echogarden 0.3.0 → 0.3.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -24,7 +24,7 @@
|
|
|
24
24
|
],
|
|
25
25
|
|
|
26
26
|
"notSucceededBy": [
|
|
27
|
-
"was", "wasn't"
|
|
27
|
+
"is", "isn't", "was", "wasn't", "will", "would"
|
|
28
28
|
],
|
|
29
29
|
|
|
30
30
|
"example": "I read this book a while ago."
|
|
@@ -36,10 +36,6 @@
|
|
|
36
36
|
}
|
|
37
37
|
},
|
|
38
38
|
|
|
39
|
-
"pos": [
|
|
40
|
-
"VB"
|
|
41
|
-
],
|
|
42
|
-
|
|
43
39
|
"example": "I will read the story."
|
|
44
40
|
}
|
|
45
41
|
],
|
|
@@ -56,7 +52,7 @@
|
|
|
56
52
|
],
|
|
57
53
|
|
|
58
54
|
"precededBy": [
|
|
59
|
-
"will", "would", "we", "they", "i", "you", "don't", "doesn't", "should", "shouldn't", "wouldn't", "may", "might", "could", "couldn't", "these", "those", "must", "mustn't", "people"
|
|
55
|
+
"will", "would", "we", "they", "i", "you", "don't", "doesn't", "should", "shouldn't", "wouldn't", "may", "might", "could", "couldn't", "these", "those", "must", "mustn't", "shall", "people"
|
|
60
56
|
],
|
|
61
57
|
|
|
62
58
|
"notPrecededBy": [
|
|
@@ -136,11 +132,11 @@
|
|
|
136
132
|
],
|
|
137
133
|
|
|
138
134
|
"precededBy": [
|
|
139
|
-
"we", "you", "they", "who", "i", "will", "also", "
|
|
135
|
+
"we", "you", "they", "who", "i", "will", "also", "don't", "didn't", "not", "doesn't", "please", "never", "ever", "often", "frequently", "rarely", "commonly", "we'll", "would", "wouldn't", "instead", "probably", "should", "shouldn't", "must", "mustn't", "shall", "can", "can't", "may", "might", "could", "couldn't", "actually", "always", "sometimes", "typically", "still", "nobody", "everybody", "everyone", "someone", "somebody", "people", "players", "customers"
|
|
140
136
|
],
|
|
141
137
|
|
|
142
138
|
"notPrecededBy": [
|
|
143
|
-
"the", "a", "for", "no", "in", "emergency", "of", "make", "its", "single", "drug", "substance", "land", "their", "good", "making", "mask", "public", "police", "future", "day", "marijuana", "efficient", "tobacco", "mandatory", "full", "own", "first", "her", "his", "its", "our", "your", "any", "mixed", "personal"
|
|
139
|
+
"the", "a", "for", "no", "in", "emergency", "of", "make", "its", "single", "drug", "substance", "land", "their", "good", "making", "mask", "public", "police", "future", "day", "marijuana", "efficient", "tobacco", "mandatory", "full", "own", "first", "her", "his", "its", "our", "your", "my", "any", "mixed", "personal"
|
|
144
140
|
],
|
|
145
141
|
|
|
146
142
|
"succeededBy": [
|
|
@@ -175,7 +171,7 @@
|
|
|
175
171
|
],
|
|
176
172
|
|
|
177
173
|
"precededBy": [
|
|
178
|
-
"to", "who", "we", "and", "i", "they", "cannot", "don't", "not", "can't", "doesn't", "will", "would", "won't", "wouldn't", "please", "never", "humans", "rather"
|
|
174
|
+
"to", "who", "we", "and", "i", "they", "cannot", "don't", "not", "can't", "doesn't", "will", "would", "won't", "wouldn't", "please", "never", "humans", "rather", "happily"
|
|
179
175
|
],
|
|
180
176
|
|
|
181
177
|
