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
Elevenlabs
Platforms
SoundHound Speech Recognition (SR) Plugin 1.1.0 to the UniMRCP Server (UMS) has been released.
The plugin is based on the following components:
- UniMRCP Server 1.7.0
- Houndify SDK 1.0.0
The binaries are currently available for the following Linux distributions:
- Red Hat / CentOS 7 (unimrcp-soundhound-sr-1.7.1-1.el7.x86_64.rpm)
- Red Hat / CentOS 8 (unimrcp-soundhound-sr-1.7.1-1.el7.x86_64.rpm)
- Ubuntu 18.04 LTS (unimrcp-soundhound-sr_1.7.1-bionic_amd64.deb)
- Ubuntu 20.04 LTS (unimrcp-soundhound-sr_1.7.1-focal_amd64.deb)
This release sets the language tag in request submitted to SoundHound API and also fixes an issue with the confidence score.
The detailed list of changes introduced in this release follows.
New Features
- Transparently set the language tag in the requests submitted to SoundHound API.
Fixed Problems
- Use the field 'ASRConfidence' instead of the field 'ConfidenceScore' to derive the confidence score from.
Configuration Parameters
- Changed the default language from 'en-US' to 'en' to conform to the format accepted by SoundHound API.
Miscellaneous
- Updated the Usage Guide to reflect the changes introduced in this release.
Visit the SoundHound SR plugin page for more information.
Thank you for using UniMRCP.
--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org
