plseng commited on
Commit
21b7158
ยท
verified ยท
1 Parent(s): d847a85

new model

Browse files
Files changed (2) hide show
  1. checkpoints/khmer_rnn.pt +3 -0
  2. checkpoints/vocab.json +411 -173
checkpoints/khmer_rnn.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6782698ea0fe8dcb953ed87d9f1a948eface721b29614a4a16d27b9126d3b2
3
+ size 9693836
checkpoints/vocab.json CHANGED
@@ -25,177 +25,415 @@
25
  "8": 23,
26
  "9": 24,
27
  ":": 25,
28
- "=": 26,
29
- "?": 27,
30
- "@": 28,
31
- "A": 29,
32
- "B": 30,
33
- "C": 31,
34
- "D": 32,
35
- "E": 33,
36
- "F": 34,
37
- "G": 35,
38
- "H": 36,
39
- "I": 37,
40
- "J": 38,
41
- "K": 39,
42
- "L": 40,
43
- "M": 41,
44
- "N": 42,
45
- "O": 43,
46
- "P": 44,
47
- "Q": 45,
48
- "R": 46,
49
- "S": 47,
50
- "T": 48,
51
- "U": 49,
52
- "V": 50,
53
- "W": 51,
54
- "X": 52,
55
- "Y": 53,
56
- "Z": 54,
57
- "[": 55,
58
- "]": 56,
59
- "_": 57,
60
- "a": 58,
61
- "b": 59,
62
- "c": 60,
63
- "d": 61,
64
- "e": 62,
65
- "f": 63,
66
- "g": 64,
67
- "h": 65,
68
- "i": 66,
69
- "j": 67,
70
- "k": 68,
71
- "l": 69,
72
- "m": 70,
73
- "n": 71,
74
- "o": 72,
75
- "p": 73,
76
- "q": 74,
77
- "r": 75,
78
- "s": 76,
79
- "t": 77,
80
- "u": 78,
81
- "v": 79,
82
- "w": 80,
83
- "x": 81,
84
- "y": 82,
85
- "z": 83,
86
- "{": 84,
87
- "|": 85,
88
- "~": 86,
89
- "ยฉ": 87,
90
- "ยซ": 88,
91
- "ยป": 89,
92
- "รก": 90,
93
- "รฎ": 91,
94
- "รฏ": 92,
95
- "รท": 93,
96
- "แž€": 94,
97
- "แž": 95,
98
- "แž‚": 96,
99
- "แžƒ": 97,
100
- "แž„": 98,
101
- "แž…": 99,
102
- "แž†": 100,
103
- "แž‡": 101,
104
- "แžˆ": 102,
105
- "แž‰": 103,
106
- "แžŠ": 104,
107
- "แž‹": 105,
108
- "แžŒ": 106,
109
- "แž": 107,
110
- "แžŽ": 108,
111
- "แž": 109,
112
- "แž": 110,
113
- "แž‘": 111,
114
- "แž’": 112,
115
- "แž“": 113,
116
- "แž”": 114,
117
- "แž•": 115,
118
- "แž–": 116,
119
- "แž—": 117,
120
- "แž˜": 118,
121
- "แž™": 119,
122
- "แžš": 120,
123
- "แž›": 121,
124
- "แžœ": 122,
125
- "แžŸ": 123,
126
- "แž ": 124,
127
- "แžก": 125,
128
- "แžข": 126,
129
- "แžฅ": 127,
130
- "แžฆ": 128,
131
- "แžง": 129,
132
- "แžช": 130,
133
- "แžซ": 131,
134
