grosenthal commited on
Commit
78fbada
1 Parent(s): ffabf5b

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +352 -0
  2. source.spm +0 -0
  3. special_tokens_map.json +5 -0
  4. target.spm +0 -0
  5. tokenizer_config.json +12 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,352 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Adjective_Ablative_Singular_Feminine_Positive": 65223,
3
+ "Adjective_Ablative_Singular_Feminine_Superlative": 65179,
4
+ "Adjective_Ablative_Singular_Masculine_Positive": 65217,
5
+ "Adjective_Ablative_Singular_Masculine_Superlative": 65176,
6
+ "Adjective_Ablative_Singular_Neuter_Positive": 65244,
7
+ "Adjective_Ablative_Singular_Unknown_Comparative": 65198,
8
+ "Adjective_Ablative_Singular_Unknown_Positive": 65237,
9
+ "Adjective_Accusative_Plural_Common_Comparative": 65208,
10
+ "Adjective_Accusative_Plural_Common_Positive": 65212,
11
+ "Adjective_Accusative_Plural_Feminine_Positive": 65219,
12
+ "Adjective_Accusative_Plural_Feminine_Superlative": 65187,
13
+ "Adjective_Accusative_Plural_Masculine_Positive": 65224,
14
+ "Adjective_Accusative_Plural_Masculine_Superlative": 65183,
15
+ "Adjective_Accusative_Plural_Neuter_Comparative": 65209,
16
+ "Adjective_Accusative_Plural_Neuter_Positive": 65243,
17
+ "Adjective_Accusative_Singular_Common_Comparative": 65195,
18
+ "Adjective_Accusative_Singular_Common_Positive": 65231,
19
+ "Adjective_Accusative_Singular_Feminine_Positive": 65233,
20
+ "Adjective_Accusative_Singular_Feminine_Superlative": 65175,
21
+ "Adjective_Accusative_Singular_Masculine_Positive": 65226,
22
+ "Adjective_Accusative_Singular_Masculine_Superlative": 65180,
23
+ "Adjective_Accusative_Singular_Neuter_Comparative": 65201,
24
+ "Adjective_Accusative_Singular_Neuter_Positive": 65239,
25
+ "Adjective_Dative_Plural_Unknown_Comparative": 65206,
26
+ "Adjective_Dative_Plural_Unknown_Positive": 65220,
27
+ "Adjective_Dative_Plural_Unknown_Superlative": 65181,
28
+ "Adjective_Dative_Singular_Common_Positive": 65230,
29
+ "Adjective_Dative_Singular_Masculine_Positive": 65235,
30
+ "Adjective_Dative_Singular_Masculine_Superlative": 65178,
31
+ "Adjective_Dative_Singular_Unknown_Comparative": 65202,
32
+ "Adjective_Dative_Singular_Unknown_Positive": 65236,
33
+ "Adjective_Genitive_Plural_Feminine_Positive": 65216,
34
+ "Adjective_Genitive_Plural_Feminine_Superlative": 65190,
35
+ "Adjective_Genitive_Plural_Masculine_Positive": 65242,
36
+ "Adjective_Genitive_Plural_Masculine_Superlative": 65188,
37
+ "Adjective_Genitive_Plural_Unknown_Comparative": 65204,
38
+ "Adjective_Genitive_Plural_Unknown_Positive": 65240,
39
+ "Adjective_Genitive_Singular_Common_Positive": 65234,
40
+ "Adjective_Genitive_Singular_Feminine_Positive": 65228,
41
+ "Adjective_Genitive_Singular_Feminine_Superlative": 65186,
42
+ "Adjective_Genitive_Singular_Masculine_Positive": 65238,
43
+ "Adjective_Genitive_Singular_Masculine_Superlative": 65189,
44
+ "Adjective_Genitive_Singular_Neuter_Comparative": 65197,
45
+ "Adjective_Genitive_Singular_Unknown_Positive": 65227,
46
