Hugging Face's logo

Snowad
/
French-Tortoise

Text-to-Speech
French
TTS
Model card Files
xet
Community
6
Snowad commited on
Commit
ff4966f
·
1 Parent(s): bdecc0a

Upload french_tokenizer.json

Browse files
Files changed (1) hide show
  1. french_tokenizer.json +466 -0
french_tokenizer.json ADDED
@@ -0,0 +1,466 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[STOP]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[SPACE]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": null,
35
+ "pre_tokenizer": {
36
+ "type": "Whitespace"
37
+ },
38
+ "post_processor": null,
39
+ "decoder": null,
40
+ "model": {
41
+ "type": "BPE",
42
+ "dropout": null,
43
+ "unk_token": "[UNK]",
44
+ "continuing_subword_prefix": null,
45
+ "end_of_word_suffix": null,
46
+ "fuse_unk": false,
47
+ "vocab": {
48
+ "[STOP]": 0,
49
+ "[UNK]": 1,
50
+ "[SPACE]": 2,
51
+ "!": 3,
52
+ "(": 4,
53
+ ")": 5,
54
+ ",": 6,
55
+ "-": 7,
56
+ ".": 8,
57
+ "/": 9,
58
+ "0": 10,
59
+ "1": 11,
60
+ "2": 12,
61
+ "3": 13,
62
+ "4": 14,
63
+ "5": 15,
64
+ "6": 16,
65
+ "7": 17,
66
+ "8": 18,
67
+ "9": 19,
68
+ ":": 20,
69
+ ";": 21,
70
+ "?": 22,
71
+ "A": 23,
72
+ "B": 24,
73
+ "C": 25,
74
+ "D": 26,
75
+ "E": 27,
76
+ "F": 28,
77
+ "G": 29,
78
+ "H": 30,
79
+ "I": 31,
80
+ "J": 32,
81
+ "K": 33,
82
+ "L": 34,
83
+ "M": 35,
84
+ "N": 36,
85
+ "O": 37,
86
+ "P": 38,
87
+ "Q": 39,
88
+ "R": 40,
89
+ "S": 41,
90
+ "T": 42,
91
+ "U": 43,
92
+ "V": 44,
93
+ "W": 45,
94
+ "X": 46,
95
+ "Y": 47,
96
+ "Z": 48,
97
+ "a": 49,
98
+ "b": 50,
99
+ "c": 51,
100
+ "d": 52,
101
+ "e": 53,
102
+ "f": 54,
103
+ "g": 55,
104
+ "h": 56,
105
+ "i": 57,
106
+ "j": 58,
107
+ "k": 59,
108
+ "l": 60,
109
+ "m": 61,
110
+ "n": 62,
111
+ "o": 63,
112
+ "p": 64,
113
+ "q": 65,
114
+ "r": 66,
115
+ "s": 67,
116
+ "t": 68,
117
+ "u": 69,
118
+ "v": 70,
119
+ "w": 71,
120
+ "x": 72,
121
+ "y": 73,
122
+ "z": 74,
123
+ "«": 75,
124
+ "»": 76,
125
+ "À": 77,
126
+ "Ç": 78,
127
+ "É": 79,
128
+ "Ô": 80,
129
+ "à": 81,
130
+ "â": 82,
131
+ "ç": 83,
132
+ "è": 84,
133
+ "é": 85,
134
+ "ê": 86,
135
+ "ë": 87,
136
+ "î": 88,
137
+ "ï": 89,
138
+ "ô": 90,
139
+ "ù": 91,
140
+ "û": 92,
141
+ "œ": 93,
142
+ "–": 94,
143
+ "’": 95,
144
+ "le": 96,
145
+ "en": 97,
146
+ "ai": 98,
147
+ "es": 99,
148
+ "ou": 100,
149
+ "on": 101,
150
+ "de": 102,
151
+ "re": 103,
152
+ "an": 104,
153
+ "qu": 105,
154
+ "et": 106,
155
+ "er": 107,
156
+ "ent": 108,
