therealvul
commited on
Upload 3 files
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +811 -0
- tokenizer_config.json +52 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,811 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "[UNK]",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "[PAD]",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "[CLS]",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "[SEP]",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "[MASK]",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"normalizer": null,
|
53 |
+
"pre_tokenizer": {
|
54 |
+
"type": "Sequence",
|
55 |
+
"pretokenizers": [
|
56 |
+
{
|
57 |
+
"type": "Whitespace"
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"type": "Punctuation",
|
61 |
+
"behavior": "Isolated"
|
62 |
+
}
|
63 |
+
]
|
64 |
+
},
|
65 |
+
"post_processor": null,
|
66 |
+
"decoder": null,
|
67 |
+
"model": {
|
68 |
+
"type": "BPE",
|
69 |
+
"dropout": null,
|
70 |
+
"unk_token": null,
|
71 |
+
"continuing_subword_prefix": null,
|
72 |
+
"end_of_word_suffix": null,
|
73 |
+
"fuse_unk": false,
|
74 |
+
"byte_fallback": false,
|
75 |
+
"ignore_merges": false,
|
76 |
+
"vocab": {
|
77 |
+
"[UNK]": 0,
|
78 |
+
"[PAD]": 1,
|
79 |
+
"[CLS]": 2,
|
80 |
+
"[SEP]": 3,
|
81 |
+
"[MASK]": 4,
|
82 |
+
"!": 5,
|
83 |
+
"'": 6,
|
84 |
+
",": 7,
|
85 |
+
"-": 8,
|
86 |
+
".": 9,
|
87 |
+
"0": 10,
|
88 |
+
"1": 11,
|
89 |
+
"2": 12,
|
90 |
+
"?": 13,
|
91 |
+
"A": 14,
|
92 |
+
"B": 15,
|
93 |
+
"C": 16,
|
94 |
+
"D": 17,
|
95 |
+
"E": 18,
|
96 |
+
"F": 19,
|
97 |
+
"G": 20,
|
98 |
+
"H": 21,
|
99 |
+
"I": 22,
|
100 |
+
"J": 23,
|
101 |
+
"K": 24,
|
102 |
+
"L": 25,
|
103 |
+
"M": 26,
|
104 |
+
"N": 27,
|
105 |
+
"O": 28,
|
106 |
+
"P": 29,
|
107 |
+
"R": 30,
|
108 |
+
"S": 31,
|
109 |
+
"T": 32,
|
110 |
+
"U": 33,
|
111 |
+
"V": 34,
|
112 |
+
"W": 35,
|
113 |
+
"Y": 36,
|
114 |
+
"Z": 37,
|
115 |
+
"H0": 38,
|
116 |
+
"AH0": 39,
|
117 |
+
"H1": 40,
|
118 |
+
"Y1": 41,
|
119 |
+
"W1": 42,
|
120 |
+
"IH0": 43,
|
121 |
+
"AE": 44,
|
122 |
+
"IH1": 45,
|
123 |
+
"AH0N": 46,
|
124 |
+
"ER": 47,
|
125 |
+