+ "Adjective_Nominative_Plural_Common_Comparative": 65205,
47
+ "Adjective_Nominative_Plural_Common_Positive": 65218,
48
+ "Adjective_Nominative_Plural_Feminine_Positive": 65211,
49
+ "Adjective_Nominative_Plural_Feminine_Superlative": 65192,
50
+ "Adjective_Nominative_Plural_Masculine_Positive": 65247,
51
+ "Adjective_Nominative_Plural_Masculine_Superlative": 65177,
52
+ "Adjective_Nominative_Plural_Neuter_Comparative": 65210,
53
+ "Adjective_Nominative_Plural_Neuter_Positive": 65214,
54
+ "Adjective_Nominative_Singular_Common_Comparative": 65199,
55
+ "Adjective_Nominative_Singular_Common_Positive": 65232,
56
+ "Adjective_Nominative_Singular_Feminine_Positive": 65215,
57
+ "Adjective_Nominative_Singular_Feminine_Superlative": 65185,
58
+ "Adjective_Nominative_Singular_Masculine_Positive": 65213,
59
+ "Adjective_Nominative_Singular_Masculine_Superlative": 65184,
60
+ "Adjective_Nominative_Singular_Neuter_Comparative": 65207,
61
+ "Adjective_Nominative_Singular_Neuter_Positive": 65222,
62
+ "Adjective_Nominative_Singular_Neuter_Superlative": 65182,
63
+ "Adjective_Nominative_Singular_Unknown_Positive": 65229,
64
+ "Adjective_Undeclined_Infinitive_Unknown_Positive": 65281,
65
+ "Adjective_Vocative_Plural_Masculine_Positive": 65241,
66
+ "Adjective_Vocative_Singular_Common_Positive": 65246,
67
+ "Adjective_Vocative_Singular_Masculine_Positive": 65245,
68
+ "Adjective_Vocative_Singular_Masculine_Superlative": 65191,
69
+ "Adjective_Vocative_Singular_Unknown_Positive": 65248,
70
+ "Adverb_Comparative": 65340,
71
+ "Adverb_Positive": 65342,
72
+ "Adverb_Superlative": 65338,
73
+ "Conjunction": 65350,
74
+ "Enclitic": 65346,
75
+ "Interjection": 65343,
76
+ "Noun_Ablative_Plural_Common": 65317,
77
+ "Noun_Ablative_Plural_Feminine": 65305,
78
+ "Noun_Ablative_Plural_Masculine": 65303,
79
+ "Noun_Ablative_Plural_Neuter": 65322,
80
+ "Noun_Ablative_Singular_Common": 65312,
81
+ "Noun_Ablative_Singular_Feminine": 65320,
82
+ "Noun_Ablative_Singular_Masculine": 65329,
83
+ "Noun_Ablative_Singular_Neuter": 65304,
84
+ "Noun_Accusative_Plural_Common": 65291,
85
+ "Noun_Accusative_Plural_Feminine": 65318,
86
+ "Noun_Accusative_Plural_Masculine": 65325,
87
+ "Noun_Accusative_Plural_Neuter": 65330,
88
+ "Noun_Accusative_Singular_Common": 65286,
89
+ "Noun_Accusative_Singular_Feminine": 65302,
90
+ "Noun_Accusative_Singular_Masculine": 65288,
91
+ "Noun_Accusative_Singular_Neuter": 65321,
92
+ "Noun_Accusative_Singular_Unknown": 65315,
93
+ "Noun_Dative_Plural_Common": 65333,
94
+ "Noun_Dative_Plural_Feminine": 65299,
95
+ "Noun_Dative_Plural_Masculine": 65319,
96
+ "Noun_Dative_Plural_Neuter": 65335,
97
+ "Noun_Dative_Singular_Common": 65326,
98
+ "Noun_Dative_Singular_Feminine": 65331,
99
+ "Noun_Dative_Singular_Masculine": 65289,
100
+ "Noun_Dative_Singular_Neuter": 65297,
101
+ "Noun_Genitive_Plural_Common": 65308,
102
+ "Noun_Genitive_Plural_Feminine": 65306,
103
+ "Noun_Genitive_Plural_Masculine": 65283,
104
+ "Noun_Genitive_Plural_Neuter": 65290,
105
+ "Noun_Genitive_Plural_Unknown": 65336,
106
+ "Noun_Genitive_Singular_Common": 65284,
107
