Powered by Universal Speech Solutions LLC

MRCP

Kaldi SR Plugin

Administrator Guide

 

Revision: 1

Distribution: Debian / Ubuntu

Created: February 5, 2018

Last updated: February 5, 2018

Author: Arsen Chaloyan


 

Table of Contents

1 Overview.. 3

1.1 Applicable Versions. 3

1.2 Supported Distributions. 3

1.3 Authentication. 3

2 Installing Deb Packages Using Apt-Get 4

2.1 Repository Configuration. 4

2.2 GnuPG Key. 4

2.3 Repository Update. 4

2.4 KaldiSR Plugin Installation. 4

3 Installing Deb Packages Manually. 6

3.1 Package List 6

3.2 Package Installation Order 7

4 Obtaining License. 8

4.1 License Type. 8

4.2 Node Information. 8

4.3 License Installation. 8

5 Configuring Server and Plugin. 9

5.1 Plugin Factory Configuration. 9

5.2 RTP Configuration. 9

5.3 Logger Configuration. 10

5.4 KaldiSR Plugin Configuration. 10

6 Validating Setup. 11

6.1 Launching Server 11

6.2 Launching Client 11

 


 

1       Overview

This guide describes how to obtain and install binary packages for the Kaldi Speech Recognition (KaldiSR) plugin to the UniMRCP server on Debian-based Linux distributions. The document is intended for system administrators and developers.

1.1      Applicable Versions

Instructions provided in this guide are applicable to the following versions.

 

UniMRCP 1.5.0 and above

UniMRCP KaldiSR Plugin 1.0.0 and above

1.2      Supported Distributions

UniMRCP binary packages are currently available only for x86_64 (64-bit) architecture.

 

Operating System

32-bit

64-bit

Ubuntu 14.04 LTS (trusty)

 

 

Ubuntu 16.04 LTS (xenial)

 

box_info.png

 

Note: packages for other distributions can be made available upon request. For more information, contact services@unimrcp.org.

1.3      Authentication

UniMRCP binary packages are available to authenticated users only. In order to register a free account with UniMRCP, please visit the following page.

 

https://www.unimrcp.org/profile-registration

 

Note: a new account needs to be verified and activated prior further proceeding.

2       Installing Deb Packages Using Apt-Get

Using the APT package handling utility (apt-get) is recommended for installation of UniMRCP binary packages.

2.1      Repository Configuration

The content of a typical configuration file of the APT repository, to be placed in /etc/apt/sources.list.d/unimrcp.list, is provided below.

 

deb [arch=amd64] https://username:password@unimrcp.org/repo/apt/ distr main

 

The username and password fields included in the HTTPS URI must be replaced with the corresponding account credentials.

The distr field must be replaced with the corresponding distribution code name such as trusty, xenial, etc.

2.2      GnuPG Key

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 -

 

2.3      Repository Update

In order to check for updates and apply the changes in the APT configuration, use the following command.

 

sudo apt-get update

 

2.4      KaldiSR Plugin Installation

In order to install the KaldiSR plugin, including all the dependencies, use the following command.

 

sudo apt-get install unimrcp-kaldi-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

 

Note: this package is optional and provides additional data which can be used for validation of basic setup.

3       Installing Deb Packages Manually

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:

 

$packagename_$universion-$distr_$arch.deb

 

where

         packagename is the name of a package

         universion is the UniMRCP version

         distr is the distribution code name (trusty, xenial, )

         arch is the architecture (amd64, i386, all, )

3.1      Package List

The following is a list of UniMRCP deb packages required for the installation of the KaldiSR plugin.

 

Package Name

Description

unimrcp-kaldi-sr

KaldiSR plugin to the server.

unilibevent

UniMRCP edition of the libevent 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.

3.2      Package Installation Order

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, a package containing the libevent library.

 

sudo dpkg --install unilibevent_$libeventversion-$distr_$arch.deb

 

Finally, a package containing the KaldiSR plugin should follow.

 

sudo dpkg --install unimrcp-kaldi-sr_$universion-$distr_all.deb

 

4       Obtaining License

The KaldiSR plugin to the UniMRCP server is a commercial product, which requires a license file to be installed.

