| | 1 | |
| | 2 | = Transcription Tool = |
| | 3 | |
| | 4 | |
| | 5 | == How to run == |
| | 6 | |
| | 7 | |
| | 8 | {{{ |
| | 9 | |
| | 10 | export MARY_BASE="[PATH TO MARYBASE]" |
| | 11 | |
| | 12 | java -Xmx1024m -classpath $MARY_BASE/java:$MARY_BASE/java/mary-common.jar:\ |
| | 13 | $MARY_BASE/java/log4j-1.2.8.jar:$MARY_BASE/java/weka.jar:\ |
| | 14 | $MARY_BASE/java/mysql-connector-java-5.1.7-bin.jar\ |
| | 15 | -Djava.endorsed.dirs=$MARYBASE/lib/endorsed\ |
| | 16 | marytts.tools.transcription.TranscriptionGUI |
| | 17 | |
| | 18 | }}} |
| | 19 | |
| | 20 | |
| | 21 | |
| | 22 | {{{ |
| | 23 | #!html |
| | 24 | <h2>Instructions for Transcription Tool</h2> |
| | 25 | <ol> |
| | 26 | <li>Prepare phoneset for your language. For example, phoneset for English (locale: en_US): <a href="http://mary.opendfki.de/wiki/TranscriptionTool/allophones_en-US.xml">http://mary.opendfki.de/wiki/TranscriptionTool/allophones_en-US.xml</a> </li> |
| | 27 | <li>Specify phoneset (allophones.xml) file using menu item 'specify phoneset'</li> |
| | 28 | <li>Load your data for transcription <br>(two options: 1. Open (MenuItem) 2. Load from MySql database (list of words as a table) )</li> |
| | 29 | <li>Save your data to a specified location. (then 'TrainPredict' button will be enable)</li> |
| | 30 | <li>If you transcribe some data, click 'trainpredict' button to predict transcription for remaining words. you have to manually correct predicted transcription.</li> |
| | 31 | <li>Description of colors: |
| | 32 | <ul> |
| | 33 | <li>Black - Manually written or manually corrected</li> |
| | 34 | <li>Red - Transcription syntax is not permitted (eg: user written transcription is incorrect)</li> |
| | 35 | <li>LightGray - Predicted by 'TrainPredict' (predicted based on manual transcription)</li> |
| | 36 | </ul> |
| | 37 | </li> |
| | 38 | </ol> |
| | 39 | }}} |