+ "Noun_Genitive_Singular_Feminine": 65287,
108
+ "Noun_Genitive_Singular_Masculine": 65293,
109
+ "Noun_Genitive_Singular_Neuter": 65313,
110
+ "Noun_Locative_Plural_Common": 65323,
111
+ "Noun_Locative_Plural_Feminine": 65314,
112
+ "Noun_Locative_Plural_Masculine": 65300,
113
+ "Noun_Locative_Plural_Neuter": 65295,
114
+ "Noun_Locative_Singular_Common": 65332,
115
+ "Noun_Locative_Singular_Feminine": 65324,
116
+ "Noun_Locative_Singular_Masculine": 65316,
117
+ "Noun_Locative_Singular_Neuter": 65311,
118
+ "Noun_Nominative_Plural_Common": 65327,
119
+ "Noun_Nominative_Plural_Feminine": 65310,
120
+ "Noun_Nominative_Plural_Masculine": 65296,
121
+ "Noun_Nominative_Plural_Neuter": 65309,
122
+ "Noun_Nominative_Singular_Common": 65328,
123
+ "Noun_Nominative_Singular_Feminine": 65292,
124
+ "Noun_Nominative_Singular_Masculine": 65298,
125
+ "Noun_Nominative_Singular_Neuter": 65294,
126
+ "Noun_Nominative_Singular_Unknown": 65334,
127
+ "Noun_PROBLEM_Infinitive_Unknown": 65203,
128
+ "Noun_PROBLEM_PROBLEM_Common": 65194,
129
+ "Noun_PROBLEM_PROBLEM_Masculine": 65193,
130
+ "Noun_PROBLEM_PROBLEM_Neuter": 65196,
131
+ "Noun_PROBLEM_PROBLEM_PROBLEM": 65200,
132
+ "Noun_Undeclined_Infinitive_Common": 65347,
133
+ "Noun_Undeclined_Infinitive_Feminine": 65344,
134
+ "Noun_Undeclined_Infinitive_Masculine": 65348,
135
+ "Noun_Undeclined_Infinitive_Neuter": 65345,
136
+ "Noun_Vocative_Singular_Common": 65307,
137
+ "Noun_Vocative_Singular_Feminine": 65301,
138
+ "Noun_Vocative_Singular_Masculine": 65285,
139
+ "Noun_Vocative_Singular_Neuter": 65337,
140
+ "OTHER": 65349,
141
+ "Participle_Ablative_Singular_Feminine_FutureActive": 65058,
142
+ "Participle_Ablative_Singular_Feminine_FuturePassive": 65046,
143
+ "Participle_Ablative_Singular_Feminine_PerfectActive": 65154,
144
+ "Participle_Ablative_Singular_Feminine_PerfectPassive": 65016,
145
+ "Participle_Ablative_Singular_Masculine_FutureActive": 65173,
146
+ "Participle_Ablative_Singular_Masculine_FuturePassive": 65039,
147
+ "Participle_Ablative_Singular_Masculine_PerfectActive": 65132,
148
+ "Participle_Ablative_Singular_Masculine_PerfectPassive": 65019,
149
+ "Participle_Ablative_Singular_Unknown_Present Active": 65028,
150
+ "Participle_Accusative_Plural_Common_Present Active": 65029,
151
+ "Participle_Accusative_Plural_Feminine_FutureActive": 65054,
152
+ "Participle_Accusative_Plural_Feminine_FuturePassive": 65044,
153
+ "Participle_Accusative_Plural_Feminine_PerfectActive": 65120,
154
+ "Participle_Accusative_Plural_Feminine_PerfectPassive": 65008,
155
+ "Participle_Accusative_Plural_Masculine_FutureActive": 65066,
156
+ "Participle_Accusative_Plural_Masculine_FuturePassive": 65036,
157
+ "Participle_Accusative_Plural_Masculine_PerfectActive": 65104,
158
+ "Participle_Accusative_Plural_Masculine_PerfectPassive": 65007,
159
+ "Participle_Accusative_Plural_Neuter_Present Active": 65050,
160
+ "Participle_Accusative_Singular_Common_Present Active": 65021,
161
+ "Participle_Accusative_Singular_Feminine_FutureActive": 65051,
162
+ "Participle_Accusative_Singular_Feminine_FuturePassive": 65034,