"EH1": 48,
|
126 |
+
"AE1": 49,
|
127 |
+
"AA": 50,
|
128 |
+
"AH1": 51,
|
129 |
+
"AA1": 52,
|
130 |
+
"ER0": 53,
|
131 |
+
"Y0": 54,
|
132 |
+
"IY0": 55,
|
133 |
+
"UW1": 56,
|
134 |
+
"DH": 57,
|
135 |
+
"AO": 58,
|
136 |
+
"AY1": 59,
|
137 |
+
"IY1": 60,
|
138 |
+
"EY1": 61,
|
139 |
+
"AH0L": 62,
|
140 |
+
"AO1": 63,
|
141 |
+
"IH0N": 64,
|
142 |
+
"OW1": 65,
|
143 |
+
"ST": 66,
|
144 |
+
"HH": 67,
|
145 |
+
"SH": 68,
|
146 |
+
"AA1R": 69,
|
147 |
+
"DHAH0": 70,
|
148 |
+
"AO1R": 71,
|
149 |
+
"AE1N": 72,
|
150 |
+
"IH1Z": 73,
|
151 |
+
"JH": 74,
|
152 |
+
"AH1V": 75,
|
153 |
+
"TS": 76,
|
154 |
+
"H2": 77,
|
155 |
+
"Y2": 78,
|
156 |
+
"AH0ND": 79,
|
157 |
+
"TUW1": 80,
|
158 |
+
"IH0NG": 81,
|
159 |
+
"ER1": 82,
|
160 |
+
"EH1N": 83,
|
161 |
+
"SHAH0N": 84,
|
162 |
+
"CH": 85,
|
163 |
+
"AH0T": 86,
|
164 |
+
"PR": 87,
|
165 |
+
"IH0K": 88,
|
166 |
+
"AH0M": 89,
|
167 |
+
"EH1R": 90,
|
168 |
+
"YUW1": 91,
|
169 |
+
"AH1M": 92,
|
170 |
+
"TH": 93,
|
171 |
+
"HHAE1": 94,
|
172 |
+
"AH0S": 95,
|
173 |
+
"AW1": 96,
|
174 |
+
"AH0NT": 97,
|
175 |
+
"W0": 98,
|
176 |
+
"IH1N": 99,
|
177 |
+
"ER0Z": 100,
|
178 |
+
"AH0D": 101,
|
179 |
+
"AH0Z": 102,
|
180 |
+
"HHAE1V": 103,
|
181 |
+
"EH1L": 104,
|
182 |
+
"RIY0": 105,
|
183 |
+
"AE1T": 106,
|
184 |
+
"KT": 107,
|
185 |
+
"EH2": 108,
|
186 |
+
"KS": 109,
|
187 |
+
"AA1N": 110,
|
188 |
+
"FAO1R": 111,
|
189 |
+
"AH1N": 112,
|
190 |
+
"LIY0": 113,
|
191 |
+
"EY1SHAH0N": 114,
|
192 |
+
"MOW1": 115,
|
193 |
+
"UH1": 116,
|
194 |
+
"EY2": 117,
|
195 |
+
"DZ": 118,
|
196 |
+
"AY2": 119,
|
197 |
+
"SAH1M": 120,
|
198 |
+
"IH2": 121,
|
199 |
+
"AO1L": 122,
|
200 |
+
"DIH0": 123,
|
201 |
+
"WIH1": 124,
|
202 |
+
"PL": 125,
|
203 |
+
"AH0K": 126,
|
204 |
+
"W2": 127,
|
205 |
+
"OW0": 128,
|
206 |
+
"TER0": 129,
|
207 |
+
"GR": 130,
|
208 |
+
"LAY1": 131,
|
209 |
+
"TR": 132,
|
210 |
+
"SP": 133,
|
211 |
+
"AH0B": 134,
|
212 |
+
"AH0LZ": 135,
|
213 |
+
"MOW1ST": 136,
|
214 |
+
"EY1N": 137,
|
215 |
+
"KAE1N": 138,
|
216 |
+
"FR": 139,
|
217 |
+
"IY0Z": 140,
|
218 |
+
"MAH0N": 141,
|
219 |
+
"IH1L": 142,
|
220 |
+
"DHAE1T": 143,
|
221 |
+