157
+ "il": 109,
158
+ "la": 110,
159
+ "ait": 111,
160
+ "ne": 112,
161
+ "it": 113,
162
+ "ar": 114,
163
+ "au": 115,
164
+ "ch": 116,
165
+ "is": 117,
166
+ "ur": 118,
167
+ "se": 119,
168
+ "el": 120,
169
+ "te": 121,
170
+ "in": 122,
171
+ "les": 123,
172
+ "our": 124,
173
+ "av": 125,
174
+ "or": 126,
175
+ "eu": 127,
176
+ "ant": 128,
177
+ "ais": 129,
178
+ "lu": 130,
179
+ "me": 131,
180
+ "que": 132,
181
+ "pr": 133,
182
+ "as": 134,
183
+ "om": 135,
184
+ "ce": 136,
185
+ "oi": 137,
186
+ "elle": 138,
187
+ "un": 139,
188
+ "ét": 140,
189
+ "des": 141,
190
+ "ous": 142,
191
+ "ans": 143,
192
+ "tr": 144,
193
+ "par": 145,
194
+ "si": 146,
195
+ "al": 147,
196
+ "une": 148,
197
+ "du": 149,
198
+ "ri": 150,
199
+ "est": 151,
200
+ "qui": 152,
201
+ "son": 153,
202
+ "aient": 154,
203
+ "pas": 155,
204
+ "tre": 156,
205
+ "che": 157,
206
+ "dans": 158,
207
+ "pour": 159,
208
+ "sa": 160,
209
+ "vi": 161,
210
+ "ment": 162,
211
+ "ti": 163,
212
+ "leur": 164,
213
+ "ré": 165,
214
+ "con": 166,
215
+ "out": 167,
216
+ "ère": 168,
217
+ "com": 169,
218
+ "dit": 170,
219
+ "ois": 171,
220
+ "ouv": 172,
221
+ "ge": 173,
222
+ "avait": 174,
223
+ "lui": 175,
224
+ "était": 176,
225
+ "plu": 177,
226
+ "ra": 178,
227
+ "mais": 179,
228
+ "ain": 180,
229
+ "eux": 181,
230
+ "bi": 182,
231
+ "je": 183,
232
+ "plus": 184,
233
+ "ses": 185,
234
+ "ir": 186,
235
+ "Il": 187,
236
+ "dé": 188,
237
+ "ma": 189,
238
+ "end": 190,
239
+ "mon": 191,
240
+ "ils": 192,
241
+ "ée": 193,
242
+ "and": 194,
243
+ "sur": 195,
244
+ "li": 196,
245
+ "ci": 197,
246
+ "ille": 198,
247
+ "vous": 199,
248
+ "vo": 200,
249
+ "bien": 201,
250
+ "mp": 202,
251
+ "ap": 203,
252
+ "ave": 204,
253
+ "ser": 205,
254
+ "oir": 206,
255
+ "tout": 207,
256
+ "mi": 208,
257
+ "su": 209,
258
+ "don": 210,
259
+ "rent": 211,
260
+ "tu": 212,
261
+ "gr": 213,
262
+ "ces": 214,
263
+ "etit": 215,
264
+ "ier": 216,
265
+ "ter": 217,
266
+ "co": 218,
267
+ "petit": 219,
268
+ "ab": 220,
269
+ "ons": 221,
270
+ "jour": 222,
271
+ "comme": 223,
272
+ "ro": 224,
273
+ "res": 225,
274
+ "avec": 226,
275
+ "eau": 227,
276
+ "és": 228,
277
+ "ort": 229,
278
+ "éc": 230,
279
+ "uis": 231,
280
+ "Le": 232,
281
+ "ut": 233,
282
+ "èrent": 234,
283
+ "ff": 235,
284
+ "lle": 236,
285
+ "oin": 237,
286
+ "gar": 238,
287
+ "gn": 239,
288
+ "enf": 240,
289
+ "us": 241,
290
+ "ors": 242,
291
+ "br": 243,
292
+ "ès": 244,
