Release notes 4.7.0

Release date 4th March 2024

Summary

This page highlights all the changes, new features and bugs addressed within the LumenVox Containers version 4.7.0 release (this incorporates 4.6.1, 4.6.2 and 4.6.3 changes). This change affects Speech products. This version is not available for Voice biometric products, this will be made available in upcoming releases.

This release builds upon the 4.6.0 release - see https://lumenvox.capacity.com/article/522226/release-notes-4-6-0

Highlights

Secure context implemented.
Memory leaks in ASR & TTS resolved.
Changes made to cater for custom acoustic models.
Licensing enhancements made.
New Prometheus metrics added.

*Note: For TTS, we recommend that text not exceed 4mb (this is roughly 1300 Characters with spaces or around 250 words)

**Note: For Transcription, we recommend that users not exceed 90 minutes of transcribed audio due to gRPC size limits.

What’s new on LumenVox Cloud 4.7.0

New Features

Secure context is implemented to allow for clients to redact sensitive information from logs
Russian ASR/Transcription model now publicly available for version 4.X

Updates

Licensing updates
- Licensing updated to round to up to the nearest second.
- Licensing for grammar-based ASR updated to aggregate grammar usage across grammars utilized.
- TTS can now be counted by number of characters used in addition to minutes.
New Prometheus metrics added:
- session_active_streams
- asr_active_europa_requests
Memory leak issues resolved in ASR & TTS.
Custom acoustic models can now be accommodated.
Improvements made to ITN processing.
Interaction sub-type added to cater for grammar-based transcriptions.
Support added for X509 for Mongo authentication with password/passphrase.
Updates ASR to use STREAM_BEGIN with offset.
Decode/recognition timeout added to ASR/Transcription requests.
Postprocess flag to gRPC transcription added for Apple.
Issues with retrieving archived audio larger than 4MB resolved.
Additional MRCP functionality added into new architecture e.g. implement out of service and save-wavform.
Various changes applied to the analysis portal including catering for large audio files and catering for MRCP transcription interactions.

Installation notes

The following helm chart can be used

Helm Chart

Note that for MRCP there is no helm chart but a docker compose file. MRCP will run on its own Docker virtual machine which will integrate into the Kubernetes cluster.

Upgrade procedures

Upgrade or migration from previous versions is supported. Please contact LumenVox to discuss.

Updated API guide

APIs for all speech products available on version 4.6 can be obtained here: https://developer.lumenvox.com/4.7.0/

Information for voice biometric products relates to version 3.4.0-3.4.3

Model versions as part of the release

ASR - 4.1.0

TTS - 1.0 sample rate 22

VB - 2.1.15

VB incorporates Selene 2.4.3 which was integrated into the Container stack

Model version changes

None

Was this article helpful?