- "แžฌ": 132,
135
- "แžญ": 133,
136
- "แžฎ": 134,
137
- "แžฏ": 135,
138
- "แžฑ": 136,
139
- "แžฒ": 137,
140
- "แžณ": 138,
141
- "แžถ": 139,
142
- "แžท": 140,
143
- "แžธ": 141,
144
- "แžน": 142,
145
- "แžบ": 143,
146
- "แžป": 144,
147
- "แžผ": 145,
148
- "แžฝ": 146,
149
- "แžพ": 147,
150
- "แžฟ": 148,
151
- "แŸ€": 149,
152
- "แŸ": 150,
153
- "แŸ‚": 151,
154
- "แŸƒ": 152,
155
- "แŸ„": 153,
156
- "แŸ…": 154,
157
- "แŸ†": 155,
158
- "แŸ‡": 156,
159
- "แŸˆ": 157,
160
- "แŸ‰": 158,
161
- "แŸŠ": 159,
162
- "แŸ‹": 160,
163
- "แŸŒ": 161,
164
- "แŸ": 162,
165
- "แŸŽ": 163,
166
- "แŸ": 164,
167
- "แŸ": 165,
168
- "แŸ’": 166,
169
- "แŸ”": 167,
170
- "แŸ•": 168,
171
- "แŸ–": 169,
172
- "แŸ—": 170,
173
- "แŸ›": 171,
174
- "แŸ ": 172,
175
- "แŸก": 173,
176
- "แŸข": 174,
177
- "แŸฃ": 175,
178
- "แŸค": 176,
179
- "แŸฅ": 177,
180
- "แŸฆ": 178,
181
- "แŸง": 179,
182
- "แŸจ": 180,
183
- "แŸฉ": 181,
184
- "โ€": 182,
185
- "โ€“": 183,
186
- "โ€™": 184,
187
- "โ€œ": 185,
188
- "โ€": 186,
189
- "โ€ฆ": 187,
190
- "โ™€": 188,
191
- "๏ธ": 189,
192
- "๏ผš": 190,
193
- "๐Ÿป": 191,
194
- "๐Ÿ‘‰": 192,
195
- "๐Ÿ’": 193,
196
- "๐Ÿ˜": 194,
197
- "๐Ÿ˜ ": 195,
198
- "๐Ÿ˜ญ": 196,
199
- "๐Ÿ™": 197,
200
- "๐Ÿคฆ": 198
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
 
25
  "8": 23,
26
  "9": 24,
27
  ":": 25,
28
+ ";": 26,
29
+ "<": 27,
30
+ "=": 28,
31
+ ">": 29,
32
+ "?": 30,
33
+ "@": 31,
34
+ "A": 32,
35
+ "B": 33,
36
+ "C": 34,
37
+ "D": 35,
38
+ "E": 36,
39
+ "F": 37,
40
+ "G": 38,
41
+ "H": 39,
42
+ "I": 40,
43
+ "J": 41,
44
+ "K": 42,
45
+ "L": 43,
46
+ "M": 44,
47
+ "N": 45,
48
+ "O": 46,
49
+ "P": 47,
50
+ "Q": 48,
51
+ "R": 49,
52
+ "S": 50,
53
+ "T": 51,
54
+ "U": 52,
55
+ "V": 53,
56
+ "W": 54,
57
+ "X": 55,
58
+ "Y": 56,
59
+ "Z": 57,
60
+ "[": 58,
61
+ "\\": 59,
62
+ "]": 60,
63
+ "^": 61,
64
+ "_": 62,
65
+ "`": 63,
66
+ "a": 64,
67
+ "b": 65,
68
+ "c": 66,
69
+ "d": 67,
70
+ "e": 68,
71
+ "f": 69,
72
+ "g": 70,
73
+ "h": 71,
74
+ "i": 72,
75
+ "j": 73,
76
+ "k": 74,
77
+ "l": 75,
78
+ "m": 76,
79
+ "n": 77,
80
+ "o": 78,
81
+ "p": 79,
82
+ "q": 80,
83
+ "r": 81,
84
+ "s": 82,
