Deepgram Speech Recognition (SR) Plugin 1.3.0 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 7
- unimrcp-deepgram-sr-1.7.6-1.el7.x86_64.rpm
- unimrcp-deepgram-sr-1.8.4-1.el7.x86_64.rpm
- Red Hat 8
- unimrcp-deepgram-sr-1.7.6-1.el8.x86_64.rpm
- unimrcp-deepgram-sr-1.8.4-1.el8.x86_64.rpm
- Red Hat 9
- unimrcp-deepgram-sr-1.7.6-1.el9.x86_64.rpm
- unimrcp-deepgram-sr-1.8.4-1.el9.x86_64.rpm
- Ubuntu 20.04 LTS
- unimrcp-deepgram-sr_1.7.6-focal_amd64.deb
- unimrcp-deepgram-sr_1.8.4-focal_amd64.deb
- Ubuntu 22.04 LTS
- unimrcp-deepgram-sr_1.7.6-jammy_amd64.deb
- unimrcp-deepgram-sr_1.8.4-jammy_amd64.deb
This release allows to specify multiple 'deepgram.tag' parameters. The release also provides a few fixes and improvements.
The detailed list of changes introduced in this release follows.
New Features
- Allow to specify multiple 'deepgram.tag' parameters.
- When 'vad_events' is set to 'true', derive START-OF-INPUT from 'SpeechStarted' event.
- Use 'speech_final' flag as an indication of input completion when 'single-utterance' is set to 'false'.
Fixed Problems
- Skip processing of new messages received from Deepgram when connection is closing.
- Make sure the keep-alive timer is properly stopped when start-of-input is set to internal. This issue could possibly cause a segfault.
Configuration Parameters
Miscellaneous
Visit the Deepgram plugin page for more information.
Thank you for using UniMRCP.
--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org
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
Announcement Group