Version: 3.5.0Virtual Appliance Changelog
- Rotate k3s logs on weekly basis
- Allow to set UI limits for Language Identification
- Allow to set UI limits for Speech Translation
- Allow to set UI limits for Voice Activity Detection
- Allow to set UI limits for Speaker Diarization
- Allow to set UI limits for Audio Quality Estimation
- Set components debug level to info
- Use dedicated error log for k3s
- Bump expected model for Enhanced Speech to Text Built on Whisper to 1.1.0
- Bump expected model for Speaker Identification to 5.2.0
- Bump expected model for Language Identification to 5.3.0
- Bump expected model for Speaker Diarization 5.1.0
- Bump expected model for Voice Activity Detection to 3.1.0
- Disable all microservices by default
- Add new default phonexia user
- Add Audio Quality Estimation technology microservice
- Add Voice Activity Detection technology microservice
- Print more information to system console
- Discourage disabling mandatory components
- Disable rate-limit on api, billing and rest-api-gateway components
- Use xl-5.1.0 model for speaker-identification
- Use debug log level for speaker-identification, language-identification,
speaker-diarization and media-conversion by default
- Improve run-diag-report.sh script output and result archive name
- Upgrade ingress-nginx helm chart to version 4.11.2
- Upgrade keda helm chart to version 2.15.1
- Upgrade dcgm-exporter helm chart to version 3.6.0
- Upgrade kube-prometheus-stack helm chart to version 65.0.0
- Upgrade nginx helm chart to version 18.2.2
- Upgrade reloader helm chart to version 1.1.0
- Upgrade k3s to 1.30.5
- Make diag report script user friendly
- Add diagnostics script
- Deploy configuration service
- Automatically resize both system and data disks
- Deploy speaker diarization
- Support for Hyper-V hypervisor
- Cloud-init for customer use is no longer disabled
- Speech engine images bumped from 3.61.0 to 3.62.0
- Enable ingress metrics for ingress without hostname
- Add language-identification technology
- Enable GPU sharing
- Deploy nvidia-device-plugin from helm chart
- Deploy nvidia-device-plugin to nvidia-device-plugin namespace instead of gpu
namespace
- Do not include models for speaker-identification and
enhanced-speech-to-text-built-on-whisper by default on data disk
- Deploy billing-related components
- Loading the licenses from secrets instead of values file
- Reloader which reloads the deployment every time its secret is edited
- Install yq
- Support running voiceprint-extraction on GPU
- Edit the way how secrets are loaded in Speech-to-Text-Phonexia and
Time-Analysis values
- Add comment explaining why disabling media-conversion is usually not a good
idea
- Update the Nvidia drivers to version 550
- Build in AWS instead of local infrastructure
- Use cloud-init for configuration
- Root (/) partition is merged with var partition (/var)
- Enable to configure parallelism in speech-to-text-phonexia and time-analysis
- Rename speech-to-text-whisper-enhanced to
enhanced-speech-to-text-built-on-whisper
- Upgrade Rocky Linux version to 9.4
- Fix language code for Levantine arabic
- Introduce extra environment variables for speech-to-text-whisper-enhanced
- Introduce max upload file size specification for filebrowser
- Increase inotify limits
- Move prometheus storage to data disk
- Admin-related backends are extracted to separate
ingressAdmin configuration
- Time-analysis reconfigured as onDemand instance by default
- Speech engine images bumped from 3.60.1 to 3.61.0
- Load models for speech-to-text-phonexia and time-analysis from data disk by
default
- Default value for maxFileSize UI limits set to 5MB instead of 5MiB
- Time-analysis is started as onDemand instance by default
- Allow to change api log level
- Allow to configure UI limits
- Add
time-analysis subchart
- Add options to change tmpdir volume for
speech-platform API and
media-conversion
- (Breaking change) Rename
speech-engine subchart to
speech-to-text-phonexia subchart
- Store models on data disk for each microservice separately
- Use free version of
media-conversion by default
- Start
nvidia-persistenced only when nvidia driver is loaded
- Enable startup probe for
speech-to-text-whisper-enhanced
- Automatically start
nvidia-persistenced daemon
- Add comments about api storage resources
- Use app frontend as landing page
- Expose admin console to
/admin uri
- Increase max data disk size to 20GB
- Disable GSP firmware in nvidia drivers
- Calculate
speech-to-text-whisper-enhanced capacity on GPU properly