Downloads
Repository
Documentation
Issues
Project Media
Google Cloud
Microsoft Azure
Amazon
Nuance Mix
OpenAI
SoundHound
IBM Watson
NVIDIA
Verbio
Deepgram
Yandex Cloud
Speechmatics
ASAPP
GoVivace
Voci
Kaldi
Platforms
Microsoft Azure Speech Recognition (SR) Plugin 1.30.0 to the UniMRCP Server (UMS) has been released.
The plugin is based on the following components:
- Microsoft Speech WebSocket Protocol
- Libevent 2.1.9
- Rapidjson 1.1.0
The plugin supports the following endpoints:
- Speech Service (regional)
- Custom Speech Service (regional)
- Speech Service (containerized)
- Custom Speech Service (containerized)
- Speech Service (private)
- Custom Speech Service (private)
The plugin is available for the following UMS versions:
- 1.7.0
- 1.8.0
The binaries are currently available for the following Linux distributions:
- Red Hat 8
- unimrcp-azure-sr-1.7.28-1.el8.x86_64.rpm
- unimrcp-azure-sr-1.8.8-1.el8.x86_64.rpm
- Red Hat 9
- unimrcp-azure-sr-1.7.28-1.el9.x86_64.rpm
- unimrcp-azure-sr-1.8.8-1.el9.x86_64.rpm
- Ubuntu 20.04 LTS
- unimrcp-azure-sr_1.7.28-focal_amd64.deb
- unimrcp-azure-sr_1.8.8-focal_amd64.deb
- Ubuntu 22.04 LTS
- unimrcp-azure-sr_1.7.28-jammy_amd64.deb
- unimrcp-azure-sr_1.8.8-jammy_amd64.deb
This release adds support for profiles of custom models. The release also allows to specify a custom model or a profile via vendor-specific parameters.
The detailed list of changes introduced in this release follows.
New Features
- Added support for profiles of custom models where a custom model is identified by the profile name and the language.
- Allow to specify a custom model or its profile via vendor-specific parameters.
Fixed Problems
- None.
Configuration Parameters
- Added new attributes 'cid' and 'cid-profile' to the element 'ws-streaming-recognition'.
Miscellaneous
- Updated the Usage Guide to reflect the changes introduced in this release.
Visit the Azure SR plugin page for more information.
Thank you for using UniMRCP.
--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org
