Training done
Browse files- added_tokens.json +2 -22
- tokenizer.json +1 -181
added_tokens.json
CHANGED
|
@@ -1,28 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"</s>": 32000,
|
| 3 |
-
"<s_cord-v2>":
|
| 4 |
"কুষ্টিয়া": 32001,
|
| 5 |
-
"খূলণা": 32022,
|
| 6 |
-
"চট্টমেটড়ো": 32006,
|
| 7 |
-
"চট্টো": 32007,
|
| 8 |
-
"চট্রো": 32016,
|
| 9 |
-
"চুয়াডাঙ্গা": 32019,
|
| 10 |
-
"জশর": 32023,
|
| 11 |
-
"জোশোড়": 32004,
|
| 12 |
-
"জোষোড়": 32010,
|
| 13 |
-
"ঝিনাইদাহ": 32020,
|
| 14 |
-
"টাংগাইল": 32005,
|
| 15 |
-
"টাঞাঈল": 32012,
|
| 16 |
-
"ঢাককা": 32024,
|
| 17 |
-
"ধাকা": 32011,
|
| 18 |
"নারায়ণগঞ্জ": 32003,
|
| 19 |
-
"নারায়নগঞ্জ": 32008,
|
| 20 |
-
"নোয়াখালী": 32021,
|
| 21 |
-
"নড়াইল": 32009,
|
| 22 |
-
"বগুড়া": 32017,
|
| 23 |
-
"মেটড়ো": 32015,
|
| 24 |
"ময়মনসিংহ": 32002,
|
| 25 |
-
"
|
| 26 |
-
"রাজবাড়ী": 32013,
|
| 27 |
-
"্ডহাকা": 32014
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"</s>": 32000,
|
| 3 |
+
"<s_cord-v2>": 32005,
|
| 4 |
"কুষ্টিয়া": 32001,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"নারায়ণগঞ্জ": 32003,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"ময়মনসিংহ": 32002,
|
| 7 |
+
"রাজবাড়ী": 32004
|
|
|
|
|
|
|
| 8 |
}
|
tokenizer.json
CHANGED
|
@@ -100,87 +100,6 @@
|
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"id": 32004,
|
| 103 |
-
"content": "জোশোড়",
|
| 104 |
-
"single_word": false,
|
| 105 |
-
"lstrip": false,
|
| 106 |
-
"rstrip": false,
|
| 107 |
-
"normalized": true,
|
| 108 |
-
"special": false
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"id": 32005,
|
| 112 |
-
"content": "টাংগাইল",
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"lstrip": false,
|
| 115 |
-
"rstrip": false,
|
| 116 |
-
"normalized": true,
|
| 117 |
-
"special": false
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"id": 32006,
|
| 121 |
-
"content": "চট্টমেটড়ো",
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"lstrip": false,
|
| 124 |
-
"rstrip": false,
|
| 125 |
-
"normalized": true,
|
| 126 |
-
"special": false
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"id": 32007,
|
| 130 |
-
"content": "চট্টো",
|
| 131 |
-
"single_word": false,
|
| 132 |
-
"lstrip": false,
|
| 133 |
-
"rstrip": false,
|
| 134 |
-
"normalized": true,
|
| 135 |
-
"special": false
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"id": 32008,
|
| 139 |
-
"content": "নারায়নগঞ্জ",
|
| 140 |
-
"single_word": false,
|
| 141 |
-
"lstrip": false,
|
| 142 |
-
"rstrip": false,
|
| 143 |
-
"normalized": true,
|
| 144 |
-
"special": false
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"id": 32009,
|
| 148 |
-
"content": "নড়াইল",
|
| 149 |
-
"single_word": false,
|
| 150 |
-
"lstrip": false,
|
| 151 |
-
"rstrip": false,
|
| 152 |
-
"normalized": true,
|
| 153 |
-
"special": false
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"id": 32010,
|
| 157 |
-
"content": "জোষোড়",
|
| 158 |
-
"single_word": false,
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"rstrip": false,
|
| 161 |
-
"normalized": true,
|
| 162 |
-
"special": false
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"id": 32011,
|
| 166 |
-
"content": "ধাকা",
|
| 167 |
-
"single_word": false,
|
| 168 |
-
"lstrip": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"normalized": true,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"id": 32012,
|
| 175 |
-
"content": "টাঞাঈল",
|
| 176 |
-
"single_word": false,
|
| 177 |
-
"lstrip": false,
|
| 178 |
-
"rstrip": false,
|
| 179 |
-
"normalized": true,
|
| 180 |
-
"special": false
