Commit 5a14b86787e34200360c3f5d4ef4616d7fceccf3
1 parent
c00c2f1895
Exists in
master
update doc
Showing 5 changed files with 60 additions and 14 deletions Side-by-side Diff
| ... | ... | @@ -28,6 +28,7 @@ |
| 28 | 28 | -f n : number of forks for speeral |
| 29 | 29 | |
| 30 | 30 | Output : result_directory/110624FR2_20002100/res_p1/ |
| 31 | + and .ctm, .trs and .txt files. | |
| 31 | 32 | |
| 32 | 33 | 2.2\ SecondPass.sh |
| 33 | 34 | ------------------ |
| ... | ... | @@ -40,6 +41,7 @@ |
| 40 | 41 | -f n : number of forks for speeral |
| 41 | 42 | |
| 42 | 43 | Output : result_directory/110624FR2_20002100/res_p2/ |
| 44 | + and .ctm, .trs and .txt files. | |
| 43 | 45 | |
| 44 | 46 | 2.3\ ConfPass.sh |
| 45 | 47 | ---------------- |
| ... | ... | @@ -75,6 +77,7 @@ |
| 75 | 77 | -f n : number of forks for speeral |
| 76 | 78 | |
| 77 | 79 | Output : result_directory/110624FR2_20002100/conf/res_p3 |
| 80 | + and .ctm, .trs and .txt files. | |
| 78 | 81 | |
| 79 | 82 | 2.6\ RecomposePass.sh |
| 80 | 83 | -------------------- |
| ... | ... | @@ -84,6 +87,7 @@ |
| 84 | 87 | $> RecomposePass.sh [options] result_directory/110624FR2_20002100/ |
| 85 | 88 | |
| 86 | 89 | Output : result_directory/110624FR2_20002100/res_all |
| 90 | + and .ctm, .trs and .txt files. | |
| 87 | 91 | |
| 88 | 92 | 2.7\ ScoringRes.sh |
| 89 | 93 | ------------------ |
| 90 | 94 | |
| 91 | 95 | |
| 92 | 96 | |
| 93 | 97 | |
| ... | ... | @@ -127,9 +131,36 @@ |
| 127 | 131 | -s Do Scoring pass |
| 128 | 132 | |
| 129 | 133 | 4\ Modify configuration |
| 134 | +----------------------- | |
| 130 | 135 | |
| 136 | + Most of the main scripts got a configuration file (cfg/ directory). | |
| 137 | + You can change script behaviour and data used. | |
| 138 | + Speeral configuration file can be also change (tools/Speeral/CFG/ directory) | |
| 139 | + | |
| 131 | 140 | 4.1\ Scripts configurations |
| 141 | + | |
| 142 | + In scripts configuration files (OTMEDIA_HOME/cfg/) you can change default options as architecture, verbose ... | |
| 143 | + Scripts using Speeral got information on binaries, models path and name, and the configuration file for speeral. | |
| 144 | + | |
| 132 | 145 | 4.2\ Speeral configurations |
| 133 | 146 | |
| 147 | + Speeral configuration files are in OTMEDIA_HOME/tools/Speeral/CFG directory. | |
| 148 | + The .tmp files are use to generate .xml file from install.sh. | |
| 149 | + You can modify .xml files for your needs, but most of data informations are pass through arguments at speeral call in scripts. | |
| 150 | + | |
| 134 | 151 | 5\ Modify binaries |
| 152 | +------------------ | |
| 153 | + | |
| 154 | + Binaries can be find in bin and tools directory. | |
| 155 | + Some binaries are compiled in 32 and 64 bits. By default all binaries are compiled in 32 bits. | |
| 156 | + You can update binaries as you need. | |
| 157 | + | |
| 158 | + To modify tools binaries, you need to download a compatible version. | |
| 159 | + lia_ltbox can be found in /labo/Tools/ | |
| 160 | + Speeral (binaries) can be compiled from the git remote git@gitlia.univ-avignon.fr:vaudriguard/libspeeral.git . Do not modify Speeral data from OTMEDIA (unless you know what you do). | |
| 161 | + In PACKAGES_MESURES_V1.0 you can update icsiboost binary (in bin) from the projet page : https://code.google.com/p/icsiboost/ | |