"notPrecededBy": [
|
|
@@ -223,7 +219,7 @@
|
|
|
223
219
|
],
|
|
224
220
|
|
|
225
221
|
"succeededBy": [
|
|
226
|
-
"a", "an"
|
|
222
|
+
"a", "an", "here", "there"
|
|
227
223
|
],
|
|
228
224
|
|
|
229
225
|
"notSucceededBy": [
|
|
@@ -255,11 +251,11 @@
|
|
|
255
251
|
],
|
|
256
252
|
|
|
257
253
|
"precededBy": [
|
|
258
|
-
"to", "will", "doesn't", "won't", "should", "shouldn't", "may", "might", "could", "couldn't", "must", "can", "you", "i", "we", "don't", "won't", "don't", "doesn't", "please", "mustn't"
|
|
254
|
+
"to", "will", "doesn't", "won't", "should", "shouldn't", "may", "might", "could", "couldn't", "must", "can", "you", "i", "we", "don't", "won't", "don't", "doesn't", "please", "mustn't", "shall"
|
|
259
255
|
],
|
|
260
256
|
|
|
261
257
|
"notPrecededBy": [
|
|
262
|
-
"very", "quite", "fairly", "a", "is", "are"
|
|
258
|
+
"very", "quite", "fairly", "somewhat", "a", "is", "are"
|
|
263
259
|
],
|
|
264
260
|
|
|
265
261
|
"succeededBy": [
|
|
@@ -267,7 +263,7 @@
|
|
|
267
263
|
],
|
|
268
264
|
|
|
269
265
|
"notSucceededBy":[
|
|
270
|
-
"contact", "friend", "friends"
|
|
266
|
+
"contact", "friend", "friends", "to"
|
|
271
267
|
],
|
|
272
268
|
|
|
273
269
|
"example": "I will close the door."
|
|
@@ -295,7 +291,7 @@
|
|
|
295
291
|
],
|
|
296
292
|
|
|
297
293
|
"precededBy": [
|
|
298
|
-
"to", "i", "they", "we", "you", "will", "would", "wouldn't", "may", "might", "could", "couldn't", "must", "mustn't", "won't", "don't", "does", "doesn't", "did", "didn't"
|
|
294
|
+
"to", "i", "they", "we", "you", "will", "would", "wouldn't", "may", "might", "could", "couldn't", "must", "mustn't", "shall", "won't", "don't", "does", "doesn't", "did", "didn't"
|
|
299
295
|
],
|
|
300
296
|
|
|
301
297
|
"notPrecededBy": [
|
|
@@ -374,7 +370,7 @@
|
|
|
374
370
|
],
|
|
375
371
|
|
|
376
372
|
"precededBy": [
|
|
377
|
-
"to", "i", "they", "we", "you", "will", "would", "may", "might","could", "couldn't", "must", "mustn't", "would", "wouldn't", "won't", "don't", "doesn't", "did", "didn't"
|
|
373
|
+
"to", "i", "they", "we", "you", "will", "would", "may", "might","could", "couldn't", "must", "mustn't", "shall", "would", "wouldn't", "won't", "don't", "doesn't", "did", "didn't"
|
|
378
374
|
],
|
|
379
375
|
|
|
380
376
|
"notPrecededBy": [
|
|
@@ -532,7 +528,7 @@
|
|
|
532
528
|
],
|
|
533
529
|
|
|
534
530
|
"precededBy": [
|
|
535
|
-
"to", "i", "they", "we", "you", "will", "not", "may", "might", "could", "couldn't", "must", "mustn't", "would", "wouldn't", "won't", "don't", "doesn't", "did", "didn't", "help"
|
|
531
|
+
"to", "i", "they", "we", "you", "will", "not", "may", "might", "could", "couldn't", "must", "mustn't", "shall", "would", "wouldn't", "won't", "don't", "doesn't", "did", "didn't", "help"
|
|
536
532
|
],
|
|
537
533
|
|
|
538
534
|
"notPrecededBy": [
|
|
@@ -570,7 +566,7 @@
|
|
|
570
566
|
],
|
|
571
567
|
|
|
572
568
|
"precededBy": [
|
|
573
|
-
