hello
i tried to adapt data (french telephonic speech), and to do scoring""WER"" i saw that the score is given according to the all test corpus , i changed paths and specify telephonic data.
i use data from broadcast news in french , and i use the scoring file from ESTER .
if some one had worked with ESTER data, and did adaptation .
help ?
thanks
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
hello
i tried to adapt data (french telephonic speech), and to do scoring""WER"" i saw that the score is given according to the all test corpus , i changed paths and specify telephonic data.
i use data from broadcast news in french , and i use the scoring file from ESTER .
if some one had worked with ESTER data, and did adaptation .
help ?
thanks