| 162 | + For QUOTE_FINDER and SIGMUND please contact support. | |
| 163 | + | |
| 164 | +Good Luck ! Luke ! | |
| 165 | +And the force be with you ! |
INSTALL
| ... | ... | @@ -14,6 +14,7 @@ |
| 14 | 14 | 1\ Before installation |
| 15 | 15 | 2\ install.sh script |
| 16 | 16 | 3\ SOLR install |
| 17 | +4\ Install descriptions | |
| 17 | 18 | |
| 18 | 19 | |
| 19 | 20 | 1\ Before installation |
| ... | ... | @@ -24,7 +25,7 @@ |
| 24 | 25 | - Have 300 Go of free space. |
| 25 | 26 | - Have acces to the network and the nyx server. |
| 26 | 27 | |
| 27 | -2/ install.sh script | |
| 28 | +2\ install.sh script | |
| 28 | 29 | -------------------- |
| 29 | 30 | |
| 30 | 31 | install.sh script will do most of the work. |
| ... | ... | @@ -37,6 +38,8 @@ |
| 37 | 38 | To disable confidence measure put CONFPASS to 0. |
| 38 | 39 | To disable second and third pass put PASS2 to 0. |
| 39 | 40 | |
| 41 | +If your login name differ from your nyx login name, edit install.sh and change the username variable to your nyx login name. | |
| 42 | + | |
| 40 | 43 | run install.sh and follow the white rabbit. |
| 41 | 44 | |
| 42 | 45 | 3\ SOLR install |
| ... | ... | @@ -46,6 +49,7 @@ |
| 46 | 49 | See SOLR.INSTALL file to install OTMEDIA SOLR DB. |
| 47 | 50 | |
| 48 | 51 | 4\ Install descriptions |
| 52 | +----------------------- | |
| 49 | 53 | |
| 50 | 54 | OTMEDIA_HOME |
| 51 | 55 | |-> bin/ |
| ... | ... | @@ -55,7 +59,7 @@ |
| 55 | 59 | |-> lia_plp_mt.64 |
| 56 | 60 | |-> LIUM_SpkDiarization-4.2.jar |
| 57 | 61 | |-> sclite |
| 58 | - |-> cfg/ | |
| 62 | + |-> cfg/ # Main scripts configurations files | |
| 59 | 63 | |-> ConfidenceMeasure.cfg |
| 60 | 64 | |-> ConfPass.cfg |
| 61 | 65 | |-> ExploitConfidencePass.cfg |
| ... | ... | @@ -65,7 +69,7 @@ |
| 65 | 69 | |-> Scoring.cfg |
| 66 | 70 | |-> Secondass.cfg |
| 67 | 71 | |-> ThirdPass.cfg |
| 68 | - |-> data/ | |
| 72 | + |-> data/ # Some data | |
| 69 | 73 | |-> rules/ |
| 70 | 74 | |-> asupp |
| 71 | 75 | |-> basic |
| ... | ... | @@ -75,7 +79,7 @@ |
| 75 | 79 | |-> postprocess.regex |
| 76 | 80 | |-> preprocess.regex |
| 77 | 81 | |-> random_regex.tab |
| 78 | - |-> main_tools/ | |
| 82 | + |-> main_tools/ # Main scripts | |
| 79 | 83 | |-> CheckResults.sh |
| 80 | 84 | |-> ConfidenceMeasure.sh |
| 81 | 85 | |-> ConfPass.sh |
| 82 | 86 | |
| ... | ... | @@ -86,11 +90,11 @@ |
| 86 | 90 | |-> ScoringRes.sh |
| 87 | 91 | |-> SecondPass.sh |
| 88 | 92 | |-> ThirdPass.sh |
| 89 | - |-> tools/ | |
| 93 | + |-> tools/ # Tools | |
| 90 | 94 | |-> lia_ltbox/ |
| 91 | 95 | |-> PACKAGE_MESURES_V1.0/ |
| 92 | 96 | |-> QUOTE_FINDER/ |
| 93 | - |-> scripts/ | |
| 97 | + |-> scripts/ # Secondary scripts (but useful) | |
| 94 | 98 | |-> ApplyCorrectionRules.pl |
| 95 | 99 | |-> BdlexUC.pl |
| 96 | 100 | |-> CheckConfPass.sh |
| ... | ... | @@ -127,6 +131,8 @@ |
| 127 | 131 | |-> Tools.sh |
| 128 | 132 | |-> UrlConverter.pl |
| 129 | 133 | |-> SIGMUND/ |
| 134 | + |-> SOLR/ | |
| 135 | + |-> Speeral/ | |
| 130 | 136 | |-> COPYING |
| 131 | 137 | |-> CorpusOTMedia.txt |
| 132 | 138 | |-> HOWTO |
README
| ... | ... | @@ -28,7 +28,8 @@ |
| 28 | 28 | - Confidence pass : calcul confidence measure from transcription output. |
| 29 | 29 | - Exploit Confidence Measure : use SOLR DB data to extend the lexicon on low confidence measure and create trigg files. |