4.1      License Type

The following license types are available:

         Trial

         Production

         Test and Development

4.2      Node Information

The license files are bound to a node the product is installed on. In order to obtain a license, the corresponding node information needs to be retrieved and submitted for generation of a license file.

 

Use the installed tool unilicnodegen to retrieve the node information.

 

sudo /opt/unimrcp/bin/unilicnodegen

 

As a result, a text file uninode.info will be saved in the current directory. Submit the file uninode.info for license generation to services@unimrcp.org by mentioning the product name in the subject.

4.3      License Installation

The license file needs to be placed into the directory /opt/unimrcp/data.

 

sudo cp umskaldisr_*.lic /opt/unimrcp/data

 

 

5       Configuring Server and Plugin

5.1      Plugin Factory Configuration

In order to load the KaldiSR 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 remaining demo plugins might also be disabled, if not installed.

 

<!-- Factory of plugins (MRCP engines) -->

<plugin-factory>

<engine id="Demo-Synth-1" name="demosynth" enable="true"/>

<engine id="Demo-Recog-1" name="demorecog" enable="false"/>

<engine id="Demo-Verifier-1" name="demoverifier" enable="true"/>

<engine id="Recorder-1" name="mrcprecorder" enable="true"/>

<engine id="Kaldi-SR-1" name="umskaldisr" enable="true"/>

</plugin-factory>

5.2      RTP Configuration

In order to support audio data sampled at 16 kHz, the corresponding codecs needs to be specified in the configuration file unimrcpserver.xml under the XML element <rtp-settings> as follows.

 

<rtp-settings id="RTP-Settings-1">

<codecs own-preference="false"> PCMU PCMA L16/96/8000 telephone-event/101/8000 PCMU/97/16000 PCMA/98/16000 L16/99/16000 telephone-event/102/16000</codecs>

</rtp-settings>

 

For the basic verification test to work, similar settings should be specified in the client configuration file unimrcpclient.xml as well.

 

<rtp-settings id="RTP-Settings-1">

<codecs>PCMU PCMA L16/96/8000 telephone-event/101/8000 PCMU/97/16000 PCMA/98/16000 L16/99/16000 telephone-event/102/16000</codecs>

</rtp-settings>

 

5.3      Logger Configuration

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="KALDISR-PLUGIN" priority="INFO" masking="NONE"/>

 

5.4      KaldiSR Plugin Configuration

The configuration file of the plugin is located in /opt/unimrcp/conf/umskaldisr.xml. Default settings should be sufficient for generic use.

 

Note that, by using the default configuration settings, an instance of the Kaldi GStreamer server is supposed to be running on the same host as the UniMRCP server, having the following attributes.

 

<kaldi-server-pool>

<kaldi-server language="en-US" sampling-rate="16000" instance-count="auto" address="127.0.0.1" port="8080"/>

</kaldi-server-pool>

 

Installation of the Kaldi GStreamer server is not covered in this document.

 

Refer to the Usage Guide for more information.

 

6       Validating Setup

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.

6.1      Launching Server

Note: an instance of the Kaldi GStreamer server needs to be running prior starting the UniMRCP server.

 

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 [Kaldi-SR-1] [/opt/unimrcp/plugin/umskaldisr.so]

 

Next, check for the license information.

 

[NOTICE] UniMRCP KALDISR License

 

-product name: umskaldisr

-product version: 1.0.0

-license owner: -

-license type: trial

-issue date: 2018-02-05

-exp date: 2018-03-07

-channel count: 2

-feature set: 0

 

Next, make sure that the plugin is successfully connected to the Kaldi GStreamer server.

 

[INFO] Received WS msg [57 bytes]

{"num_workers_available": 2, "num_requests_processed": 0}

[INFO] Set instance count to 2 for <127.0.0.1:8080>

 

6.2      Launching Client

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 bsr1 from the console of the umc client application.

 

run bsr1

 

This command sends a RECOGNIZE request to the server and then starts streaming a sample audio input file whatstheweatherlike.pcm to recognize.

 

Check for the NLSML results to be returned as expected.

 

<?xml version="1.0"?>

<result>

<interpretation grammar="builtin:speech/transcribe" confidence="0.50">

<instance>what's the weather like</instance>

<input mode="speech">what's the weather like</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 umskaldisr.xml and/or requested by the client.