---
name: "sylseg-sk-training"
section: "1"
platform: "linux"
package: "sylseg-sk"
version: "0.7.3-1.1"
release: "Debian 13 (Trixie)"
platforms: ["linux"]
url: "https://new.carta.tech/sylseg-sk-training"
---

# sylseg-sk-training(1)

train the statistic for the syllabic segmentation

## NAME

sylseg-sk-training - train the statistic for the syllabic segmentation

## SYNOPSIS

**sylseg-sk-training** \[--color\] \[--dl debug level\] \[--help\] \[\<input file\>\]

## DESCRIPTION

The syllabic segmentation is essential for some linguistic or speech recognition applications. Depending on the language either rule-based or statistical approach is being used. For Slovak, the statistical approach seems to be more suitable.

sylseg-sk-training creates the necessary data for one of the statistical approaches  for the syllabic segmentation. The input data are expected to be word segmented into syllables. The syllabic separator should be "-". If no input file is specified, the standard input is expected.  The output is written into the file. The filename is input filename with  the extension ".statistics". If standard input is used, then the output filename is syl\_output.statistics.

The design of the sylseg-sk-training is language independent. Theoretically it should work for any language.

## OPTIONS

- \--color

  Enable color output.

- \--dl

  Set the debug level. Control the amount of displayed information Debug level 0 displays nothing. The maximum level 5 displays a full debugging report. The default debug level is 1.

- \--help

  Display a short help text.

## EXAMPLES

- Use file aaa.txt as training input and set up debug level to 3:

  **sylseg-sk-training** --dl 3 aaa.txt

## EXIT STATUS

sylseg-sk-training returns zero if the training  succeeds.

## AUTHOR

Jozef Ivanecky (dodo (at) kanoistika.sk)

## SEE ALSO

[sylseg-sk(1)](/sylseg-sk/1.md)