163
+ "Participle_Accusative_Singular_Feminine_PerfectActive": 65147,
164
+ "Participle_Accusative_Singular_Feminine_PerfectPassive": 65011,
165
+ "Participle_Accusative_Singular_Masculine_FutureActive": 65062,
166
+ "Participle_Accusative_Singular_Masculine_FuturePassive": 65032,
167
+ "Participle_Accusative_Singular_Masculine_PerfectActive": 65156,
168
+ "Participle_Accusative_Singular_Masculine_PerfectPassive": 65006,
169
+ "Participle_Accusative_Singular_Neuter_Present Active": 65026,
170
+ "Participle_Dative_Plural_Unknown_FutureActive": 65057,
171
+ "Participle_Dative_Plural_Unknown_FuturePassive": 65020,
172
+ "Participle_Dative_Plural_Unknown_PerfectActive": 65109,
173
+ "Participle_Dative_Plural_Unknown_PerfectPassive": 65017,
174
+ "Participle_Dative_Plural_Unknown_Present Active": 65031,
175
+ "Participle_Dative_Singular_Masculine_FutureActive": 65053,
176
+ "Participle_Dative_Singular_Masculine_FuturePassive": 65037,
177
+ "Participle_Dative_Singular_Masculine_PerfectActive": 65153,
178
+ "Participle_Dative_Singular_Masculine_PerfectPassive": 65002,
179
+ "Participle_Dative_Singular_Unknown_Present Active": 65023,
180
+ "Participle_Genitive_Plural_Feminine_FutureActive": 65067,
181
+ "Participle_Genitive_Plural_Feminine_FuturePassive": 65048,
182
+ "Participle_Genitive_Plural_Feminine_PerfectActive": 65141,
183
+ "Participle_Genitive_Plural_Feminine_PerfectPassive": 65005,
184
+ "Participle_Genitive_Plural_Masculine_FutureActive": 65065,
185
+ "Participle_Genitive_Plural_Masculine_FuturePassive": 65049,
186
+ "Participle_Genitive_Plural_Masculine_PerfectActive": 65121,
187
+ "Participle_Genitive_Plural_Masculine_PerfectPassive": 65004,
188
+ "Participle_Genitive_Plural_Unknown_Present Active": 65027,
189
+ "Participle_Genitive_Singular_Feminine_FutureActive": 65068,
190
+ "Participle_Genitive_Singular_Feminine_FuturePassive": 65033,
191
+ "Participle_Genitive_Singular_Feminine_PerfectActive": 65152,
192
+ "Participle_Genitive_Singular_Feminine_PerfectPassive": 65010,
193
+ "Participle_Genitive_Singular_Masculine_FutureActive": 65061,
194
+ "Participle_Genitive_Singular_Masculine_FuturePassive": 65022,
195
+ "Participle_Genitive_Singular_Masculine_PerfectActive": 65162,
196
+ "Participle_Genitive_Singular_Masculine_PerfectPassive": 65012,
197
+ "Participle_Genitive_Singular_Unknown_Present Active": 65024,
198
+ "Participle_Nominative_Plural_Common_Present Active": 65030,
199
+ "Participle_Nominative_Plural_Feminine_FutureActive": 65060,
200
+ "Participle_Nominative_Plural_Feminine_FuturePassive": 65045,
201
+ "Participle_Nominative_Plural_Feminine_PerfectActive": 65131,
202
+ "Participle_Nominative_Plural_Feminine_PerfectPassive": 65018,
203
+ "Participle_Nominative_Plural_Masculine_FutureActive": 65063,
204
+ "Participle_Nominative_Plural_Masculine_FuturePassive": 65042,
205
+ "Participle_Nominative_Plural_Masculine_PerfectActive": 65143,
206
+ "Participle_Nominative_Plural_Masculine_PerfectPassive": 65001,
207
+ "Participle_Nominative_Plural_Neuter_FutureActive": 65064,
208
