Deepgram Speech Recognition (SR) Plugin 1.4.1 to the UniMRCP Server (UMS) has been released.
The plugin is based on the following components:
- Deepgram WebSocket API
- Libevent 2.1.9
- Rapidjson 1.1.0
The plugin is available for the following UMS versions:
The binaries are currently available for the following Linux distributions:
- Red Hat 8
- unimrcp-deepgram-sr-1.7.9-1.el8.x86_64.rpm
- unimrcp-deepgram-sr-1.8.7-1.el8.x86_64.rpm
- Red Hat 9
- unimrcp-deepgram-sr-1.7.9-1.el9.x86_64.rpm
- unimrcp-deepgram-sr-1.8.7-1.el9.x86_64.rpm
- Ubuntu 20.04 LTS
- unimrcp-deepgram-sr_1.7.9-focal_amd64.deb
- unimrcp-deepgram-sr_1.8.7-focal_amd64.deb
- Ubuntu 22.04 LTS
- unimrcp-deepgram-sr_1.7.9-jammy_amd64.deb
- unimrcp-deepgram-sr_1.8.7-jammy_amd64.deb
This release fixes a regression introduced in 1.3.0 release resulting in an empty body in the RECOGNITION-COMPLETE event. The release also allows specifying multiple 'deepgram.redact' parameters similarly to 'deepgram.tag'.
The detailed list of changes introduced in this release follows.
New Features
- Allow to specify multiple 'deepgram.redact' parameters.
Fixed Problems
- Fixed a regression introduced in 1.3.0 release resulting in an empty body in the RECOGNITION-COMPLETE event. The issue was caused by a race condition while stopping the input based on the speech_final flag with single utterance set to false.
Configuration Parameters
Miscellaneous
Visit the Deepgram SR plugin page for more information.
Thank you for using UniMRCP.
--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org