85
+ "t": 83,
86
+ "u": 84,
87
+ "v": 85,
88
+ "w": 86,
89
+ "x": 87,
90
+ "y": 88,
91
+ "z": 89,
92
+ "{": 90,
93
+ "|": 91,
94
+ "}": 92,
95
+ "~": 93,
96
+ "ยฅ": 94,
97
+ "ยฉ": 95,
98
+ "ยซ": 96,
99
+ "ยฌ": 97,
100
+ "ยญ": 98,
101
+ "ยฎ": 99,
102
+ "ยฒ": 100,
103
+ "ยท": 101,
104
+ "ยป": 102,
105
+ "ร€": 103,
106
+ "รˆ": 104,
107
+ "ร‰": 105,
108
+ "ร‘": 106,
109
+ "ร–": 107,
110
+ "ร—": 108,
111
+ "ร": 109,
112
+ "ร ": 110,
113
+ "รก": 111,
114
+ "รฃ": 112,
115
+ "รค": 113,
116
+ "รฆ": 114,
117
+ "รง": 115,
118
+ "รจ": 116,
119
+ "รฉ": 117,
120
+ "รช": 118,
121
+ "รญ": 119,
122
+ "รฎ": 120,
123
+ "รฏ": 121,
124
+ "รฑ": 122,
125
+ "รณ": 123,
126
+ "รด": 124,
127
+ "รถ": 125,
128
+ "รท": 126,
129
+ "รธ": 127,
130
+ "รน": 128,
131
+ "รบ": 129,
132
+ "รป": 130,
133
+ "รผ": 131,
134
+ "ฤ": 132,
135
+ "ฤƒ": 133,
136
+ "ฤ‡": 134,
137
+ "ฤŒ": 135,
138
+ "ฤฏ": 136,
139
+ "ล": 137,
140
+ "ล“": 138,
141
+ "ลก": 139,
142
+ "ลฉ": 140,
143
+ "ลซ": 141,
144
+ "ฦฐ": 142,
145
+ "ฮผ": 143,
146
+ "ะ’": 144,
147
+ "ะœ": 145,
148
+ "ะ": 146,
149
+ "ะ ": 147,
150
+ "ะฐ": 148,
151
+ "ะฑ": 149,
152
+ "ะฒ": 150,
153
+ "ะณ": 151,
154
+ "ะด": 152,
155
+ "ะต": 153,
156
+ "ะถ": 154,
157
+ "ะท": 155,
158
+ "ะธ": 156,
159
+ "ะบ": 157,
160
+ "ะป": 158,
161
+ "ะผ": 159,
162
+ "ะฝ": 160,
163
+ "ะพ": 161,
164
+ "ะฟ": 162,
165
+ "ั€": 163,
166
+ "ั": 164,
167
+ "ั‚": 165,
168
+ "ัƒ": 166,
169
+ "ั…": 167,
170
+ "ั†": 168,
171
+ "ั‡": 169,
172
+ "ัˆ": 170,
173
+ "ั‰": 171,
174
+ "ั‹": 172,
175
+ "ัŒ": 173,
176
+ "ั": 174,
177
+ "ัŽ": 175,
178
+ "ั": 176,
179
+ "เธ": 177,
180
+ "เธ‚": 178,
181
+ "เธ„": 179,
182
+ "เธ‡": 180,
183
+ "เธˆ": 181,
184
+ "เธŠ": 182,
185
+ "เธ‹": 183,
186
+ "เธ“": 184,
187
+ "เธ”": 185,
188
+ "เธ•": 186,
189
+ "เธ–": 187,
190
+ "เธ—": 188,
191
+ "เธ™": 189,
192
+ "เธš": 190,
193
+ "เธ›": 191,
194
+ "เธŸ": 192,
195
+ "เธก": 193,
196
+ "เธข": 194,
197
+ "เธฃ": 195,
198
+ "เธฅ": 196,
199
+ "เธง": 197,
200
+ "เธช": 198,
201
+ "เธซ": 199,
202
+ "เธญ": 200,
203
+ "เธฐ": 201,
204
+ "เธฑ": 202,
205
+ "เธฒ": 203,
206
+ "เธด": 204,
207
+ "เธต": 205,
208