293
+ "ta": 245,
294
+ "quel": 246,
295
+ "ette": 247,
296
+ "cou": 248,
297
+ "mes": 249,
298
+ "vie": 250,
299
+ "di": 251,
300
+ "gu": 252,
301
+ "aire": 253,
302
+ "per": 254
303
+ },
304
+ "merges": [
305
+ "l e",
306
+ "e n",
307
+ "a i",
308
+ "e s",
309
+ "o u",
310
+ "o n",
311
+ "d e",
312
+ "r e",
313
+ "a n",
314
+ "q u",
315
+ "e t",
316
+ "e r",
317
+ "en t",
318
+ "i l",
319
+ "l a",
320
+ "ai t",
321
+ "n e",
322
+ "i t",
323
+ "a r",
324
+ "a u",
325
+ "c h",
326
+ "i s",
327
+ "u r",
328
+ "s e",
329
+ "e l",
330
+ "t e",
331
+ "i n",
332
+ "le s",
333
+ "ou r",
334
+ "a v",
335
+ "o r",
336
+ "e u",
337
+ "an t",
338
+ "ai s",
339
+ "l u",
340
+ "m e",
341
+ "qu e",
342
+ "p r",
343
+ "a s",
344
+ "o m",
345
+ "c e",
346
+ "o i",
347
+ "el le",
348
+ "u n",
349
+ "é t",
350
+ "d es",
351
+ "ou s",
352
+ "an s",
353
+ "t r",
354
+ "p ar",
355
+ "s i",
356
+ "a l",
357
+ "u ne",
358
+ "d u",
359
+ "r i",
360
+ "es t",
361
+ "qu i",
362
+ "s on",
363
+ "ai ent",
364
+ "p as",
365
+ "t re",
366
+ "ch e",
367
+ "d ans",
368
+ "p our",
369
+ "s a",
370
+ "v i",
371
+ "m ent",
372
+ "t i",
373
+ "le ur",
374
+ "r é",
375
+ "c on",
376
+ "ou t",
377
+ "è re",
378
+ "c om",
379
+ "d it",
380
+ "o is",
381
+ "ou v",
382
+ "g e",
383
+ "av ait",
384
+ "lu i",
385
+ "ét ait",
386
+ "p lu",
387
+ "r a",
388
+ "m ais",
389
+ "ai n",
390
+ "eu x",
391
+ "b i",
392
+ "j e",
393
+ "plu s",
394
+ "s es",
395
+ "i r",
396
+ "I l",
397
+ "d é",
398
+ "m a",
399
+ "en d",
400
+ "m on",
401
+ "il s",
402
+ "é e",
403
+ "an d",
404
+ "s ur",
405
+ "l i",
406
+ "c i",
407
+ "il le",
408
+ "v ous",
409
+ "v o",
410
+ "bi en",
411
+ "m p",
412
+ "a p",
413
+ "av e",
414
+ "s er",
415
+ "oi r",
416
+ "t out",
417
+ "m i",
418
+ "s u",
419
+ "d on",
420
+ "r ent",
421
+ "t u",
422
+ "g r",
423
+ "c es",
424
+ "et it",
425
+ "i er",
426
+ "t er",
427
+ "c o",
428
+ "p etit",
429
+ "a b",
430
+ "on s",
431
+ "j our",
432
+ "com me",
433
+ "r o",
434
+ "r es",
435
+ "ave c",
436
+ "e au",
437
+ "é s",
438
+ "or t",
439
+ "é c",
440
+ "u is",
441
+ "L e",
442
+ "u t",
443
+ "è rent",
444
+ "f f",
445
+ "l le",
446
+ "o in",
447
+ "g ar",
448
+ "g n",
449
+ "en f",
450
+ "u s",
451
+ "or s",
452
+ "b r",
453
+ "è s",
454
+ "t a",
455
+ "qu el",
456
+ "et te",
457
+ "c ou",
458
+ "m es",
459
+ "vi e",
460
+ "d i",
461
+ "g u",
462
+ "ai re",
463
+ "p er"
464
+ ]
465
+ }
466
+ }