"AE2": 144,
|
222 |
+
"AH0NS": 145,
|
223 |
+
"ND": 146,
|
224 |
+
"IH1T": 147,
|
225 |
+
"AA1RT": 148,
|
226 |
+
"KAA1": 149,
|
227 |
+
"KR": 150,
|
228 |
+
"OW1N": 151,
|
229 |
+
"AA2": 152,
|
230 |
+
"IH0V": 153,
|
231 |
+
"AH0P": 154,
|
232 |
+
"OW2": 155,
|
233 |
+
"UW0": 156,
|
234 |
+
"AA1L": 157,
|
235 |
+
"AH0TIY0": 158,
|
236 |
+
"IH0Z": 159,
|
237 |
+
"STR": 160,
|
238 |
+
"BIY1": 161,
|
239 |
+
"SK": 162,
|
240 |
+
"IH1NG": 163,
|
241 |
+
"EY2T": 164,
|
242 |
+
"AH0JH": 165,
|
243 |
+
"PAA1RT": 166,
|
244 |
+
"NZ": 167,
|
245 |
+
"EH1K": 168,
|
246 |
+
"DHEH1R": 169,
|
247 |
+
"BR": 170,
|
248 |
+
"IY1Z": 171,
|
249 |
+
"IY1T": 172,
|
250 |
+
"AE1Z": 173,
|
251 |
+
"AH0NZ": 174,
|
252 |
+
"VER0": 175,
|
253 |
+
"WIH1DH": 176,
|
254 |
+
"AH1T": 177,
|
255 |
+
"BAY1": 178,
|
256 |
+
"EH1T": 179,
|
257 |
+
"DR": 180,
|
258 |
+
"PAH0L": 181,
|
259 |
+
"OW1L": 182,
|
260 |
+
"YUW1Z": 183,
|
261 |
+
"WAY1": 184,
|
262 |
+
"AH0F": 185,
|
263 |
+
"IY2": 186,
|
264 |
+
"AE0": 187,
|
265 |
+
"EH1S": 188,
|
266 |
+
"EY1T": 189,
|
267 |
+
"EH0": 190,
|
268 |
+
"EH1M": 191,
|
269 |
+
"AO2": 192,
|
270 |
+
"FL": 193,
|
271 |
+
"MEH1N": 194,
|
272 |
+
"AE1K": 195,
|
273 |
+
"BL": 196,
|
274 |
+
"EH1D": 197,
|
275 |
+
"PER0": 198,
|
276 |
+
"IH1R": 199,
|
277 |
+
"EH1KT": 200,
|
278 |
+
"OY1": 201,
|
279 |
+
"MZ": 202,
|
280 |
+
"IH1F": 203,
|
281 |
+
"EH1ST": 204,
|
282 |
+
"MEY1": 205,
|
283 |
+
"WIY1": 206,
|
284 |
+
"DHER0": 207,
|
285 |
+
"CHER0": 208,
|
286 |
+
"LZ": 209,
|
287 |
+
"AY0": 210,
|
288 |
+
"KL": 211,
|
289 |
+
"DIY0": 212,
|
290 |
+
"GZ": 213,
|
291 |
+
"IH1ST": 214,
|
292 |
+
"VAY1": 215,
|
293 |
+
"EH1RIY0": 216,
|
294 |
+
"UH1R": 217,
|
295 |
+
"DER0": 218,
|
296 |
+
"AE1L": 219,
|
297 |
+
"AW1T": 220,
|
298 |
+
"FRAH1M": 221,
|
299 |
+
"AH1L": 222,
|
300 |
+
"MP": 223,
|
301 |
+
"NOW1": 224,
|
302 |
+
"AH0ST": 225,
|
303 |
+
"TAY1": 226,
|
304 |
+
"PIY1": 227,
|
305 |
+
"AH0LIY0": 228,
|
306 |
+
"AE1S": 229,
|
307 |
+
"WER1": 230,
|
308 |
+
"IH1S": 231,
|
309 |
+
"PS": 232,
|
310 |
+
"IH0T": 233,
|
311 |
+
"IH2N": 234,
|
312 |
+
"PRAA1": 235,
|
313 |
+