"to", "i", "they", "we", "you", "will", "not", "may", "might", "could", "couldn't", "must", "mustn't", "would", "wouldn't", "won't", "don't", "doesn't", "did", "didn't", "help"
|
|
569
|
+
"to", "i", "they", "we", "you", "will", "not", "may", "might", "could", "couldn't", "must", "mustn't", "shall", "would", "wouldn't", "won't", "don't", "doesn't", "did", "didn't", "help"
|
|
574
570
|
],
|
|
575
571
|
|
|
576
572
|
"notPrecededBy": [
|
|
@@ -608,7 +604,7 @@
|
|
|
608
604
|
],
|
|
609
605
|
|
|
610
606
|
"precededBy": [
|
|
611
|
-
"to", "i", "they", "we", "you", "will", "would", "may", "might", "could", "couldn't", "must", "mustn't", "would", "wouldn't", "won't", "don't", "doesn't", "did", "didn't"
|
|
607
|
+
"to", "i", "they", "we", "you", "will", "would", "may", "might", "could", "couldn't", "must", "mustn't", "shall", "would", "wouldn't", "won't", "don't", "doesn't", "did", "didn't"
|
|
612
608
|
],
|
|
613
609
|
|
|
614
610
|
"notPrecededBy": [
|
|
@@ -885,7 +881,7 @@
|
|
|
885
881
|
],
|
|
886
882
|
|
|
887
883
|
"precededBy": [
|
|
888
|
-
"i", "we", "they", "to", "not", "don't", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "
|
|
884
|
+
"i", "we", "they", "you", "to", "not", "don't", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "shall"
|
|
889
885
|
],
|
|
890
886
|
|
|
891
887
|
"notPrecededBy": [
|
|
@@ -964,7 +960,7 @@
|
|
|
964
960
|
],
|
|
965
961
|
|
|
966
962
|
"precededBy": [
|
|
967
|
-
"i", "we", "they", "to", "not", "don't", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't"
|
|
963
|
+
"i", "we", "they", "to", "not", "don't", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "shall"
|
|
968
964
|
],
|
|
969
965
|
|
|
970
966
|
"notPrecededBy": [
|
|
@@ -976,7 +972,7 @@
|
|
|
976
972
|
],
|
|
977
973
|
|
|
978
974
|
"notSucceededBy": [
|
|
979
|
-
"i", "we", "was", "has", "had", "will", "not", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "of", "number"
|
|
975
|
+
"i", "we", "was", "has", "had", "will", "not", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "shall", "of", "number"
|
|
980
976
|
],
|
|
981
977
|
|
|
982
978
|
"example": "Did you record that TV show?"
|
|
@@ -1043,7 +1039,7 @@
|
|
|
1043
1039
|
],
|
|
1044
1040
|
|
|
1045
1041
|
"precededBy": [
|
|
1046
|
-
"i", "we", "they", "to", "not", "doesn't", "don't", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't"
|
|
1042
|
+
"i", "we", "they", "to", "not", "doesn't", "don't", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "shall"
|
|
1047
1043
|
],
|
|
1048
1044
|
|
|
1049
1045
|
"notPrecededBy": [
|
|
@@ -1055,7 +1051,7 @@
|
|
|
1055
1051
|
],
|
|
1056
1052
|
|
|
1057
1053
|
"notSucceededBy": [
|
|
1058
|
-
"i", "we", "was", "has", "had", "will", "not", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "of"
|
|
1054
|
+
"i", "we", "was", "has", "had", "will", "not", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "shall", "of"
|
|
1059
1055
|
],
|
|
1060
1056
|
|
|
1061
1057
|
"example": "We conflict in our views."
