Yandex Speech Recognition (SR) Plugin 1.5.0 to the UniMRCP Server (UMS) has been released.
The plugin is based on the following components:
- UniMRCP Server 1.6.0
- Yandex SpeechKit Speech to Text API v2
- gRPC 1.20.0
- Protobuf 3.7.0
- Libevent 2.1.9
- Rapidjson 1.1.0
The binaries are currently available for the following Linux distributions:
- Red Hat / CentOS 7 (unimrcp-yandex-sr-1.6.6-1.el7.x86_64.rpm)
- Ubuntu 16.04 LTS (unimrcp-yandex-sr_1.6.6-xenial_amd64.deb)
- Ubuntu 18.04 LTS (unimrcp-yandex-sr_1.6.6-bionic_amd64.deb)
This release allows to control the format of instance element in returned NLSML results to optionally include name of recorded utterance. The release also allows to enable data logging at the service side for debugging purposes.
The detailed list of changes introduced in this release follows.
- If a new configuration parameter 'tag-format' is set to 'extended', then the instance element in NLSML result concatenates transcription result and name of recorded utterance using a character '|'.
- For debugging purposes, enable data logging at the service side by setting a new configuration parameter 'data-logging' to 'true'. No data is stored by default.
- Added a new attribute 'tag-format' to the element 'streaming-recognition'.
- Added a new attribute 'data-logging' to the element 'streaming-recognition'.
- Updated the Usage Guide to reflect the changes introduced in this release.
Visit the Yandex SR plugin page for more information.
Thank you for using UniMRCP.
Author of UniMRCP