Real-time Virtual Appliance

High Level Summary

This release provides new Improved language packs for all Speechmatics' 31 commercially available languages with each language now contain a standard and enhanced model. The standard is the default model with the same or slightly improved accuracy before. The enhanced model is more accurate for all languages, and must be explicitly requested in the configuration. The enhanced model requires more compute resources to run and specific hardware. Please refer to the Install/Admin Guide on our recommendations for running the enhanced model.

Important Notices

Speechmatics now supports exclusively speechmatics-python for use in both our Real-time Container and our Real-time Virtual Appliance. The older library smwebsocket-py will still work, but is not compatible with the new enhanced model and is no longer supported. Please see here for access to speechmatics-python.

The new enhanced model has increased compute requirements and new recommended AVX flags. Each concurrent worker will require at least 3GB of memory and up to 5GB if using other features such as Custom Dictionary. Please check the updated system requirements in the installation guide and ensure your hardware meets Speechmatics' recommendations. Otherwise you may see a slow down in processing speed when using the enhanced model. It is also now necessary to run the appliance on processors that support AVX2 in order to take advantage of latest performance optimisations for both the standard and enhanced model for all language packs.

If you are importing an appliance through VirtualBox, and AVX flags are not automatically enabled, you can also take advantage of the the performance benefits from AVX 2 following these guidelines.

What's New

3.8.0

  • New improved language packs for all 31 languages. By default a language pack will contain a standard and enhanced model for all 31 languages. The standard model is available to use, with no user change required. For using the enhanced model refer to the API guide for details
  • General improvements in pop culture terms recognition for the English language pack
  • Removal of foreign characters from English and German language packs
  • Profanity tagging in Italian and Spanish
  • Chinese Mandarin language pack now supports Traditional as well as Simplified Mandarin. Please see API guide for guidelines of how to do so

Known Limitations

The following are known issues in this release:

Issue IDSummaryDetailed Description and Possible Workarounds
REQ-1409Proteus HCL with <unk> causes out of memory errorA custom dictionary list that contains the word '' causes the worker to crash.
REQ-7549Memory leak affecting gRPCThere is a small memory leak in the gRPC Python server https://github.com/grpc/grpc/issues/5913.
REQ-10160Advanced punctuation for Spanish (es) does not contain inverted marks.Inverted marks [ ¿ ¡ ] are not currently available for Spanish advanced punctuation.
REQ-10627Double full stops when acronym is at the end of the sentenceIf there is an acronym at the end of the sentence, then a double full stop will be output, for example: "team G.B.."
REQ-11792Speaker change token positioning is incorrectWe are aware of a consistent mis-placing of the speaker change token after the first word of the new speakers' sentence rather than before it.
REQ-12202High memory usage when using custom dictionaryIt has been observed that when using custom dictionary an additional 800-1700MB of memory is required (depending on the size of the wordlist used).
REQ-16256Heavy usage of RAM when swapping between 8kHz and 16kHz inputWhere multiple persistent workers are configured with Custom Dictionary that swap between 8kHz and 16kHz input, this can cause a memory leak that causes the container to crash. If this starts to impact services it is recommended to restart all the services with the management API or drop the worker count to 1 and then increase it again
REQ-20261The Japanese language pack may output fewer punctuation marks in certain scenariosIn some cases, users may see a decreased output in punctuation marks when transcribing in Japanese. Adjusting punctuation sensitivity sessions may improve output

Supported Platforms

Virtual Appliance image (OVA) for installation on:

  • VMware ESXi 6.5+ or VMware Workstation Player.
  • VirtualBox 5.2+
  • Amazon EC2

See the Installation and Admin Guide for details on the minimum specifications for the VM. The maximum number of concurrent jobs (maxworkers) that you can run on a single appliance is 30.

Form Factors

There are five variants of the Real-time Virtual Appliance.

VariantImage SizeMax. Disk SpaceLanguages
nano9GB40GBen
mini14GB40GBen, de, es
midi27GB60GBen, de, es, fr, ko, ja, nl, pt
maxi45GB80GBen, de, es, fr, ko, ja, nl, pt, it, da, pl, ca, hi, ru, sv
plus47GB80GBen, cmn, no, ar, bg, cs, el, fi, hu, hr, lt, lv, ro, sk, sl, tr, ms

Upgrade Path

Remove the license from your old appliance (see the Admin Guide), then re-import the new OVA and configure networking as per the Installation and Admin guide. You will need to re-apply the license code you have once the OVA has imported.

Installation

Upload the OVA to VMWare ESX, VMWare Workstation Player, or VirtualBox. See the Installation and Admin Guide for more information.