+ "Participle_Nominative_Plural_Neuter_FuturePassive": 65040,
209
+ "Participle_Nominative_Plural_Neuter_PerfectActive": 65158,
210
+ "Participle_Nominative_Plural_Neuter_PerfectPassive": 65003,
211
+ "Participle_Nominative_Plural_Neuter_Present Active": 65025,
212
+ "Participle_Nominative_Singular_Feminine_FutureActive": 65056,
213
+ "Participle_Nominative_Singular_Feminine_FuturePassive": 65035,
214
+ "Participle_Nominative_Singular_Feminine_PerfectActive": 65099,
215
+ "Participle_Nominative_Singular_Feminine_PerfectPassive": 65014,
216
+ "Participle_Nominative_Singular_Masculine_FutureActive": 65052,
217
+ "Participle_Nominative_Singular_Masculine_FuturePassive": 65038,
218
+ "Participle_Nominative_Singular_Masculine_PerfectActive": 65155,
219
+ "Participle_Nominative_Singular_Masculine_PerfectPassive": 65015,
220
+ "Participle_Nominative_Singular_Neuter_FutureActive": 65059,
221
+ "Participle_Nominative_Singular_Neuter_FuturePassive": 65047,
222
+ "Participle_Nominative_Singular_Neuter_PerfectActive": 65157,
223
+ "Participle_Nominative_Singular_Neuter_PerfectPassive": 65013,
224
+ "Participle_Nominative_Singular_Unknown_Present Active": 65041,
225
+ "Participle_Vocative_Singular_Masculine_FutureActive": 65055,
226
+ "Participle_Vocative_Singular_Masculine_FuturePassive": 65043,
227
+ "Participle_Vocative_Singular_Masculine_PerfectActive": 65161,
228
+ "Participle_Vocative_Singular_Masculine_PerfectPassive": 65009,
229
+ "Preposition_Ablative": 65339,
230
+ "Preposition_Accusative": 65341,
231
+ "Pronoun_Ablative_Infinitive_Common": 65280,
232
+ "Pronoun_Ablative_Plural_Feminine": 65253,
233
+ "Pronoun_Ablative_Singular_Common": 65262,
234
+ "Pronoun_Ablative_Singular_Feminine": 65274,
235
+ "Pronoun_Ablative_Singular_Masculine": 65278,
236
+ "Pronoun_Ablative_Singular_Neuter": 65277,
237
+ "Pronoun_Ablative_Singular_Unknown": 65267,
238
+ "Pronoun_Accusative_Plural_Common": 65279,
239
+ "Pronoun_Accusative_Plural_Feminine": 65252,
240
+ "Pronoun_Accusative_Plural_Masculine": 65256,
241
+ "Pronoun_Accusative_Plural_Neuter": 65251,
242
+ "Pronoun_Accusative_Singular_Feminine": 65254,
243
+ "Pronoun_Accusative_Singular_Masculine": 65263,
244
+ "Pronoun_Accusative_Singular_Neuter": 65264,
245
+ "Pronoun_Dative_Infinitive_Common": 65268,
246
+ "Pronoun_Dative_Plural_Common": 65272,
247
+ "Pronoun_Dative_Plural_Unknown": 65270,
248
+ "Pronoun_Dative_Singular_Common": 65273,
249
+ "Pronoun_Dative_Singular_Unknown": 65271,
250
+ "Pronoun_Genitive_Infinitive_Common": 65275,
251
+ "Pronoun_Genitive_Plural_Common": 65258,
252
+ "Pronoun_Genitive_Plural_Feminine": 65269,
253
+ "Pronoun_Genitive_Plural_Masculine": 65266,
254
+ "Pronoun_Genitive_Singular_Common": 65276,
255
+ "Pronoun_Genitive_Singular_Unknown": 65249,
256
+ "Pronoun_Nominative_Plural_Common": 65282,
257
+ "Pronoun_Nominative_Plural_Feminine": 65259,
258
+ "Pronoun_Nominative_Plural_Masculine": 65260,
259
+ "Pronoun_Nominative_Plural_Neuter": 65257,
260
+ "Pronoun_Nominative_Singular_Common": 65261,
261
+ "Pronoun_Nominative_Singular_Feminine": 65265,
262
