This guide describes how to obtain and install binary packages for the NVIDIA Riva Speech Recognition (SR) plugin to the UniMRCP server on Debian-based Linux distributions. The document is intended for system administrators and developers.
Instructions provided in this guide are applicable to the following versions.
UniMRCP 1.7.0 and above
UniMRCP Riva SR Plugin 1.0.0 and above
The NVIDIA Riva Speech Skills platform must be installed separatelly. The implementation of the plugin is compatible with the following versions.
NVIDIA Riva Speech Skills 1.9.0-beta and above
UniMRCP deb packages are currently available for x86_64 (64-bit) architecture only.
|Operating System||Released||End of Support|
|Ubuntu 18.04 LTS (bionic)||March 2022||TBA|
|Ubuntu 20.04 LTS (focal)||March 2022||TBA|
Packages for other distributions can be developed and made available in the scope of an annual maintenance agreement.
UniMRCP binary packages are available to authenticated users only. In order to register a free account, please visit the following page.
A newly registered account needs to be verified by the user and then activated by the administrator prior further proceeding.
Account verification and activation.
The account credentials can be used to log in to the following websites.
Using the APT package handling utility (apt-get) is recommended for installation of UniMRCP binary packages.
Supply login information by creating a file /etc/apt/auth.conf.d/unimrcp.conf containing the following entry.
machine unimrcp.org login username password password
The username and password fields must be replaced with the corresponding account credentials.
Configure a repository by creating a file /etc/apt/sources.list.d/unimrcp.list containing the following entry.
deb [arch=amd64] https://unimrcp.org/repo/apt/ distr main
The distr field must be replaced with the corresponding distribution code name such as xenial, bionic, focal, etc. To determine the distribution code, use
Distribution code name.
For verification of binary packages, UniMRCP provides a public GnuPG key, which can be retrieved and installed as follows.
wget -O - https://unimrcp.org/keys/unimrcp-gpg-key.public | sudo apt-key add -
In order to check for updates and apply the changes in the APT configuration, use the following command.
sudo apt-get update
In order to install the Riva SR plugin, including all the dependencies, use the following command.
sudo apt-get install unimrcp-riva-sr
As a result, apt-get will check and prompt to download all the required packages by installing them in the directory /opt/unimrcp.
In order to install the additional data files for the sample client application umc, the following command can be used.
sudo apt-get install umc-addons
This package is optional and provides additional data to be used for validation of basic setup.
UniMRCP deb packages can be installed manually using the dpkg utility. Note, however, that the system administrator should take care of package dependencies and install all the packages in appropriate order.
The deb packages have the following naming convention:
The following is a list of UniMRCP deb packages required for the installation of the Riva SR plugin.
|unimrcp-riva-sr||Riva SR plugin to the server.|
|uninvidiaapis||NVIDIA APIs library built based on the proto files.|
|unigrpc||UniMRCP edition of the gRPC library.|
|unigrpc-deps||UniMRCP edition of the gRPC-deps library.|
|unigrpc||UniMRCP edition of the gRPC library.|
|umc-addons||Sample en-US data files used with umc. [Optional]|
|unilicnodegen||Node information retrieval tool, required for license deployment.|
|unimrcp-server||Shared library and application of the server.|
|unimrcp-client||Shared libraries and sample applications of the client. [Optional]|
|unimrcp-demo-plugins||Set of demo plugins to the server. [Optional]|
|unimrcp-common||Data common for the client and the server.|
|uniapr||UniMRCP edition of the Apache Portable Runtime (APR) library.|
|uniapr-util||UniMRCP edition of the Apache Portable Runtime Utility (APR-Util) library.|
|unisofia-sip||UniMRCP edition of the Sofia SIP library.|
Packages for APR, APR-Util and Sofia-SIP libraries must be installed first.
sudo dpkg --install uniapr_$aprversion-$distr_$arch.deb sudo dpkg --install uniapr-util_$apuversion-$distr_$arch.deb sudo dpkg --install unisofia-sip_$sofiaversion-$distr_$arch.deb
Then, a package containing common data for the client and the server, and a package for the server should follow.