"IH0L": 236,
|
314 |
+
"AA1T": 237,
|
315 |
+
"SAY1": 238,
|
316 |
+
"KAH0M": 239,
|
317 |
+
"MIY1": 240,
|
318 |
+
"WAH1N": 241,
|
319 |
+
"WAO1": 242,
|
320 |
+
"AH0NTS": 243,
|
321 |
+
"PLAE1N": 244,
|
322 |
+
"SIY1": 245,
|
323 |
+
"SHAH0NZ": 246,
|
324 |
+
"UH1D": 247,
|
325 |
+
"PIY1PAH0L": 248,
|
326 |
+
"MAY1": 249,
|
327 |
+
"VZ": 250,
|
328 |
+
"MEH1NIY0": 251,
|
329 |
+
"AE1M": 252,
|
330 |
+
"MAH0NT": 253,
|
331 |
+
"UW2": 254,
|
332 |
+
"AH0W": 255,
|
333 |
+
"HHEH1L": 256,
|
334 |
+
"YAH0L": 257,
|
335 |
+
"IH1RIY0": 258,
|
336 |
+
"WAO1TER0": 259,
|
337 |
+
"LOW1": 260,
|
338 |
+
"KAH0NT": 261,
|
339 |
+
"AH1ST": 262,
|
340 |
+
"FIY1": 263,
|
341 |
+
"AH0MZ": 264,
|
342 |
+
"MAO1R": 265,
|
343 |
+
"EY1S": 266,
|
344 |
+
"AE1KT": 267,
|
345 |
+
"AH2": 268,
|
346 |
+
"DUW1": 269,
|
347 |
+
"AH0BAH0L": 270,
|
348 |
+
"KAA1Z": 271,
|
349 |
+
"SEH1L": 272,
|
350 |
+
"AO1RT": 273,
|
351 |
+
"YUW0": 274,
|
352 |
+
"LIY1": 275,
|
353 |
+
"THR": 276,
|
354 |
+
"EH1ND": 277,
|
355 |
+
"UW1D": 278,
|
356 |
+
"BAH1T": 279,
|
357 |
+
"SER1": 280,
|
358 |
+
"NT": 281,
|
359 |
+
"SOW1": 282,
|
360 |
+
"FAY1": 283,
|
361 |
+
"AO1LS": 284,
|
362 |
+
"AH0G": 285,
|
363 |
+
"NG": 286,
|
364 |
+
"DHEY1": 287,
|
365 |
+
"AH1DHER0": 288,
|
366 |
+
"AO1LSOW0": 289,
|
367 |
+
"HHAY1": 290,
|
368 |
+
"LIH1": 291,
|
369 |
+
"AH1NG": 292,
|
370 |
+
"EH1NT": 293,
|
371 |
+
"WEY1": 294,
|
372 |
+
"AH0V": 295,
|
373 |
+
"PRAH0D": 296,
|
374 |
+
"AW1ER0": 297,
|
375 |
+
"IH0KAH0L": 298,
|
376 |
+
"SHAH0L": 299,
|
377 |
+
"AE1NAH0M": 300,
|
378 |
+
"DHAE1N": 301,
|
379 |
+
"HHAE1Z": 302,
|
380 |
+
"EH1V": 303,
|
381 |
+
"NAH0S": 304,
|
382 |
+
"AY1T": 305,
|
383 |
+
"UW1S": 306,
|
384 |
+
"RIH1": 307,
|
385 |
+
"KAE1": 308,
|
386 |
+
"LD": 309,
|
387 |
+
"VEH1RIY0": 310,
|
388 |
+
"RIY1": 311,
|
389 |
+
"OW1Z": 312,
|
390 |
+
"SER0": 313,
|
391 |
+
"IH0KS": 314,
|
392 |
+
"LAY1K": 315,
|
393 |
+
"AY2Z": 316,
|
394 |
+
"WEH1N": 317,
|
395 |
+
"PT": 318,
|
396 |
+
"KAH0N": 319,
|
397 |
+
"NUW1": 320,
|
398 |
+
"AW1ND": 321,
|
399 |
+
"RIH0": 322,
|
400 |
+
"FER0": 323,
|
401 |
+
"AO1NG": 324,