+ "Pronoun_Nominative_Singular_Masculine": 65255,
263
+ "Pronoun_Nominative_Singular_Neuter": 65250,
264
+ "Supine_Ablative_Singular_Neuter": 65221,
265
+ "Supine_Accusative_Singular_Neuter": 65225,
266
+ "Verb_FuturePerfect_Active_Indicative_First_Singular": 65138,
267
+ "Verb_Future_Active_Imperative_Second_Plural": 65169,
268
+ "Verb_Future_Active_Imperative_Second_Singular": 65171,
269
+ "Verb_Future_Active_Imperative_Third_Plural": 65172,
270
+ "Verb_Future_Active_Indicative_First_Plural": 65170,
271
+ "Verb_Future_Active_Indicative_First_Singular": 65166,
272
+ "Verb_Future_Active_Indicative_Second_Plural": 65168,
273
+ "Verb_Future_Active_Indicative_Second_Singular": 65167,
274
+ "Verb_Future_Active_Indicative_Third_Plural": 65164,
275
+ "Verb_Future_Active_Indicative_Third_Singular": 65165,
276
+ "Verb_Future_Active_Infinitive_Undeclined_Infinitive": 65174,
277
+ "Verb_Future_Passive_Imperative_Second_Singular": 65148,
278
+ "Verb_Future_Passive_Indicative_First_Plural": 65160,
279
+ "Verb_Future_Passive_Indicative_First_Singular": 65108,
280
+ "Verb_Future_Passive_Indicative_Second_Plural": 65144,
281
+ "Verb_Future_Passive_Indicative_Second_Singular": 65125,
282
+ "Verb_Future_Passive_Indicative_Third_Plural": 65111,
283
+ "Verb_Future_Passive_Indicative_Third_Singular": 65128,
284
+ "Verb_Future_Passive_Infinitive_Undeclined_Infinitive": 65163,
285
+ "Verb_Imperfect_Active_Indicative_First_Plural": 65126,
286
+ "Verb_Imperfect_Active_Indicative_First_Singular": 65124,
287
+ "Verb_Imperfect_Active_Indicative_Second_Plural": 65133,
288
+ "Verb_Imperfect_Active_Indicative_Second_Singular": 65145,
289
+ "Verb_Imperfect_Active_Indicative_Third_Plural": 65130,
290
+ "Verb_Imperfect_Active_Indicative_Third_Singular": 65134,
291
+ "Verb_Imperfect_Active_Subjunctive_First_Plural": 65119,
292
+ "Verb_Imperfect_Active_Subjunctive_First_Singular": 65112,
293
+ "Verb_Imperfect_Active_Subjunctive_Second_Plural": 65106,
294
+ "Verb_Imperfect_Active_Subjunctive_Second_Singular": 65149,
295
+ "Verb_Imperfect_Active_Subjunctive_Third_Plural": 65118,
296
+ "Verb_Imperfect_Active_Subjunctive_Third_Singular": 65150,
297
+ "Verb_Imperfect_Passive_Indicative_First_Plural": 65074,
298
+ "Verb_Imperfect_Passive_Indicative_First_Singular": 65091,
299
+ "Verb_Imperfect_Passive_Indicative_Second_Plural": 65081,
300
+ "Verb_Imperfect_Passive_Indicative_Second_Singular": 65070,
301
+ "Verb_Imperfect_Passive_Indicative_Third_Plural": 65085,
302
+ "Verb_Imperfect_Passive_Indicative_Third_Singular": 65069,
303
+ "Verb_Imperfect_Passive_Subjunctive_First_Plural": 65071,
304
+ "Verb_Imperfect_Passive_Subjunctive_First_Singular": 65090,
305
+ "Verb_Imperfect_Passive_Subjunctive_Second_Plural": 65079,
306
+ "Verb_Imperfect_Passive_Subjunctive_Second_Singular": 65089,
307
+ "Verb_Imperfect_Passive_Subjunctive_Third_Plural": 65080,
308
+ "Verb_Imperfect_Passive_Subjunctive_Third_Singular": 65075,
309
+ "Verb_Pluperfect_Active_Indicative_First_Plural": 65129,
310
+ "Verb_Pluperfect_Active_Indicative_First_Singular": 65102,
311