sudo dpkg --install unimrcp-common_$universion-$distr_$arch.deb sudo dpkg --install unimrcp-server_$universion-$distr_$arch.deb
Next, a package containing the utility tool unilicnodegen, required for license deployment.
sudo dpkg --install unilicnodegen_$toolversion-$distr_$arch.deb
Next, packages containing the gRPC-deps and gRPC libraries.
sudo dpkg --install unigrpc-deps_$grpcversion-$distr_$arch.deb sudo dpkg --install unigrpc_$grpcversion-$distr_$arch.deb
Next, a package containing the NVIDIA APIs library.
sudo dpkg --install uninvidiaapis_$apisversion-$distr_$arch.deb
Finally, a package containing the Riva SR plugin should follow.
sudo dpkg --install unimrcp-riva-sr_$universion-$distr_all.deb
The Riva SR plugin to the UniMRCP server is a licensed software.
In order to obtain a trial license, node information must be retrieved and submitted for license generation.
Use the installed tool unilicnodegen to retrieve the node information.
As a result, a text file uninode.info will be saved in the current directory.
Consider the following procedure to place an order.
- Navigate to https://unispeech.io/rivasr.
- Under the section Obtain License, select
- License Variation: Trial
- License Term: 30-day
- License Type: Node-bound
- License Quantity: 2
Ther orders are normally processed within one business day. A license file will be provided as a result.
The license file needs to be placed into the directory /opt/unimrcp/data.
sudo cp umsrivasr_*.lic /opt/unimrcp/data
In order to load the Riva SR plugin into the UniMRCP server, open the file unimrcpserver.xml, located in the directory /opt/unimrcp/conf, and add the following entry under the XML element <plugin-factory>. Disable other recognition plugins, if available. The demo plugins for other resources can also be disabled.
<!-- Factory of plugins (MRCP engines) --> <plugin-factory> <engine id="Demo-Recog-1" name="demorecog" enable="false"/> <engine id="Riva-SR-1" name="umsrivasr" enable="true"/> <plugin-factory>
In order to enable log output from the plugin and set filtering rules, open the configuration file logger.xml, located in the directory /opt/unimrcp/conf, and add the following entry under the element <sources>.
<source name="RIVASR-PLUGIN" priority="INFO" masking="NONE"/>
Open the configuration file umsrivasr.xml, located in the directory /opt/unimrcp/conf, and specify a Riva service endpoint matching your deployment.
<streaming-recognition service-uri="127.0.0.1:50051" secure-transport="false" />
Validate your setup by using the sample UniMRCP client and server applications on the same host. The default configuration and data files should be sufficient for a basic test.
Launch the UniMRCP server application.
cd /opt/unimrcp/bin sudo ./unimrcpserver
In the server log output, check whether the plugin is normally loaded.
[INFO] Load Plugin [Riva-SR-1] [/opt/unimrcp/plugin/umsrivasr.so]
Next, check for the license information.
[NOTICE] UniMRCP Riva SR License -product name: umsrivasr -product version: 1.0.0 -license owner: Name -license type: trial -issue date: 2022-03-07 -exp date: 2022-04-06 -channel count: 2 -feature set: 0
Note: the optional package umc-addons must be installed for this test to work.
Launch the sample UniMRCP client application umc.
cd /opt/unimrcp/bin ./umc
Run a typical speech recognition scenario by issuing the command run gsr1 from the console of the umc client application.
This command sends a RECOGNIZE request to the server and then starts streaming a sample audio input file callsteve.pcm to recognize.
Check for the NLSML results to be returned as expected.
<?xml version="1.0"?> <result> <interpretation grammar="command" confidence="0.92"> <instance>call Steve</instance> <input mode="speech">call Steve</input> </interpretation> </result>
Visually inspect the log output for any possible warnings or errors.
Note that utterances are stored in the var directory, if the corresponding parameter is enabled in the configuration file umsrivasr.xml and/or requested by the client.