|
402 |
+
"AE1ND": 325,
|
403 |
+
"EY1NJH": 326,
|
404 |
+
"AH0TS": 327,
|
405 |
+
"EY1SHAH0NZ": 328,
|
406 |
+
"WAH1T": 329,
|
407 |
+
"SEH2": 330,
|
408 |
+
"DIH0Z": 331,
|
409 |
+
"PLAE1NTS": 332,
|
410 |
+
"ER1N": 333,
|
411 |
+
"THIH1NG": 334,
|
412 |
+
"0R": 335,
|
413 |
+
"SIH1": 336,
|
414 |
+
"GROW1": 337,
|
415 |
+
"EH1NER0": 338,
|
416 |
+
"AO2R": 339,
|
417 |
+
"KW": 340,
|
418 |
+
"WIH1CH": 341,
|
419 |
+
"AA1KS": 342,
|
420 |
+
"SAH1": 343,
|
421 |
+
"IH2Z": 344,
|
422 |
+
"AO1F": 345,
|
423 |
+
"EY2TAH0D": 346,
|
424 |
+
"MAH1": 347,
|
425 |
+
"WEH1L": 348,
|
426 |
+
"AE1NAH0MAH0LZ": 349,
|
427 |
+
"IY1V": 350,
|
428 |
+
"EH1VER0": 351,
|
429 |
+
"HHYUW1": 352,
|
430 |
+
"TEY1": 353,
|
431 |
+
"IH0MP": 354,
|
432 |
+
"SEY1": 355,
|
433 |
+
"JHAH1ST": 356,
|
434 |
+
"AY1M": 357,
|
435 |
+
"AH1P": 358,
|
436 |
+
"KAH1M": 359,
|
437 |
+
"EH2RIY0": 360,
|
438 |
+
"IH1SHAH0N": 361,
|
439 |
+
"IY1N": 362,
|
440 |
+
"OW1T": 363,
|
441 |
+
"BAA1": 364,
|
442 |
+
"DIH1F": 365,
|
443 |
+
"IH1K": 366,
|
444 |
+
"BIH0K": 367,
|
445 |
+
"BIH0": 368,
|
446 |
+
"AW1N": 369,
|
447 |
+
"SM": 370,
|
448 |
+
"EY1Z": 371,
|
449 |
+
"MAH0T": 372,
|
450 |
+
"IH0D": 373,
|
451 |
+
"KIH0NG": 374,
|
452 |
+
"WAA1": 375,
|
453 |
+
"TAY1M": 376,
|
454 |
+
"HHYUW1MAH0N": 377,
|
455 |
+
"BER1": 378,
|
456 |
+
"HHIY1": 379,
|
457 |
+
"DHIH1S": 380,
|
458 |
+
"AE1NG": 381,
|
459 |
+
"IH1V": 382,
|
460 |
+
"FUW1D": 383
|
461 |
+
},
|
462 |
+
"merges": [
|
463 |
+
"H 0",
|
464 |
+
"A H0",
|
465 |
+
"H 1",
|
466 |
+
"Y 1",
|
467 |
+
"W 1",
|
468 |
+
"I H0",
|
469 |
+
"A E",
|
470 |
+
"I H1",
|
471 |
+
"AH0 N",
|
472 |
+
"E R",
|
473 |
+
"E H1",
|
474 |
+
"AE 1",
|
475 |
+
"A A",
|
476 |
+
"A H1",
|
477 |
+
"AA 1",
|
478 |
+
"ER 0",
|
479 |
+
"Y 0",
|
480 |
+
"I Y0",
|
481 |
+
"U W1",
|
482 |
+
"D H",
|
483 |
+
"A O",
|
484 |
+
"A Y1",
|
485 |
+
"I Y1",
|
486 |
+
"E Y1",
|
487 |
+
"AH0 L",
|
488 |
+
"AO 1",
|
489 |
+
"IH0 N",
|
490 |
+
"O W1",
|
491 |
+
"S T",
|
492 |
+
"H H",
|
493 |
+
"S H",
|
494 |
+
"AA1 R",
|
495 |
+
"DH AH0",
|
496 |
+
"AO1 R",
|
497 |
+
"AE1 N",
|
498 |
+
"IH1 Z",
|
499 |