|
|
@@ -1197,11 +1193,11 @@
|
|
|
1197
1193
|
],
|
|
1198
1194
|
|
|
1199
1195
|
"precededBy": [
|
|
1200
|
-
"be", "is", "was", "are", "they're", "were", "very", "heart's", "isn't", "aren't", "wasn't", "weren't", "
|
|
1196
|
+
"be", "is", "was", "are", "they're", "were", "very", "heart's", "isn't", "aren't", "wasn't", "weren't", "very", "somewhat", "quite", "slightly", "largely", "truly"
|
|
1201
1197
|
],
|
|
1202
1198
|
|
|
1203
1199
|
"notPrecededBy": [
|
|
1204
|
-
"misleading", "such", "course", "streaming", "most", "free", "original"
|
|
1200
|
+
"misleading", "such", "course", "streaming", "most", "free", "original", "whatever", "which", "that", "the", "of"
|
|
1205
1201
|
],
|
|
1206
1202
|
|
|
1207
1203
|
"succeededBy": [
|
|
@@ -1209,7 +1205,7 @@
|
|
|
1209
1205
|
],
|
|
1210
1206
|
|
|
1211
1207
|
"notSucceededBy": [
|
|
1212
|
-
"creators", "rules"
|
|
1208
|
+
"creators", "rules", "which", "to", "on", "is", "was", "from", "as", "at", "moderation", "officer", "creation", "which", "will", "would", "won't", "wouldn't", "may", "might", "must", "mustn't", "including"
|
|
1213
1209
|
],
|
|
1214
1210
|
|
|
1215
1211
|
"example": "I feel content about this."
|
|
@@ -1237,7 +1233,7 @@
|
|
|
1237
1233
|
],
|
|
1238
1234
|
|
|
1239
1235
|
"precededBy": [
|
|
1240
|
-
"to", "i", "they", "we", "you", "will", "would", "may", "might", "would", "wouldn't", "won't", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "did", "didn't", "then"
|
|
1236
|
+
"to", "i", "they", "we", "you", "will", "would", "may", "might", "would", "wouldn't", "won't", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "shall", "did", "didn't", "then"
|
|
1241
1237
|
],
|
|
1242
1238
|
|
|
1243
1239
|
"notPrecededBy": [
|
|
@@ -1277,7 +1273,7 @@
|
|
|
1277
1273
|
],
|
|
1278
1274
|
|
|
1279
1275
|
"precededBy": [
|
|
1280
|
-
"to", "i", "they", "we", "you", "will", "would", "may", "might", "would", "wouldn't", "won't", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "did", "didn't"
|
|
1276
|
+
"to", "i", "they", "we", "you", "will", "would", "may", "might", "would", "wouldn't", "won't", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "shall", "did", "didn't"
|
|
1281
1277
|
],
|
|
1282
1278
|
|
|
1283
1279
|
"notPrecededBy": [
|
|
@@ -1317,7 +1313,7 @@
|
|
|
1317
1313
|
],
|
|
1318
1314
|
|
|
1319
1315
|
"precededBy": [
|
|
1320
|
-
"to", "will", "help", "can", "we", "not", "would", "wouldn't", "won't", "do", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "may", "might", "did", "didn't", "directly", "does", "they", "adequately", "you", "really", "actually", "effectively", "can't", "leaders", "properly", "i", "specifically", "still", "please", "may", "did", "potentially", "cannot", "meaningfully", "finally", "continually", "it'd", "they'd", "visibly", "ever", "i'll", "itself", "therefore"
|
|
1316
|
+
