Skip to content
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.

Commit 9a5622f

Browse files
committedSep 25, 2024·
Support IPA symbols, resolves nltk#3323
1 parent d1dabec commit 9a5622f

File tree

1 file changed

+238
-0
lines changed

1 file changed

+238
-0
lines changed
 

‎nltk/metrics/aline.py

+238
Original file line numberDiff line numberDiff line change
@@ -860,6 +860,20 @@
860860
"long": "minus",
861861
"aspirated": "minus",
862862
},
863+
"ø̞": {
864+
"place": "vowel",
865+
"manner": "vowel2",
866+
"syllabic": "plus",
867+
"voice": "plus",
868+
"nasal": "minus",
869+
"retroflex": "minus",
870+
"lateral": "minus",
871+
"high": "mid",
872+
"back": "front",
873+
"round": "plus",
874+
"long": "minus",
875+
"aspirated": "minus",
876+
},
863877
"ɛ": {
864878
"place": "vowel",
865879
"manner": "vowel2",
@@ -916,6 +930,48 @@
916930
"long": "minus",
917931
"aspirated": "minus",
918932
},
933+
"ä": {
934+
"place": "vowel",
935+
"manner": "vowel2",
936+
"syllabic": "plus",
937+
"voice": "plus",
938+
"nasal": "minus",
939+
"retroflex": "minus",
940+
"lateral": "minus",
941+
"high": "low",
942+
"back": "central",
943+
"round": "minus",
944+
"long": "minus",
945+
"aspirated": "minus",
946+
},
947+
"ɐ": {
948+
"place": "vowel",
949+
"manner": "vowel2",
950+
"syllabic": "plus",
951+
"voice": "plus",
952+
"nasal": "minus",
953+
"retroflex": "minus",
954+
"lateral": "minus",
955+
"high": "low",
956+
"back": "central",
957+
"round": "minus",
958+
"long": "minus",
959+
"aspirated": "minus",
960+
},
961+
"ɶ": {
962+
"place": "vowel",
963+
"manner": "vowel2",
964+
"syllabic": "plus",
965+
"voice": "plus",
966+
"nasal": "minus",
967+
"retroflex": "minus",
968+
"lateral": "minus",
969+
"high": "low",
970+
"back": "front",
971+
"round": "plus",
972+
"long": "minus",
973+
"aspirated": "minus",
974+
},
919975
"A": {
920976
"place": "vowel",
921977
"manner": "vowel2",
@@ -972,6 +1028,34 @@
9721028
"long": "minus",
9731029
"aspirated": "minus",
9741030
},
1031+
"ɜ": {
1032+
"place": "vowel",
1033+
"manner": "vowel2",
1034+
"syllabic": "plus",
1035+
"voice": "plus",
1036+
"nasal": "minus",
1037+
"retroflex": "minus",
1038+
"lateral": "minus",
1039+
"high": "mid",
1040+
"back": "central",
1041+
"round": "minus",
1042+
"long": "minus",
1043+
"aspirated": "minus",
1044+
},
1045+
"ɞ": {
1046+
"place": "vowel",
1047+
"manner": "vowel2",
1048+
"syllabic": "plus",
1049+
"voice": "plus",
1050+
"nasal": "minus",
1051+
"retroflex": "minus",
1052+
"lateral": "minus",
1053+
"high": "mid",
1054+
"back": "central",
1055+
"round": "plus",
1056+
"long": "minus",
1057+
"aspirated": "minus",
1058+
},
9751059
"u": {
9761060
"place": "vowel",
9771061
"manner": "vowel2",
@@ -1014,6 +1098,20 @@
10141098
"long": "minus",
10151099
"aspirated": "minus",
10161100
},
1101+
"o̞": {
1102+
"place": "vowel",
1103+
"manner": "vowel2",
1104+
"syllabic": "plus",
1105+
"voice": "plus",
1106+
"nasal": "minus",
1107+
"retroflex": "minus",
1108+
"lateral": "minus",
1109+
"high": "mid",
1110+
"back": "back",
1111+
"round": "plus",
1112+
"long": "minus",
1113+
"aspirated": "minus",
1114+
},
10171115
"O": {
10181116
"place": "vowel",
10191117
"manner": "vowel2",
@@ -1042,7 +1140,35 @@
10421140
"long": "minus",
10431141
"aspirated": "minus",
10441142
},
1143+
"ʌ": {
1144+
"place": "vowel",
1145+
"manner": "vowel2",
1146+
"syllabic": "plus",
1147+
"voice": "plus",