+
"J H",
|
500 |
+
"AH1 V",
|
501 |
+
"T S",
|
502 |
+
"H 2",
|
503 |
+
"Y 2",
|
504 |
+
"AH0N D",
|
505 |
+
"T UW1",
|
506 |
+
"IH0N G",
|
507 |
+
"ER 1",
|
508 |
+
"EH1 N",
|
509 |
+
"SH AH0N",
|
510 |
+
"C H",
|
511 |
+
"AH0 T",
|
512 |
+
"P R",
|
513 |
+
"IH0 K",
|
514 |
+
"AH0 M",
|
515 |
+
"EH1 R",
|
516 |
+
"Y UW1",
|
517 |
+
"AH1 M",
|
518 |
+
"T H",
|
519 |
+
"HH AE1",
|
520 |
+
"AH0 S",
|
521 |
+
"A W1",
|
522 |
+
"AH0N T",
|
523 |
+
"W 0",
|
524 |
+
"IH1 N",
|
525 |
+
"ER0 Z",
|
526 |
+
"AH0 D",
|
527 |
+
"AH0 Z",
|
528 |
+
"HHAE1 V",
|
529 |
+
"EH1 L",
|
530 |
+
"R IY0",
|
531 |
+
"AE1 T",
|
532 |
+
"K T",
|
533 |
+
"E H2",
|
534 |
+
"K S",
|
535 |
+
"AA1 N",
|
536 |
+
"F AO1R",
|
537 |
+
"AH1 N",
|
538 |
+
"L IY0",
|
539 |
+
"EY1 SHAH0N",
|
540 |
+
"M OW1",
|
541 |
+
"U H1",
|
542 |
+
"E Y2",
|
543 |
+
"D Z",
|
544 |
+
"A Y2",
|
545 |
+
"S AH1M",
|
546 |
+
"I H2",
|
547 |
+
"AO1 L",
|
548 |
+
"D IH0",
|
549 |
+
"W IH1",
|
550 |
+
"P L",
|
551 |
+
"AH0 K",
|
552 |
+
"W 2",
|
553 |
+
"O W0",
|
554 |
+
"T ER0",
|
555 |
+
"G R",
|
556 |
+
"L AY1",
|
557 |
+
"T R",
|
558 |
+
"S P",
|
559 |
+
"AH0 B",
|
560 |
+
"AH0L Z",
|
561 |
+
"MOW1 ST",
|
562 |
+
"EY1 N",
|
563 |
+
"K AE1N",
|
564 |
+
"F R",
|
565 |
+
"IY0 Z",
|
566 |
+
"M AH0N",
|
567 |
+
"IH1 L",
|
568 |
+
"DH AE1T",
|
569 |
+
"AE 2",
|
570 |
+
"AH0N S",
|
571 |
+
"N D",
|
572 |
+
"IH1 T",
|
573 |
+
"AA1R T",
|
574 |
+
"K AA1",
|
575 |
+
"K R",
|
576 |
+
"OW1 N",
|
577 |
+
"AA 2",
|
578 |
+
"IH0 V",
|
579 |
+
"AH0 P",
|
580 |
+
"O W2",
|
581 |
+
"U W0",
|
582 |
+
"AA1 L",
|
583 |
+
"AH0T IY0",
|
584 |
+
"IH0 Z",
|
585 |
+
"ST R",
|
586 |
+
"B IY1",
|
587 |
+
"S K",
|
588 |
+
"IH1N G",
|
589 |
+
"EY2 T",
|
590 |
+
"AH0 JH",
|
591 |
+
"P AA1RT",
|
592 |
+
"N Z",
|
593 |
+
"EH1 K",
|
594 |
+
"DH EH1R",
|
595 |
+
"B R",
|
596 |
+
"IY1 Z",
|
597 |
+
"IY1 T",
|
598 |
+
"AE1 Z",
|
599 |
+
"AH0N Z",
|
600 |
+
"V ER0",
|
601 |
+
"WIH1 DH",
|
602 |
+
"AH1 T",
|
603 |
+
"B AY1",
|
604 |
+
"EH1 T",
|
605 |
+
"D R",
|
606 |
+
"P AH0L",
|
607 |
+
"OW1 L",
|
608 |
+
"YUW1 Z",
|
609 |
+
"W AY1",
|
610 |
+
"AH0 F",
|
611 |
