The transcript file containing the spoken text that IDOL Speech Server aligns the recognition output to.
You can specify an absolute or relative file path. If you specify a relative path, it is considered as being relative to the data directory. If the file path is excluded, IDOL Speech Server defaults to the data directory.
Note: The DataDir parameter in the [Paths]
section of the configuration file sets the location of the data directory.
The file that you specify must contain normalized text. This text can be provided in ‘natural’ text form (multiple words on each line, multiple lines in each file, and so on). Alternatively, you can supply it in a multicolumn format, in which case there must be only one transcribed word on each line. For example:
Article one All human beings are born free
With this format, you can optionally follow words with a pair of numbers that specify the earliest start time and latest end time in seconds at which the word might appear in the aligned output. For example:
Article 0.000 1.000 one 0.000 1.000 All 0.000 1.000 human 0.500 1.500 beings 0.500 1.500 are 1.000 2.000 born 1.000 2.000 free 1.000 2.000
This example indicates that the word Article must appear between 0.000 and 1.000 seconds in the aligned output, human must appear between 0.500 and 1.500 seconds, and so on.
The transcript checker automatically adds approximate timestamps in this form to transcripts. If you perform an iterative alignment, you must convert the CTM file from a previous alignment to this form before performing the next alignment.
IDOL Speech Server ignores entries that begin with <metadata>
.
Type: | String |
---|---|
Default: | None |
Required: | Yes |
Configuration Section: | align module |
Example: | TxtFile=T:\data\normalizedText.txt
|
See Also: | TxtFile (action parameter) |
|