel® Xeon® CPU E5-2630 v4 (Sandy Bridge) 2.20GHz (or equivalent).

This is important because these chipsets (and later ones) support Advanced Vector Extensions (AVX). The machine your hypervisor has must be AVX enabled. The machine learning algorithms used by the transcription engine requires the performance optimisations that AVX provides. You must also ensure that your hypervisor has AVX enabled.

Guest Requirements

The Virtual Appliance must be allocated the following minimum specification:

  • 2 vCPUs
  • 8 GB RAM
  • Up to 44GB hard disk space
Scalability

The transcription engine is capable of handling multiple transcription jobs (workers) dependent upon the resources available within the VM.

In general terms, each concurrent worker will require 1vCPU and up to 5 GB, depending on the quality of the audio, per worker thread enabled.

Firewall Ports

There are several firewall rules that may need to be enabled to ensure the communication can be made to the virtual appliance. The following are some:

  • 8080/TCP
  • 3000/TCP
  • 8082/TCP