"to", "will", "help", "can", "we", "not", "would", "wouldn't", "won't", "do", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "shall", "may", "might", "did", "didn't", "directly", "does", "they", "adequately", "you", "really", "actually", "effectively", "can't", "leaders", "properly", "i", "specifically", "still", "please", "may", "did", "potentially", "cannot", "meaningfully", "finally", "continually", "it'd", "they'd", "visibly", "ever", "i'll", "itself", "therefore"
|
|
1321
1317
|
],
|
|
1322
1318
|
|
|
1323
1319
|
"notPrecededBy": [
|
|
@@ -1434,7 +1430,7 @@
|
|
|
1434
1430
|
],
|
|
1435
1431
|
|
|
1436
1432
|
"precededBy": [
|
|
1437
|
-
"i", "we", "would", "wouldn't", "won't", "do", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "may", "might", "did", "didn't", "does", "doesn't"
|
|
1433
|
+
"i", "we", "would", "wouldn't", "won't", "do", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "shall", "may", "might", "did", "didn't", "does", "doesn't"
|
|
1438
1434
|
],
|
|
1439
1435
|
|
|
1440
1436
|
"notPrecededBy": [
|
|
@@ -1514,7 +1510,7 @@
|
|
|
1514
1510
|
],
|
|
1515
1511
|
|
|
1516
1512
|
"notPrecededBy": [
|
|
1517
|
-
"the", "a", "all", "his", "her", "its", "our", "your", "their"
|
|
1513
|
+
"the", "a", "all", "his", "her", "its", "our", "your", "their", "my"
|
|
1518
1514
|
],
|
|
1519
1515
|
|
|
1520
1516
|
"succeededBy": [
|
|
@@ -1626,7 +1622,7 @@
|
|
|
1626
1622
|
],
|
|
1627
1623
|
|
|
1628
1624
|
"precededBy": [
|
|
1629
|
-
"to", "i", "they", "we", "should", "will", "would", "wouldn't", "won't", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "may", "might", "did", "didn't", "does", "doesn't"
|
|
1625
|
+
"to", "i", "they", "we", "should", "will", "would", "wouldn't", "won't", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "shall", "may", "might", "did", "didn't", "does", "doesn't"
|
|
1630
1626
|
],
|
|
1631
1627
|
|
|
1632
1628
|
"notPrecededBy": [
|
|
@@ -1666,7 +1662,7 @@
|
|
|
1666
1662
|
],
|
|
1667
1663
|
|
|
1668
1664
|
"precededBy": [
|
|
1669
|
-
"to", "i", "they", "we", "should", "will", "would", "wouldn't", "won't", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "may", "might", "did", "didn't", "does", "doesn't"
|
|
1665
|
+
"to", "i", "they", "we", "should", "will", "would", "wouldn't", "won't", "don't", "doesn't", "should", "shouldn't", "could", "couldn't", "must", "mustn't", "shall", "may", "might", "did", "didn't", "does", "doesn't"
|
|
1670
1666
|
],
|
|
1671
1667
|
|
|
1672
1668
|
"notPrecededBy": [
|
|
@@ -1706,7 +1702,7 @@
|
|
|
1706
1702
|
],
|
|
1707
1703
|
|
|
1708
1704
|
"precededBy": [
|
|
1709
|
-
"to", "not", "doesn't", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't"
|
|
1705
|
+
"to", "not", "doesn't", "should", "shouldn't", "will", "would", "wouldn't", "won't", "does", "doesn't", "can", "can't", "may", "might", "could", "couldn't", "must", "mustn't", "shall"
|
|
1710
1706
|
],
|
|
1711
1707
|
|
|
1712
1708
|
"notPrecededBy": [
|
|
@@ -9,23 +9,23 @@ export function getNormalizationMapForSpeech(words, language) {
