Browse
 
Tools
Rss Categories

Deprecated - sre_server.conf

Reference Number: AA-01540 Views: 7835 0 Rating/ Voters

Deprecated Content

This page refers to outdated, obsolete, or deprecated products or software. This is provided for historical reference for users of older releases. Please see our current page on sre_server.conf.

This file controls settings related to the speech server.

It is located by default in /etc/lumenvox/

See Configuration Files for more information about otherconfiguration files.

The following parameters can be set. The format to use within the configuration file is PROPERTY_NAME= VALUE

HMM_TYPE

Description: Which Engine decoder modelis used – continuous or semi-continuous. The continuous decoder has seenincreased in accuracy across several domains, but may require approximately15-20% more processing time. In some domains, the semi-continuous decoderproved more accurate. Our recommendation in most cases is to use continuousmode.

Possible Values: SEMI (for semi-continuous) or CONT (for continuous) .

Default Value: SEMI

ENABLE_CACHE

Description: Whether grammar caching should be turned onor off. Grammar caching allows the server to automatically cache all loaded grammars to disk. Thiscan save a lot of time when loading larger grammars, as they must be compiled before use, and thiscan take a while for big grammars.

Possible Values: 0 (disabled) or 1 (enabled).

Default Value: 1

CACHE_EXPIRATION

Description: The amount of time, in seconds, the Engine willuse a cached grammars on disk. If a cached grammar on disk is older than this value, the Enginewill disregard the cached copy. If you are making extensive use of caching to preload verylarge grammars, you may want to set this very high.

Possible Values: An integer. If it is set to 0, the Enginewill never used cached grammars.

Default Value: 1440

CACHE_MAX_NUMBER

Description: The maximum number of grammars to be kept in cache. The higher the number of grammars kept in memory, the more memory gets used in storing them.

Possible Values: An integer. If it is set to 0, the Enginewill not cache any grammars.

Default Value: 100

CACHE_MAX_MEMORY

Description: The maximum amount of memory, in bytes, that can be used to cache grammars

Possible Values: An integer. If it is set to 0, the Enginewill not cache any grammars.

Default Value: 268435456 (256 MB)

SRE_PORTNUM

Description: The port number that the speech server willuse to listen for incoming speech requests.

Possible Values: A port number.

Default Value: 5730

NUM_DECODE_THREADS

Description: The maximum number of processing threads for decodingaudio. This parameter should NOT be modified at all, unless instructed by LumenVox support.

Possible Values: An integer. If it is set to 0, the Enginewill not perform any decodes.

Default Value: 4

LOAD_XXX_RES_MODEL

Description: Determines which of the three resolution levels (LOW, MED, HIGH) of acoustic model are loaded. A higher resolution model requires more memory, and may result in longer decode times, but can also provide increased accuracy. Combinations (LOW and HIGH) can be enabled, but the lower resolution will be defaulted to.

Possible Values: 0 (disabled) or 1 (enabled)

Default Value: LOW enabled
LOAD_LOW_RES_MODEL = 1
LOAD_MED_RES_MODEL = 0
LOAD_HIGH_RES_MODEL = 0