+ "เธถ": 206,
209
+ "เธท": 207,
210
+ "เธธ": 208,
211
+ "เธน": 209,
212
+ "เน€": 210,
213
+ "เน": 211,
214
+ "เน‚": 212,
215
+ "เนƒ": 213,
216
+ "เน„": 214,
217
+ "เน†": 215,
218
+ "เน‡": 216,
219
+ "เนˆ": 217,
220
+ "เน‰": 218,
221
+ "เนŠ": 219,
222
+ "เนŒ": 220,
223
+ "แž€": 221,
224
+ "แž": 222,
225
+ "แž‚": 223,
226
+ "แžƒ": 224,
227
+ "แž„": 225,
228
+ "แž…": 226,
229
+ "แž†": 227,
230
+ "แž‡": 228,
231
+ "แžˆ": 229,
232
+ "แž‰": 230,
233
+ "แžŠ": 231,
234
+ "แž‹": 232,
235
+ "แžŒ": 233,
236
+ "แž": 234,
237
+ "แžŽ": 235,
238
+ "แž": 236,
239
+ "แž": 237,
240
+ "แž‘": 238,
241
+ "แž’": 239,
242
+ "แž“": 240,
243
+ "แž”": 241,
244
+ "แž•": 242,
245
+ "แž–": 243,
246
+ "แž—": 244,
247
+ "แž˜": 245,
248
+ "แž™": 246,
249
+ "แžš": 247,
250
+ "แž›": 248,
251
+ "แžœ": 249,
252
+ "แž": 250,
253
+ "แžŸ": 251,
254
+ "แž ": 252,
255
+ "แžก": 253,
256
+ "แžข": 254,
257
+ "แžฅ": 255,
258
+ "แžฆ": 256,
259
+ "แžง": 257,
260
+ "แžฉ": 258,
261
+ "แžช": 259,
262
+ "แžซ": 260,
263
+ "แžฌ": 261,
264
+ "แžญ": 262,
265
+ "แžฎ": 263,
266
+ "แžฏ": 264,
267
+ "แžฐ": 265,
268
+ "แžฑ": 266,
269
+ "แžฒ": 267,
270
+ "แžณ": 268,
271
+ "แžถ": 269,
272
+ "แžท": 270,
273
+ "แžธ": 271,
274
+ "แžน": 272,
275
+ "แžบ": 273,
276
+ "แžป": 274,
277
+ "แžผ": 275,
278
+ "แžฝ": 276,
279
+ "แžพ": 277,
280
+ "แžฟ": 278,
281
+ "แŸ€": 279,
282
+ "แŸ": 280,
283
+ "แŸ‚": 281,
284
+ "แŸƒ": 282,
285
+ "แŸ„": 283,
286
+ "แŸ…": 284,
287
+ "แŸ†": 285,
288
+ "แŸ‡": 286,
289
+ "แŸˆ": 287,
290
+ "แŸ‰": 288,
291
+ "แŸŠ": 289,
292
+ "แŸ‹": 290,
293
+ "แŸŒ": 291,
294
+ "แŸ": 292,
295
+ "แŸŽ": 293,
296
+ "แŸ": 294,
297
+ "แŸ": 295,
298
+ "แŸ‘": 296,
299
+ "แŸ’": 297,
300
+ "แŸ”": 298,
301
+ "แŸ•": 299,
302
+ "แŸ–": 300,
303
+ "แŸ—": 301,
304
+ "แŸ˜": 302,
305
+ "แŸ›": 303,
306
+ "แŸ ": 304,
307
+ "แŸก": 305,
308
+ "แŸข": 306,
309
+ "แŸฃ": 307,
310
+ "แŸค": 308,
311
+ "แŸฅ": 309,
312
+ "แŸฆ": 310,
313
+ "แŸง": 311,
314
+ "แŸจ": 312,
315
+ "แŸฉ": 313,
316
+ "แบง": 314,
317
+ "แบฟ": 315,
318
+ "แป‘": 316,
319
+ "แปฃ": 317,
320
+ "โ€Œ": 318,
321
+ "โ€": 319,
322
+ "โ€“": 320,
323
+ "โ€”": 321,
324
+ "โ€˜": 322,