|
|
|
9
9
|
const fourDigitYearPattern = /^[0-9][0-9][0-9][0-9]$/;
|
|
10
10
|
const fourDigitDecadePattern = /^[0-9][0-9][0-9]0s$/;
|
|
11
11
|
const fourDigitYearRangePattern = /^[0-9][0-9][0-9][0-9][\-\–][0-9][0-9][0-9][0-9]$/;
|
|
12
|
-
const
|
|
12
|
+
const wordsPrecedingAYear = [
|
|
13
13
|
"in", "since", "©",
|
|
14
14
|
"january", "february", "march", "april", "may", "june", "july", "august", "september", "october", "november", "december",
|
|
15
15
|
"jan", "feb", "mar", "apr", "may", "jun", "jul", "aug", "sep", "oct", "nov", "dec"
|
|
16
16
|
];
|
|
17
17
|
for (let wordIndex = 0; wordIndex < words.length; wordIndex++) {
|
|
18
18
|
const word = words[wordIndex];
|
|
19
|
-
const
|
|
19
|
+
const lowerCaseWord = word.toLocaleLowerCase();
|
|
20
20
|
const nextWords = words.slice(wordIndex + 1);
|
|
21
21
|
const nextWord = nextWords[0];
|
|
22
|
-
if (
|
|
22
|
+
if (wordsPrecedingAYear.includes(lowerCaseWord) &&
|
|
23
23
|
fourDigitYearPattern.test(nextWord)) {
|
|
24
24
|
const normalizedString = normalizeFourDigitYearString(nextWord);
|
|
25
25
|
normalizationMap.set(wordIndex + 1, normalizedString);
|
|
26
26
|
wordIndex += 1;
|
|
27
27
|
}
|
|
28
|
-
else if (
|
|
28
|
+
else if (['the', 'in'].includes(lowerCaseWord) &&
|
|
29
29
|
fourDigitDecadePattern.test(nextWord)) {
|
|
30
30
|
const normalizedString = normalizeFourDigitDecadeString(nextWord);
|
|
31
31
|
normalizationMap.set(wordIndex + 1, normalizedString);
|
|
@@ -56,10 +56,10 @@ export function normalizeFourDigitYearString(yearString) {
|
|
|
56
56
|
return normalizedString;
|
|
57
57
|
}
|
|
58
58
|
export function normalizeFourDigitDecadeString(decadeString) {
|
|
59
|
-
const firstTwoDigitsValue =
|
|
60
|
-
const secondTwoDigitsValue =
|
|
59
|
+
const firstTwoDigitsValue = parseInt(decadeString.substring(0, 2));
|
|
60
|
+
const secondTwoDigitsValue = parseInt(decadeString.substring(2, 4));
|
|
61
61
|
let normalizedString;
|
|
62
|
-
if (firstTwoDigitsValue >= 10 && firstTwoDigitsValue
|
|
62
|
+
if (firstTwoDigitsValue >= 10 && firstTwoDigitsValue >= 10) {
|
|
63
63
|
normalizedString = `${firstTwoDigitsValue} ${secondTwoDigitsValue}s`;
|
|
64
64
|
}
|
|
65
65
|
else {
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"TextNormalizer.js","sourceRoot":"","sources":["../../src/nlp/TextNormalizer.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,oBAAoB,EAAE,MAAM,wBAAwB,CAAA;AAE7D,MAAM,UAAU,4BAA4B,CAAC,KAAe,EAAE,QAAgB;IAC7E,QAAQ,GAAG,oBAAoB,CAAC,QAAQ,CAAC,CAAA;IAEzC,MAAM,gBAAgB,GAAG,IAAI,GAAG,EAAkB,CAAA;IAElD,IAAI,QAAQ,IAAI,IAAI,EAAE;QACrB,OAAO,gBAAgB,CAAA;KACvB;IAED,MAAM,aAAa,GAAG,mBAAmB,CAAA;IAEzC,MAAM,oBAAoB,GAAG,wBAAwB,CAAA;IACrD,MAAM,sBAAsB,GAAG,qBAAqB,CAAA;IAEpD,MAAM,yBAAyB,GAAG,kDAAkD,CAAA;IAEpF,MAAM,
|
|
1
|
+