1148+
"nasal": "minus",
1149+
"retroflex": "minus",
1150+
"lateral": "minus",
1151+
"high": "mid",
1152+
"back": "back",
1153+
"round": "minus",
1154+
"long": "minus",
1155+
"aspirated": "minus",
1156+
},
10451157
"ɒ": {
1158+
"place": "vowel",
1159+
"manner": "vowel2",
1160+
"syllabic": "plus",
1161+
"voice": "plus",
1162+
"nasal": "minus",
1163+
"retroflex": "minus",
1164+
"lateral": "minus",
1165+
"high": "low",
1166+
"back": "back",
1167+
"round": "plus",
1168+
"long": "minus",
1169+
"aspirated": "minus",
1170+
},
1171+
"ɑ": {
10461172
"place": "vowel",
10471173
"manner": "vowel2",
10481174
"syllabic": "plus",
@@ -1070,6 +1196,118 @@
10701196
"long": "plus",
10711197
"aspirated": "minus",
10721198
},
1199+
"ɯ": {
1200+
"place": "vowel",
1201+
"manner": "vowel2",
1202+
"syllabic": "plus",
1203+
"voice": "plus",
1204+
"nasal": "minus",
1205+
"retroflex": "minus",
1206+
"lateral": "minus",
1207+
"high": "high",
1208+
"back": "back",
1209+
"round": "plus",
1210+
"long": "minus",
1211+
"aspirated": "minus",
1212+
},
1213+
"ʏ": {
1214+
"place": "vowel",
1215+
"manner": "vowel2",
1216+
"syllabic": "plus",
1217+
"voice": "plus",
1218+
"nasal": "minus",
1219+
"retroflex": "minus",
1220+
"lateral": "minus",
1221+
"high": "high",
1222+
"back": "front",
1223+
"round": "plus",
1224+
"long": "minus",
1225+
"aspirated": "minus",
1226+
},
1227+
"ʊ": {
1228+
"place": "vowel",
1229+
"manner": "vowel2",
1230+
"syllabic": "plus",
1231+
"voice": "plus",
1232+
"nasal": "minus",
1233+
"retroflex": "minus",
1234+
"lateral": "minus",
1235+
"high": "high",
1236+
"back": "back",
1237+
"round": "plus",
1238+
"long": "minus",
1239+
"aspirated": "minus",
1240+
},
1241+
"ɘ": {
1242+
"place": "vowel",
1243+
"manner": "vowel2",
1244+
"syllabic": "plus",
1245+
"voice": "plus",
1246+
"nasal": "minus",
1247+
"retroflex": "minus",
1248+
"lateral": "minus",
1249+
"high": "high",
1250+
"back": "central",
1251+
"round": "minus",
1252+
"long": "minus",
1253+
"aspirated": "minus",
1254+
},
1255+
"e̞": {
1256+
"place": "vowel",
1257+
"manner": "vowel2",
1258+
"syllabic": "plus",
1259+
"voice": "plus",
1260+
"nasal": "minus",
1261+
"retroflex": "minus",
1262+
"lateral": "minus",
1263+
"high": "mid",
1264+
"back": "front",
1265+
"round": "minus",
1266+
"long": "minus",
1267+
"aspirated": "minus",
1268+
},
1269+
"ɵ": {
1270+
"place": "vowel",
1271+
"manner": "vowel2",
1272+
"syllabic": "plus",
1273+
"voice": "plus",
1274+
"nasal": "minus",
1275+
"retroflex": "minus",
1276+
"lateral": "minus",
1277+
"high": "high",
1278+
"back": "central",
1279+
"round": "plus",
1280+
"long": "minus",
1281+
"aspirated": "minus",
1282+
},
1283+
"ɤ": {
1284+
"place": "vowel",
1285+
"manner": "vowel2",
1286+
"syllabic": "plus",
1287+
"voice": "plus",
1288+
"nasal": "minus",
1289+
"retroflex": "minus",
1290+
"lateral": "minus",
1291+
"high": "mid",
1292+
"back": "back",
1293+
"round": "minus",
1294+
"long": "minus",
1295+
"aspirated": "minus",
1296+
},
1297+
"ɤ̞": {
1298+
"place": "vowel",
1299+
"manner": "vowel2",
1300+
"syllabic": "plus",
1301+
"voice": "plus",
1302+
"nasal": "minus",
1303+
"retroflex": "minus",
1304+
"lateral": "minus",
1305+
"high": "mid",
1306+
"back": "back",
1307+
"round": "minus",
1308+
"long": "minus",
1309+
"aspirated": "minus",
1310+
},
10731311
}
10741312

10751313
# === Algorithm ===

0 commit comments

Comments
 (0)
Please sign in to comment.