Step 4 - Creating the Transcription Files

Words Level Transcriptions 

HTK toolkit cannot process your prompts.txt file directly.  You have two options, you can create a separate 'label' file for each line your prompts.txt file in the following format:

*/sample1
DIAL
ONE
TWO
THREE
FOUR
FIVE
SIX
SEVEN
EIGHT
NINE
OH
ZERO

Or you can create a Master Label File (MLF) - which is a single file that contains a label entry for each line in your prompts.txt file.  This is the easiest approach, and the one we will use for this tutorial. 

Download the Julia script prompts2mlf.jl to your voxforge/bin directory to generate the mlf file from your prompts.txt file.  Execute the prompts2mlf script from your 'voxforge/tutporial' folder as follows:

 julia ../bin/prompts2mlf.jl prompts.txt words.mlf

This script generates a words.mlf file.

Phone Level Transcriptions 

Next you need to execute the HLEd command to expand the Word Level Transcriptions to Phone Level Transcriptions - i.e. replace each word with its phonemes, and put the result in a new Phone Level Master Label File  This is done by reviewing each word in the MLF file, and looking up the phones that make up that word in the dict file you created earlier, and outputing the result in a file called phones0.mlf (which will not have short pauses ("sp"s) after each word phone group).

First, create  the mkphones0.led edit script in your 'voxforge/tutorial' folder:

EX
IS sil sil
DE sp
 

(note: remember to include a blank line at the end of this script)

Then execute the following HLEd command from your 'voxforge/tutorial' folder:

Linux:

$HLEd -A -D -T 1 -l '*' -d dict -i phones0.mlf mkphones0.led words.mlf

Windows:

C:>HLEd -A -D -T 1 -l * -d dict -i phones0.mlf mkphones0.led words.mlf

Which creates the phones0.mlf file

Next, we need to create a second phones1.mlf file (which will include short pauses (“sp”) after each word phone group).  First create the mkphones1.led in your 'voxforge/tutorial' folder as follows:

EX
IS sil sil

(note: remember to include a blank line at the end of this script)

Then run the HLEd command again from your 'voxforge/tutorial' folder as follows:

Linux:

$HLEd -A -D -T 1 -l '*' -d dict -i phones1.mlf mkphones1.led words.mlf

Windows:

C:>HLEd -A -D -T 1 -l * -d dict -i phones1.mlf mkphones1.led words.mlf

Which creates the phones1.mlf file.

Comments

By Gururaj - 12/18/2016 hi all..

By Gururaj - 12/15/2016 - 13 Replies Hello everyone,

By Gururaj - 12/13/2016 - 4 Replies Hi all,

By Wageesha - 11/8/2016 How to set HTK configuration parameters when running HLEd -A -D -T 1 -l * -d dict -i phones0.mlf mkphones0.led words.mlf command in voxforge/tutorial folder?

By ehsan moradi - 7/8/2016 - 1 Replies hello what is dict file

By angga - 5/17/2014 - 1 Replies hello..can you help me?? i have follow your instruction in HLEd phones1 but "sp" not include,,, why??

By Mohammad Zaki - 9/3/2013 Hi,

By Asim12 - 1/9/2013 - 1 Replies After running this command HLEd -l '*' -d dict -i phones0.mlf mkphones0.led words.mlf. I am getting error that work > cannot be found in dicitionary.

By bejimed - 2/7/2011 - 1 Replies If there are several possible pronunciations of a word in the pronunciation dictionary how i can create my phones file because

By amza - 7/18/2010 - 3 Replies Hi,

By spring - 12/19/2009 - 6 Replies Hi,ken

By Sugarune - 12/12/2009 I found the error ponts at 2 script line.

By chandu - 10/4/2009 - 7 Replies hello all,

By Adam - 11/9/2008 - 1 Replies HERest breaks (first time we reestimate) if this script includes the IS sil sil line in the first script. Perhaps I am incorrect, but I would recommend this modification.

By Manuel - 9/3/2007 - 3 Replies When you execute: $HLEd -A -D -T 1 -l '*' -d dict -i phones0.mlf mkphones0.led words.mlf if you have some number in the word of the file words.mlf this are not recognize as label, for example if I have : "*/sample1" 1 + 3 HLEd not work, it's ok the follow: "*/sample1" ONE + THREE How can I resolve this? Tks