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