325
+ "โ€™": 323,
326
+ "โ€œ": 324,
327
+ "โ€": 325,
328
+ "โ€ฆ": 326,
329
+ "โ€ฌ": 327,
330
+ "โ€ญ": 328,
331
+ "โ€ณ": 329,
332
+ "โฃ": 330,
333
+ "โ‚ฌ": 331,
334
+ "โ„–": 332,
335
+ "โ„ข": 333,
336
+ "โ†’": 334,
337
+ "โ‹†": 335,
338
+ "โ– ": 336,
339
+ "โ—": 337,
340
+ "โ˜Ž": 338,
341
+ "โ˜ž": 339,
342
+ "โ˜น": 340,
343
+ "โ˜บ": 341,
344
+ "โ™€": 342,
345
+ "โ™‚": 343,
346
+ "โ™ฅ": 344,
347
+ "โŒ": 345,
348
+ "โค": 346,
349
+ "ใ€Š": 347,
350
+ "ใ€‹": 348,
351
+ "ใ„": 349,
352
+ "ใŽ": 350,
353
+ "ใ“": 351,
354
+ "ใ™": 352,
355
+ "ใŸ": 353,
356
+ "ใค": 354,
357
+ "ใช": 355,
358
+ "ใซ": 356,
359
+ "ใฎ": 357,
360
+ "ใฏ": 358,
361
+ "ใ‚„": 359,
362
+ "ใ‚Š": 360,
363
+ "ใ‚‹": 361,
364
+ "ใ‚Œ": 362,
365
+ "ใ‚’": 363,
366
+ "ใ‚ฒ": 364,
367
+ "ใƒ ": 365,
368
+ "ใƒผ": 366,
369
+ "ไพ›": 367,
370
+ "ๅ…จ": 368,
371
+ "ๅ›ฝ": 369,
372
+ "ๅญ": 370,
373
+ "ๆŒ": 371,
374
+ "ๆ™‚": 372,
375
+ "็›ฎ": 373,
376
+ "็ทš": 374,
377
+ "่ฆช": 375,
378
+ "่จ€": 376,
379
+ "้•ท": 377,
380
+ "้–“": 378,
381
+ "๏€ญ": 379,
382
+ "๏ธ": 380,
383
+ "๏ปฟ": 381,
384
+ "๏ผ…": 382,
385
+ "๏ผš": 383,
386
+ "๐Ÿ‡ฆ": 384,
387
+ "๐Ÿ‡ญ": 385,
388
+ "๐Ÿ‡ฐ": 386,
389
+ "๐Ÿ‡ฑ": 387,
390
+ "๐ŸŒฑ": 388,
391
+ "๐ŸŒด": 389,
392
+ "๐Ÿป": 390,
393
+ "๐Ÿผ": 391,
394
+ "๐Ÿฝ": 392,
395
+ "๐Ÿ‘‡": 393,
396
+ "๐Ÿ‘‰": 394,
397
+ "๐Ÿ‘Œ": 395,
398
+ "๐Ÿ‘Ž": 396,
399
+ "๐Ÿ‘": 397,
400
+ "๐Ÿ‘ฉ": 398,
401
+ "๐Ÿ‘ต": 399,
402
+ "๐Ÿ’": 400,
403
+ "๐Ÿ’”": 401,
404
+ "๐Ÿ’š": 402,
405
+ "๐Ÿ’ข": 403,
406
+ "๐Ÿ’ช": 404,
407
+ "๐Ÿ“Œ": 405,
408
+ "๐Ÿ˜‚": 406,
409
+ "๐Ÿ˜…": 407,
410
+ "๐Ÿ˜‰": 408,
411
+ "๐Ÿ˜‹": 409,
412
+ "๐Ÿ˜Œ": 410,
413
+ "๐Ÿ˜": 411,
414
+ "๐Ÿ˜Ž": 412,
415
+ "๐Ÿ˜“": 413,
416
+ "๐Ÿ˜”": 414,
417
+ "๐Ÿ˜˜": 415,
418
+ "๐Ÿ˜œ": 416,
419
+ "๐Ÿ˜": 417,
420
+ "๐Ÿ˜ ": 418,
421
+ "๐Ÿ˜ข": 419,
422
+ "๐Ÿ˜ค": 420,
423
+ "๐Ÿ˜ฅ": 421,
424
+ "๐Ÿ˜ช": 422,
425
+ "๐Ÿ˜ญ": 423,
426
+ "๐Ÿ˜ฐ": 424,
427
+ "๐Ÿ™‚": 425,
428
+ "๐Ÿ™„": 426,
429
+ "๐Ÿ™": 427,
430
+ "๐Ÿšจ": 428,
431
+ "๐Ÿค’": 429,
432
+ "๐Ÿคฆ": 430,
433
+ "๐Ÿคฎ": 431,
434
+ "๐Ÿคท": 432,
435
+ "๐Ÿฅฐ": 433,
436
+ "๐Ÿฅบ": 434,
437
+ "๐Ÿฆฐ": 435,
438
+ "๐Ÿง ": 436
439
  }