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
Kaldi Speech Recognition (KaldiSR) Plugin 1.1.0 to the UniMRCP Server (UMS) has been released.
The plugin is based on the following components:
- UniMRCP Server 1.5.0
- Kaldi GStreamer Server
- Libevent 2.1.8
- Rapidjson 1.1.0
The binaries are currently available for the following Linux distributions:
- Red Hat / CentOS 7
- Ubuntu 16.04 LTS
This release fixes and improves processing of several error cases.
The detailed list of changes introduced in this release follows.
Fixed Problems
- When the MRCP client closes session while recognition is in-progress, instead of waiting for the recognition to complete, close the WebSocket connection and respond straightaway.
- When the WebSocket connection hangs up while recognition is in-progress, properly handle the disconnect event and terminate the recognition with an error.
- Reconnect to the GStreamer server on each recognition attempt placed in the scope of the same MRCP session, since the previous connection, if any, is unconditionally terminated by the GStreamer server.
http://www.unimrcp.org/kaldisr
Thank you for using UniMRCP.
--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org