+
"I Y2",
|
612 |
+
"AE 0",
|
613 |
+
"EH1 S",
|
614 |
+
"EY1 T",
|
615 |
+
"E H0",
|
616 |
+
"EH1 M",
|
617 |
+
"AO 2",
|
618 |
+
"F L",
|
619 |
+
"M EH1N",
|
620 |
+
"AE1 K",
|
621 |
+
"B L",
|
622 |
+
"EH1 D",
|
623 |
+
"P ER0",
|
624 |
+
"IH1 R",
|
625 |
+
"EH1 KT",
|
626 |
+
"O Y1",
|
627 |
+
"M Z",
|
628 |
+
"IH1 F",
|
629 |
+
"EH1 ST",
|
630 |
+
"M EY1",
|
631 |
+
"W IY1",
|
632 |
+
"DH ER0",
|
633 |
+
"CH ER0",
|
634 |
+
"L Z",
|
635 |
+
"A Y0",
|
636 |
+
"K L",
|
637 |
+
"D IY0",
|
638 |
+
"G Z",
|
639 |
+
"IH1 ST",
|
640 |
+
"V AY1",
|
641 |
+
"EH1R IY0",
|
642 |
+
"UH1 R",
|
643 |
+
"D ER0",
|
644 |
+
"AE1 L",
|
645 |
+
"AW1 T",
|
646 |
+
"FR AH1M",
|
647 |
+
"AH1 L",
|
648 |
+
"M P",
|
649 |
+
"N OW1",
|
650 |
+
"AH0 ST",
|
651 |
+
"T AY1",
|
652 |
+
"P IY1",
|
653 |
+
"AH0L IY0",
|
654 |
+
"AE1 S",
|
655 |
+
"W ER1",
|
656 |
+
"IH1 S",
|
657 |
+
"P S",
|
658 |
+
"IH0 T",
|
659 |
+
"IH2 N",
|
660 |
+
"PR AA1",
|
661 |
+
"IH0 L",
|
662 |
+
"AA1 T",
|
663 |
+
"S AY1",
|
664 |
+
"K AH0M",
|
665 |
+
"M IY1",
|
666 |
+
"W AH1N",
|
667 |
+
"W AO1",
|
668 |
+
"AH0N TS",
|
669 |
+
"PL AE1N",
|
670 |
+
"S IY1",
|
671 |
+
"SHAH0N Z",
|
672 |
+
"UH1 D",
|
673 |
+
"PIY1 PAH0L",
|
674 |
+
"M AY1",
|
675 |
+
"V Z",
|
676 |
+
"MEH1N IY0",
|
677 |
+
"AE1 M",
|
678 |
+
"M AH0NT",
|
679 |
+
"U W2",
|
680 |
+
"AH0 W",
|
681 |
+
"HH EH1L",
|
682 |
+
"Y AH0L",
|
683 |
+
"IH1 RIY0",
|
684 |
+
"WAO1 TER0",
|
685 |
+
"L OW1",
|
686 |
+
"K AH0NT",
|
687 |
+
"AH1 ST",
|
688 |
+
"F IY1",
|
689 |
+
"AH0M Z",
|
690 |
+
"M AO1R",
|
691 |
+
"EY1 S",
|
692 |
+
"AE1 KT",
|
693 |
+
"A H2",
|
694 |
+
"D UW1",
|
695 |
+
"AH0B AH0L",
|
696 |
+
"KAA1 Z",
|
697 |
+
"S EH1L",
|
698 |
+
"AO1R T",
|
699 |
+
"Y UW0",
|
700 |
+
"L IY1",
|
701 |
+
"TH R",
|
702 |
+
"EH1N D",
|
703 |
+
"UW1 D",
|
704 |
+
"B AH1T",
|
705 |
+
"S ER1",
|
706 |
+
"N T",
|
707 |
+
"S OW1",
|
708 |
+
"F AY1",
|
709 |
+
"AO1L S",
|
710 |
+
"AH0 G",
|
711 |
+
"N G",
|
712 |
+
"DH EY1",
|
713 |
+
"AH1 DHER0",
|
714 |
+
"AO1LS OW0",
|
715 |
+
"HH AY1",
|
716 |
+
"L IH1",
|
717 |
+
"AH1N G",
|
718 |
+
"EH1N T",
|
719 |
+
"W EY1",
|
