Powered by Universal Speech Solutions LLC

Menu

Google Dialogflow (GDF) Plugin 1.26.0 to the UniMRCP Server (UMS) has been released.

The plugin is based on the following components:

  • Google APIs 1.6.0
  • gRPC 1.30.3
  • Protobuf 3.12.2

The plugin supports the following Dialogflow API versions:

  • v2
  • v2beta1
  • v3
  • v3beta1

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 / CentOS 7
    • unimrcp-gdf-1.7.16-1.el7.x86_64.rpm
    • unimrcp-gdf-1.8.3-1.el7.x86_64.rpm
  • Red Hat / CentOS 8
    • unimrcp-gdf-1.7.16-1.el8.x86_64.rpm
    • unimrcp-gdf-1.8.3-1.el8.x86_64.rpm
  • Ubuntu 18.04 LTS
    • unimrcp-gdf_1.7.16-bionic_amd64.deb
    • unimrcp-gdf_1.8.3-bionic_amd64.deb
  • Ubuntu 20.04 LTS
    • unimrcp-gdf_1.7.16-focal_amd64.deb
    • unimrcp-gdf_1.8.3-focal_amd64.deb

This release introduces two new minor capabilities and fixes a regression introduced in GDF 1.24.0 release.

The detailed list of changes introduced in this release follows.
New Features
  • Allow to derive the confidence score either from intent detection (default) or speech transcription.
  • Allow to specify the behavior whether START-OF-INPUT is required or implied before RECOGNITION-COMPLETE is sent.
Fixed Problems
  • Fixed the value of the 'input' element in the NLSML result. This is a regression introduced in GDF 1.24.0.
Configuration Parameters
  • Added a new attribute 'start-of-input-event' to the element 'streaming-recognition'.
  • Added a new attribute 'confidence-source' to the element 'results'.
Miscellaneous
  • Updated the Usage Guide to reflect the changes introduced in this release.

Visit the GDF plugin page for more information.

Thank you for using UniMRCP.

--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org

Latest News


This release adds support for speech transcription using native 8 kHz audio stream without upsampling to 16 kHz. ...Read more
This release adds support for connect timeout and graceful closure of WebSocket connection. The release also allows to specify the HTTP proxy ...Read more
This release adds support for the new Deepgram Flux (/v2/listen) API. ...Read more
View all posts
Google Cloud

Products Provided By

Universal Speech Solutions LLC

previous arrow
next arrow