| 30 | 30 | - Third pass : second pass using the new lexicon and trigg files. |
| 31 | - | |
| 31 | + | |
| 32 | + From GIT : git@gitlia.univ-avignon.fr/otmedia.git | |
| 32 | 33 | |
| 33 | 34 | DEPENDENCIES |
| 34 | 35 | ------------ |
install.sh
| ... | ... | @@ -3,9 +3,10 @@ |
| 3 | 3 | #-------------------# |
| 4 | 4 | # OTMEDIA LIA # |
| 5 | 5 | # Install script # |
| 6 | -# version : 1.0.0 # | |
| 6 | +# version : 1.1.0 # | |
| 7 | 7 | #-------------------# |
| 8 | 8 | |
| 9 | +# nyx login name | |
| 9 | 10 | username=${LOGNAME} |
| 10 | 11 | |
| 11 | 12 | # Color variables |
| ... | ... | @@ -143,8 +144,12 @@ |
| 143 | 144 | ### Speeral Configuration ### |
| 144 | 145 | |
| 145 | 146 | echo -e "\n\t${txtblu}Speeral configuration${txtrst}\n" |
| 146 | -echo -e "Download Speeral bin and data :" | |
| 147 | -scp -r ${username}@nyx:~/OTMEDIA_DATA/Speeral $OTMEDIA_HOME/tools/ | |
| 147 | +read -e -p "Download Speeral bin and data ? (y/n) " speeral | |
| 148 | +if [ "$speeral" == "y" ] | |
| 149 | +then | |
| 150 | + echo -e "Download Speeral bin and data :" | |
| 151 | + scp -r ${username}@nyx:/local/OTMEDIA/OTMEDIA_DATA/Speeral $OTMEDIA_HOME/tools/ | |
| 152 | +fi | |
| 148 | 153 | echo -e "\n\t${txtblu}Generating Speeral configuration files :${txtrst}\n" |
| 149 | 154 | cat $PWD/tools/Speeral/CFG/SpeeralFirstPass.xml.tmp | sed -e "s|<nom>[^<]*</nom>|<nom>$PWD/tools/Speeral/LEX/LEXIQUE_V6.speer</nom>|g" \ |
| 150 | 155 | | sed -e "s|<ngramme>[^<]*</ngramme>|<ngramme>$PWD/tools/Speeral/LM/ML_4gOTMEDIA_LEXIQUE_V6</ngramme>|g" \ |
| ... | ... | @@ -204,7 +209,7 @@ |
| 204 | 209 | |
| 205 | 210 | echo -e "Download SOLR DB\r" |
| 206 | 211 | mkdir -p $OTMEDIA_HOME/tools/SOLR 2> /dev/null |
| 207 | - scp -r ${username}@nyx:~/OTMEDIA_DATA/SOLR/otmedia-2013-04.tar.gz $OTMEDIA_HOME/tools/SOLR | |
| 212 | + scp -r ${username}@nyx:/local/OTMEDIA/OTMEDIA_DATA/SOLR/otmedia-2013-04.tar.gz $OTMEDIA_HOME/tools/SOLR | |
| 208 | 213 | echo -e "Unzip SOLR DB\r" |
| 209 | 214 | res=0 |
| 210 | 215 | #res = $(tar -xvzf "$OTMEDIA_HOME/tools/SOLR/otmedia-2013-04.tar.gz" "$OTMEDIA_HOME/tools/SOLR/") |
| 211 | 216 | |
| ... | ... | @@ -259,10 +264,10 @@ |
| 259 | 264 | echo "export SRILM_BIN=$SRILM/bin/$MACHINE_TYPE" |
| 260 | 265 | |
| 261 | 266 | |
| 262 | -echo " \\ " | |
| 267 | +echo "${txtwht} \\ " | |
| 263 | 268 | echo " ,-~~~-\\\\_" |
| 264 | 269 | echo " ( .\ " |
| 265 | -echo " @\___(__--'" | |
| 270 | +echo " @\___(__--'${txtrst}" | |
| 266 | 271 | |
| 267 | 272 | echo "${txtgrn}Yes${txtylw}I${txtred}Rastafari${txtrst}" |
main_tools/ConfidenceMeasure.sh
| ... | ... | @@ -102,8 +102,11 @@ |
| 102 | 102 | mkdir -p $SEGCTM > /dev/null 2>&1 |
| 103 | 103 | mkdir -p $SUPER_CTM > /dev/null 2>&1 |
| 104 | 104 | mkdir -p $SCORED_CTM > /dev/null 2>&1 |
| 105 | -if [ -z $BOOST_BIN ];then | |
| 105 | +if [ -z $BOOST_BIN ] && [ $ARCH == ".64"] ;then | |
| 106 | 106 | BOOST_BIN=$ROOT/bin/icsiboost-64bit-static-r160 |
| 107 | +fi | |
| 108 | +if [ -z $BOOST_BIN ] ;then | |
| 109 | + BOOST_BIN=$ROOT/bin/icsiboost-32bit-static-r176 | |
| 107 | 110 | fi |
| 108 | 111 | #----------------------------------------------------------------- |
| 109 | 112 | # STEP 1 - Extension des treillis + ajout posteriors (format htk) |