720 |
+
"AH0 V",
|
721 |
+
"PR AH0D",
|
722 |
+
"AW1 ER0",
|
723 |
+
"IH0K AH0L",
|
724 |
+
"SH AH0L",
|
725 |
+
"AE1N AH0M",
|
726 |
+
"DH AE1N",
|
727 |
+
"HHAE1 Z",
|
728 |
+
"EH1 V",
|
729 |
+
"N AH0S",
|
730 |
+
"AY1 T",
|
731 |
+
"UW1 S",
|
732 |
+
"R IH1",
|
733 |
+
"K AE1",
|
734 |
+
"L D",
|
735 |
+
"V EH1RIY0",
|
736 |
+
"R IY1",
|
737 |
+
"OW1 Z",
|
738 |
+
"S ER0",
|
739 |
+
"IH0K S",
|
740 |
+
"LAY1 K",
|
741 |
+
"AY2 Z",
|
742 |
+
"W EH1N",
|
743 |
+
"P T",
|
744 |
+
"K AH0N",
|
745 |
+
"N UW1",
|
746 |
+
"AW1 ND",
|
747 |
+
"R IH0",
|
748 |
+
"F ER0",
|
749 |
+
"AO1 NG",
|
750 |
+
"AE1N D",
|
751 |
+
"EY1N JH",
|
752 |
+
"AH0 TS",
|
753 |
+
"EY1SHAH0N Z",
|
754 |
+
"W AH1T",
|
755 |
+
"S EH2",
|
756 |
+
"DIH0 Z",
|
757 |
+
"PLAE1N TS",
|
758 |
+
"ER1 N",
|
759 |
+
"TH IH1NG",
|
760 |
+
"0 R",
|
761 |
+
"S IH1",
|
762 |
+
"GR OW1",
|
763 |
+
"EH1N ER0",
|
764 |
+
"AO2 R",
|
765 |
+
"K W",
|
766 |
+
"WIH1 CH",
|
767 |
+
"AA1 KS",
|
768 |
+
"S AH1",
|
769 |
+
"IH2 Z",
|
770 |
+
"AO1 F",
|
771 |
+
"EY2T AH0D",
|
772 |
+
"M AH1",
|
773 |
+
"W EH1L",
|
774 |
+
"AE1NAH0M AH0LZ",
|
775 |
+
"IY1 V",
|
776 |
+
"EH1 VER0",
|
777 |
+
"HH YUW1",
|
778 |
+
"T EY1",
|
779 |
+
"IH0 MP",
|
780 |
+
"S EY1",
|
781 |
+
"JH AH1ST",
|
782 |
+
"AY1 M",
|
783 |
+
"AH1 P",
|
784 |
+
"K AH1M",
|
785 |
+
"EH2 RIY0",
|
786 |
+
"IH1 SHAH0N",
|
787 |
+
"IY1 N",
|
788 |
+
"OW1 T",
|
789 |
+
"B AA1",
|
790 |
+
"D IH1F",
|
791 |
+
"IH1 K",
|
792 |
+
"B IH0K",
|
793 |
+
"B IH0",
|
794 |
+
"AW1 N",
|
795 |
+
"S M",
|
796 |
+
"EY1 Z",
|
797 |
+
"M AH0T",
|
798 |
+
"IH0 D",
|
799 |
+
"K IH0NG",
|
800 |
+
"W AA1",
|
801 |
+
"TAY1 M",
|
802 |
+
"HHYUW1 MAH0N",
|
803 |
+
"B ER1",
|
804 |
+
"HH IY1",
|
805 |
+
"DH IH1S",
|
806 |
+
"AE1N G",
|
807 |
+
"IH1 V",
|
808 |
+
"F UW1D"
|
809 |
+
]
|
810 |
+
}
|
811 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"mask_token": "[MASK]",
|
47 |
+
"model_max_length": 1000000000000000019884624838656,
|
48 |
+
"pad_token": "[PAD]",
|
49 |
+
"sep_token": "[SEP]",
|
50 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
51 |
+
"unk_token": "[UNK]"
|
52 |
+
}
|