{"version":3,"file":"TextNormalizer.js","sourceRoot":"","sources":["../../src/nlp/TextNormalizer.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,oBAAoB,EAAE,MAAM,wBAAwB,CAAA;AAE7D,MAAM,UAAU,4BAA4B,CAAC,KAAe,EAAE,QAAgB;IAC7E,QAAQ,GAAG,oBAAoB,CAAC,QAAQ,CAAC,CAAA;IAEzC,MAAM,gBAAgB,GAAG,IAAI,GAAG,EAAkB,CAAA;IAElD,IAAI,QAAQ,IAAI,IAAI,EAAE;QACrB,OAAO,gBAAgB,CAAA;KACvB;IAED,MAAM,aAAa,GAAG,mBAAmB,CAAA;IAEzC,MAAM,oBAAoB,GAAG,wBAAwB,CAAA;IACrD,MAAM,sBAAsB,GAAG,qBAAqB,CAAA;IAEpD,MAAM,yBAAyB,GAAG,kDAAkD,CAAA;IAEpF,MAAM,mBAAmB,GAAG;QAC3B,IAAI,EAAE,OAAO,EAAE,GAAG;QAClB,SAAS,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,WAAW,EAAE,SAAS,EAAE,UAAU,EAAE,UAAU;QACxH,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK;KAClF,CAAA;IAED,KAAK,IAAI,SAAS,GAAG,CAAC,EAAE,SAAS,GAAG,KAAK,CAAC,MAAM,EAAE,SAAS,EAAE,EAAE;QAC9D,MAAM,IAAI,GAAG,KAAK,CAAC,SAAS,CAAC,CAAA;QAC7B,MAAM,aAAa,GAAG,IAAI,CAAC,iBAAiB,EAAE,CAAA;QAE9C,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,CAAA;QAC5C,MAAM,QAAQ,GAAG,SAAS,CAAC,CAAC,CAAC,CAAA;QAE7B,IACC,mBAAmB,CAAC,QAAQ,CAAC,aAAa,CAAC;YAC3C,oBAAoB,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE;YACrC,MAAM,gBAAgB,GAAG,4BAA4B,CAAC,QAAQ,CAAC,CAAA;YAE/D,gBAAgB,CAAC,GAAG,CAAC,SAAS,GAAG,CAAC,EAAE,gBAAgB,CAAC,CAAA;YAErD,SAAS,IAAI,CAAC,CAAA;SACd;aAAM,IACN,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC,QAAQ,CAAC,aAAa,CAAC;YACrC,sBAAsB,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE;YAEvC,MAAM,gBAAgB,GAAG,8BAA8B,CAAC,QAAQ,CAAC,CAAA;YAEjE,gBAAgB,CAAC,GAAG,CAAC,SAAS,GAAG,CAAC,EAAE,gBAAgB,CAAC,CAAA;YAErD,SAAS,IAAI,CAAC,CAAA;SACd;aAAM,IAAI,yBAAyB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE;YAChD,MAAM,eAAe,GAAG,4BAA4B,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;YAC1E,MAAM,aAAa,GAAG,4BAA4B,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;YAExE,MAAM,gBAAgB,GAAG,GAAG,eAAe,OAAO,aAAa,EAAE,CAAA;YAEjE,gBAAgB,CAAC,GAAG,CAAC,SAAS,EAAE,gBAAgB,CAAC,CAAA;SACjD;KACD;IAED,OAAO,gBAAgB,CAAA;AACxB,CAAC;AAED,MAAM,UAAU,4BAA4B,CAAC,UAAkB;IAC9D,MAAM,mBAAmB,GAAG,UAAU,CAAC,UAAU,CAAC,SAAS,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAClE,MAAM,oBAAoB,GAAG,UAAU,CAAC,UAAU,CAAC,SAAS,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAEnE,IAAI,gBAAwB,CAAA;IAE5B,IAAI,mBAAmB,IAAI,EAAE,IAAI,oBAAoB,IAAI,EAAE,EAAE;QAC5D,gBAAgB,GAAG,GAAG,mBAAmB,IAAI,oBAAoB,EAAE,CAAA;KACnE;SAAM,IAAI,mBAAmB,IAAI,EAAE,IAAI,mBAAmB,GAAG,EAAE,IAAI,CAAC,IAAI,oBAAoB,GAAG,EAAE,EAAE;QACnG,gBAAgB,GAAG,GAAG,mBAAmB,OAAO,oBAAoB,EAAE,CAAA;KACtE;SAAM;QACN,gBAAgB,GAAG,UAAU,CAAA;KAC7B;IAED,OAAO,gBAAgB,CAAA;AACxB,CAAC;AAED,MAAM,UAAU,8BAA8B,CAAC,YAAoB;IAClE,MAAM,mBAAmB,GAAG,QAAQ,CAAC,YAAY,CAAC,SAAS,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAClE,MAAM,oBAAoB,GAAG,QAAQ,CAAC,YAAY,CAAC,SAAS,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAEnE,IAAI,gBAAwB,CAAA;IAE5B,IAAI,mBAAmB,IAAI,EAAE,IAAI,mBAAmB,IAAI,EAAE,EAAE;QAC3D,gBAAgB,GAAG,GAAG,mBAAmB,IAAI,oBAAoB,GAAG,CAAA;KACpE;SAAM;QACN,gBAAgB,GAAG,YAAY,CAAA;KAC/B;IAED,OAAO,gBAAgB,CAAA;AACxB,CAAC"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "echogarden",
|
|
3
|
-
"version": "0.3.