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"id": 32013,
|
| 184 |
"content": "রাজবাড়ী",
|
| 185 |
"single_word": false,
|
| 186 |
"lstrip": false,
|
|
@@ -189,106 +108,7 @@
|
|
| 189 |
"special": false
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"id":
|
| 193 |
-
"content": "্ডহাকা",
|
| 194 |
-
"single_word": false,
|
| 195 |
-
"lstrip": false,
|
| 196 |
-
"rstrip": false,
|
| 197 |
-
"normalized": true,
|
| 198 |
-
"special": false
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"id": 32015,
|
| 202 |
-
"content": "মেটড়ো",
|
| 203 |
-
"single_word": false,
|
| 204 |
-
"lstrip": false,
|
| 205 |
-
"rstrip": false,
|
| 206 |
-
"normalized": true,
|
| 207 |
-
"special": false
|
| 208 |
-
},
|
| 209 |
-
{
|
| 210 |
-
"id": 32016,
|
| 211 |
-
"content": "চট্রো",
|
| 212 |
-
"single_word": false,
|
| 213 |
-
"lstrip": false,
|
| 214 |
-
"rstrip": false,
|
| 215 |
-
"normalized": true,
|
| 216 |
-
"special": false
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"id": 32017,
|
| 220 |
-
"content": "বগুড়া",
|
| 221 |
-
"single_word": false,
|
| 222 |
-
"lstrip": false,
|
| 223 |
-
"rstrip": false,
|
| 224 |
-
"normalized": true,
|
| 225 |
-
"special": false
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"id": 32018,
|
| 229 |
-
"content": "যশোর",
|
| 230 |
-
"single_word": false,
|
| 231 |
-
"lstrip": false,
|
| 232 |
-
"rstrip": false,
|
| 233 |
-
"normalized": true,
|
| 234 |
-
"special": false
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"id": 32019,
|
| 238 |
-
"content": "চুয়াডাঙ্গা",
|
| 239 |
-
"single_word": false,
|
| 240 |
-
"lstrip": false,
|
| 241 |
-
"rstrip": false,
|
| 242 |
-
"normalized": true,
|
| 243 |
-
"special": false
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"id": 32020,
|
| 247 |
-
"content": "ঝিনাইদাহ",
|
| 248 |
-
"single_word": false,
|
| 249 |
-
"lstrip": false,
|
| 250 |
-
"rstrip": false,
|
| 251 |
-
"normalized": true,
|
| 252 |
-
"special": false
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"id": 32021,
|
| 256 |
-
"content": "নোয়াখালী",
|
| 257 |
-
"single_word": false,
|
| 258 |
-
"lstrip": false,
|
| 259 |
-
"rstrip": false,
|
| 260 |
-
"normalized": true,
|
| 261 |
-
"special": false
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"id": 32022,
|
| 265 |
-
"content": "খূলণা",
|
| 266 |
-
"single_word": false,
|
| 267 |
-
"lstrip": false,
|
| 268 |
-
"rstrip": false,
|
| 269 |
-
"normalized": true,
|
| 270 |
-
"special": false
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"id": 32023,
|
| 274 |
-
"content": "জশর",
|
| 275 |
-
"single_word": false,
|
| 276 |
-
"lstrip": false,
|
| 277 |
-
"rstrip": false,
|
| 278 |
-
"normalized": true,
|
| 279 |
-
"special": false
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"id": 32024,
|
| 283 |
-
"content": "ঢাককা",
|
| 284 |
-
"single_word": false,
|
| 285 |
-
"lstrip": false,
|
| 286 |
-
"rstrip": false,
|
| 287 |
-
"normalized": true,
|
| 288 |
-
"special": false
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"id": 32025,
|
| 292 |
"content": "<s_cord-v2>",
|
| 293 |
"single_word": false,
|
| 294 |
"lstrip": false,
|
|
|
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"id": 32004,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
"content": "রাজবাড়ী",
|
| 104 |
"single_word": false,
|
| 105 |
"lstrip": false,
|
|
|
|
| 108 |
"special": false
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"id": 32005,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 112 |
"content": "<s_cord-v2>",
|
| 113 |
"single_word": false,
|
| 114 |
"lstrip": false,
|