+ "Verb_Pluperfect_Active_Indicative_Second_Plural": 65107,
312
+ "Verb_Pluperfect_Active_Indicative_Second_Singular": 65151,
313
+ "Verb_Pluperfect_Active_Indicative_Third_Plural": 65100,
314
+ "Verb_Pluperfect_Active_Indicative_Third_Singular": 65122,
315
+ "Verb_Pluperfect_Active_Infinitive_Undeclined_Infinitive": 65123,
316
+ "Verb_Pluperfect_Active_Subjunctive_First_Plural": 65101,
317
+ "Verb_Pluperfect_Active_Subjunctive_First_Singular": 65113,
318
+ "Verb_Pluperfect_Active_Subjunctive_Second_Plural": 65105,
319
+ "Verb_Pluperfect_Active_Subjunctive_Second_Singular": 65142,
320
+ "Verb_Pluperfect_Active_Subjunctive_Third_Plural": 65127,
321
+ "Verb_Pluperfect_Active_Subjunctive_Third_Singular": 65098,
322
+ "Verb_Pluperfect_Passive_Infinitive_Undeclined_Infinitive": 65095,
323
+ "Verb_Present_Active_Imperative_Second_Plural": 65137,
324
+ "Verb_Present_Active_Imperative_Second_Singular": 65135,
325
+ "Verb_Present_Active_Indicative_First_Plural": 65110,
326
+ "Verb_Present_Active_Indicative_First_Singular": 65097,
327
+ "Verb_Present_Active_Indicative_Second_Plural": 65116,
328
+ "Verb_Present_Active_Indicative_Second_Singular": 65117,
329
+ "Verb_Present_Active_Indicative_Third_Plural": 65140,
330
+ "Verb_Present_Active_Indicative_Third_Singular": 65115,
331
+ "Verb_Present_Active_Infinitive_Undeclined_Infinitive": 65096,
332
+ "Verb_Present_Active_Subjunctive_First_Plural": 65139,
333
+ "Verb_Present_Active_Subjunctive_First_Singular": 65136,
334
+ "Verb_Present_Active_Subjunctive_Second_Plural": 65114,
335
+ "Verb_Present_Active_Subjunctive_Second_Singular": 65159,
336
+ "Verb_Present_Active_Subjunctive_Third_Plural": 65103,
337
+ "Verb_Present_Active_Subjunctive_Third_Singular": 65146,
338
+ "Verb_Present_Passive_Imperative_Second_Singular": 65094,
339
+ "Verb_Present_Passive_Indicative_First_Plural": 65088,
340
+ "Verb_Present_Passive_Indicative_First_Singular": 65084,
341
+ "Verb_Present_Passive_Indicative_Second_Plural": 65087,
342
+ "Verb_Present_Passive_Indicative_Second_Singular": 65083,
343
+ "Verb_Present_Passive_Indicative_Third_Plural": 65072,
344
+ "Verb_Present_Passive_Indicative_Third_Singular": 65077,
345
+ "Verb_Present_Passive_Infinitive_Undeclined_Infinitive": 65082,
346
+ "Verb_Present_Passive_Subjunctive_First_Plural": 65076,
347
+ "Verb_Present_Passive_Subjunctive_First_Singular": 65086,
348
+ "Verb_Present_Passive_Subjunctive_Second_Plural": 65093,
349
+ "Verb_Present_Passive_Subjunctive_Second_Singular": 65073,
350
+ "Verb_Present_Passive_Subjunctive_Third_Plural": 65092,
351
+ "Verb_Present_Passive_Subjunctive_Third_Singular": 65078
352
+ }
source.spm ADDED
Binary file (800 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
Binary file (779 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "model_max_length": 512,
4
+ "pad_token": "<pad>",
5
+ "separate_vocabs": false,
6
+ "source_lang": "fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la",
7
+ "sp_model_kwargs": {},
8
+ "special_tokens_map_file": null,
9
+ "target_lang": "en",
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff