LmPerplexity

The LmPerplexity task analyzes the perplexity of a sample text file, when given a specific language model.

Parameters

Parameter Description Required
Type The task name. Set to LmPerplexity. Yes
CaseMap Whether to ignore casing.  
ChronosCompat Whether to treat <s> context reset markers in the same way as in the decoder.  
Clm The custom language model to use in conjunction with a base model.  
CWeight

The interpolation weight of the custom language model, if applicable.

 
Out The log file to generate. Yes
Text The sample text file. Yes
Tlm The language model to use. Yes

Example

http://localhost:13000/action=AddTask&Type=LmPerplexity&Text=C:\data\transcript.txt&Tlm=C:\LP\ENUK\ver-ENUK-5.0.tlm&Out=PerpScore.ctm

This action uses port 13000 to instruct HPE IDOL Speech Server, which is located on the local machine, to calculate the perplexity of the ver-ENUK-5.0.tlm language model using the transcript.txt sample text, and write the results to the PerpScore.ctm file.


_HP_HTML5_bannerTitle.htm