Install Speech-to-Text Language Packs
Language packs can contain hundreds of megabytes of data, so they are not included in the Media Server installation and must be downloaded and installed separately.
OpenText recommends installing the common speech-to-text resources first. The common resources provide the micro
, small
, and large
speech-to-text models (see the ModelVersion parameter). These models support all languages supported by legacy speech-to-text (see Speech Analysis Supported Languages).
In some cases you might need to install one or more legacy speech-to-text language packs. These are necessary to run the following operations:
- Speech-to-text with
ModelVersion=Legacy
. - Transcript alignment (action=AlignAudioTranscript)
- Speaker clustering
TIP: There are more than 60 legacy language packs available for Media Server. A legacy language pack supports a single language and a single audio sample rate. For example, there is a language pack for processing US English (16kHz) and another for US English (8kHz). The 8kHz language packs are for processing telephony audio. For a list of available language packs, see Speech Analysis Supported Languages.
To install the common speech-to-text resources
- Download the Media Server common speech resources from the support portal.
-
Extract the common resources into the folder
staticdata/speechtotext/
so that there is a folder namedCommon
containing the common resources.TIP: The path of the static data directory can be configured by setting the
StaticDataDirectory
parameter in the[Paths]
section of the Media Server configuration file. The default value is thestaticdata
folder in the Media Server installation directory.
To install a legacy language pack
- Download a language pack (such as
ENUK-24.3.0.zip
) from the support portal. -
Extract the contents of the language pack into the folder
staticdata/speechtotext/
.TIP: The path of the static data directory can be configured by setting the
StaticDataDirectory
parameter in the[Paths]
section of the Media Server configuration file. The default value is thestaticdata
folder in the Media Server installation directory. - To confirm that the language pack was installed successfully, start Media Server and run the action
ListSpeechLanguagePacks
. The response lists each language pack that is available, along with its supported sample rate.