|
|
3
|
+
"version": "0.3.2",
|
|
4
4
|
"description": "An integrated speech toolbox designed with end-users in mind.",
|
|
5
5
|
"author": "Rotem Dan",
|
|
6
6
|
"license": "GPL-3.0-only",
|
|
@@ -55,8 +55,8 @@
|
|
|
55
55
|
"echogarden": "./dist/cli/CLILauncher.js"
|
|
56
56
|
},
|
|
57
57
|
"dependencies": {
|
|
58
|
-
"@aws-sdk/client-polly": "^3.
|
|
59
|
-
"@aws-sdk/client-transcribe-streaming": "^3.
|
|
58
|
+
"@aws-sdk/client-polly": "^3.363.0",
|
|
59
|
+
"@aws-sdk/client-transcribe-streaming": "^3.363.0",
|
|
60
60
|
"@echogarden/espeak-ng-emscripten": "^0.1.2",
|
|
61
61
|
"@echogarden/fasttext-wasm": "^0.1.0",
|
|
62
62
|
"@echogarden/flite-wasi": "^0.1.1",
|
|
@@ -73,7 +73,7 @@
|
|
|
73
73
|
"@types/graceful-fs": "^4.1.6",
|
|
74
74
|
"alawmulaw": "^6.0.0",
|
|
75
75
|
"buffer-split": "^1.0.0",
|
|
76
|
-
"chalk": "^5.
|
|
76
|
+
"chalk": "^5.3.0",
|
|
77
77
|
"cldr-segmentation": "^2.2.0",
|
|
78
78
|
"command-exists": "^1.2.9",
|
|
79
79
|
"compromise": "^14.9.0",
|
|
@@ -87,7 +87,7 @@
|
|
|
87
87
|
"jieba-wasm": "^0.0.2",
|
|
88
88
|
"jsdom": "^22.1.0",
|
|
89
89
|
"kuromoji": "^0.1.2",
|
|
90
|
-
"microsoft-cognitiveservices-speech-sdk": "^1.
|
|
90
|
+
"microsoft-cognitiveservices-speech-sdk": "^1.30.0",
|
|
91
91
|
"moving-median": "^1.0.0",
|
|
92
92
|
"msgpack-lite": "^0.1.26",
|
|
93
93
|
"ndarray": "^1.0.19",
|
|
@@ -122,14 +122,14 @@
|
|
|
122
122
|
"@types/msgpack-lite": "^0.1.8",
|
|
123
123
|
"@types/ndarray": "^1.0.11",
|
|
124
124
|
"@types/ndarray-ops": "^1.2.4",
|
|
125
|
-
"@types/node": "^20.3.
|
|
125
|
+
"@types/node": "^20.3.3",
|
|
126
126
|
"@types/recursive-readdir": "^2.2.1",
|
|
127
127
|
"@types/tar": "^6.1.5",
|
|
128
128
|
"@types/ws": "^8.5.5",
|
|
129
129
|
"@typescript-eslint/eslint-plugin": "^5.60.1",
|
|
130
130
|
"@typescript-eslint/parser": "^5.60.1",
|
|
131
|
-
"eslint": "^8.
|
|
131
|
+
"eslint": "^8.44.0",
|
|
132
132
|
"ts-json-schema-generator": "^1.2.0",
|
|
133
|
-
"typescript": "^5.1.
|
|
133
|
+
"typescript": "^5.1.6"
|
|
134
134
|
}
|
|
135
135
|
}
|