Training started
Browse files- added_tokens.json +2 -34
- preprocessor_config.json +2 -2
- special_tokens_map.json +2 -36
- tokenizer.json +8 -310
added_tokens.json
CHANGED
@@ -1,39 +1,7 @@
|
|
1 |
{
|
2 |
-
"</
|
3 |
-
"</s_ignore>": 57556,
|
4 |
-
"</s_item_key>": 57554,
|
5 |
-
"</s_item_name>": 57552,
|
6 |
-
"</s_item_quantity>": 57550,
|
7 |
-
"</s_item_value>": 57548,
|
8 |
-
"</s_line_items>": 57546,
|
9 |
-
"</s_others>": 57542,
|
10 |
-
"</s_store_addr>": 57540,
|
11 |
-
"</s_store_name>": 57538,
|
12 |
-
"</s_subtotal>": 57536,
|
13 |
-
"</s_tax>": 57534,
|
14 |
-
"</s_telephone>": 57532,
|
15 |
-
"</s_text>": 57544,
|
16 |
-
"</s_time>": 57530,
|
17 |
-
"</s_tips>": 57528,
|
18 |
-
"</s_total>": 57526,
|
19 |
-
"<s_date>": 57557,
|
20 |
-
"<s_ignore>": 57555,
|
21 |
"<s_iitcdip>": 57523,
|
22 |
-
"<
|
23 |
-
"<s_item_name>": 57551,
|
24 |
-
"<s_item_quantity>": 57549,
|
25 |
-
"<s_item_value>": 57547,
|
26 |
-
"<s_line_items>": 57545,
|
27 |
-
"<s_others>": 57541,
|
28 |
-
"<s_store_addr>": 57539,
|
29 |
-
"<s_store_name>": 57537,
|
30 |
-
"<s_subtotal>": 57535,
|
31 |
"<s_synthdog>": 57524,
|
32 |
-
"<s_tax>": 57533,
|
33 |
-
"<s_telephone>": 57531,
|
34 |
-
"<s_text>": 57543,
|
35 |
-
"<s_time>": 57529,
|
36 |
-
"<s_tips>": 57527,
|
37 |
-
"<s_total>": 57525,
|
38 |
"<sep/>": 57522
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"</s_receipt>": 57526,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"<s_iitcdip>": 57523,
|
4 |
+
"<s_receipt>": 57525,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"<s_synthdog>": 57524,
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"<sep/>": 57522
|
7 |
}
|
preprocessor_config.json
CHANGED
@@ -20,7 +20,7 @@
|
|
20 |
"resample": 2,
|
21 |
"rescale_factor": 0.00392156862745098,
|
22 |
"size": [
|
23 |
-
|
24 |
-
|
25 |
]
|
26 |
}
|
|
|
20 |
"resample": 2,
|
21 |
"rescale_factor": 0.00392156862745098,
|
22 |
"size": [
|
23 |
+
1280,
|
24 |
+
1920
|
25 |
]
|
26 |
}
|
special_tokens_map.json
CHANGED
@@ -1,41 +1,7 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
"<
|
4 |
-
"
|
5 |
-
"<s_tips>",
|
6 |
-
"</s_tips>",
|
7 |
-
"<s_time>",
|
8 |
-
"</s_time>",
|
9 |
-
"<s_telephone>",
|
10 |
-
"</s_telephone>",
|
11 |
-
"<s_tax>",
|
12 |
-
"</s_tax>",
|
13 |
-
"<s_subtotal>",
|
14 |
-
"</s_subtotal>",
|
15 |
-
"<s_store_name>",
|
16 |
-
"</s_store_name>",
|
17 |
-
"<s_store_addr>",
|
18 |
-
"</s_store_addr>",
|
19 |
-
"<s_others>",
|
20 |
-
"</s_others>",
|
21 |
-
"<s_text>",
|
22 |
-
"</s_text>",
|
23 |
-
"<s_line_items>",
|
24 |
-
"</s_line_items>",
|
25 |
-
"<s_item_value>",
|
26 |
-
"</s_item_value>",
|
27 |
-
"<s_item_quantity>",
|
28 |
-
"</s_item_quantity>",
|
29 |
-
"<s_item_name>",
|
30 |
-
"</s_item_name>",
|
31 |
-
"<s_item_key>",
|
32 |
-
"</s_item_key>",
|
33 |
-
"<s_ignore>",
|
34 |
-
"</s_ignore>",
|
35 |
-
"<s_date>",
|
36 |
-
"</s_date>",
|
37 |
-
"<s>",
|
38 |
-
"</s>"
|
39 |
],
|
40 |
"bos_token": "<s>",
|
41 |
"cls_token": "<s>",
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"<s_iitcdip>",
|
4 |
+
"<s_synthdog>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
],
|
6 |
"bos_token": "<s>",
|
7 |
"cls_token": "<s>",
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 512,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 512
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 1,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "<pad>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
@@ -91,309 +77,21 @@
|
|
91 |
},
|
92 |
{
|
93 |
"id": 57525,
|
94 |
-
"content": "<
|
95 |
"single_word": false,
|
96 |
"lstrip": false,
|
97 |
"rstrip": false,
|
98 |
-
"normalized":
|
99 |
-
"special":
|
100 |
},
|
101 |
{
|
102 |
"id": 57526,
|
103 |
-
"content": "</
|
104 |
-
"single_word": false,
|
105 |
-
"lstrip": false,
|
106 |
-
"rstrip": false,
|
107 |
-
"normalized": false,
|
108 |
-
"special": true
|
109 |
-
},
|
110 |
-
{
|
111 |
-
"id": 57527,
|
112 |
-
"content": "<s_tips>",
|
113 |
-
"single_word": false,
|
114 |
-
"lstrip": false,
|
115 |
-
"rstrip": false,
|
116 |
-
"normalized": false,
|
117 |
-
"special": true
|
118 |
-
},
|
119 |
-
{
|
120 |
-
"id": 57528,
|
121 |
-
"content": "</s_tips>",
|
122 |
-
"single_word": false,
|
123 |
-
"lstrip": false,
|
124 |
-
"rstrip": false,
|
125 |
-
"normalized": false,
|
126 |
-
"special": true
|
127 |
-
},
|
128 |
-
{
|
129 |
-
"id": 57529,
|
130 |
-
"content": "<s_time>",
|
131 |
-
"single_word": false,
|
132 |
-
"lstrip": false,
|
133 |
-
"rstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"special": true
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"id": 57530,
|
139 |
-
"content": "</s_time>",
|
140 |
-
"single_word": false,
|
141 |
-
"lstrip": false,
|
142 |
-
"rstrip": false,
|
143 |
-
"normalized": false,
|
144 |
-
"special": true
|
145 |
-
},
|
146 |
-
{
|
147 |
-
"id": 57531,
|
148 |
-
"content": "<s_telephone>",
|
149 |
-
"single_word": false,
|
150 |
-
"lstrip": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"normalized": false,
|
153 |
-
"special": true
|
154 |
-
},
|
155 |
-
{
|
156 |
-
"id": 57532,
|
157 |
-
"content": "</s_telephone>",
|
158 |
-
"single_word": false,
|
159 |
-
"lstrip": false,
|
160 |
-
"rstrip": false,
|
161 |
-
"normalized": false,
|
162 |
-
"special": true
|
163 |
-
},
|
164 |
-
{
|
165 |
-
"id": 57533,
|
166 |
-
"content": "<s_tax>",
|
167 |
-
"single_word": false,
|
168 |
-
"lstrip": false,
|
169 |
-
"rstrip": false,
|
170 |
-
"normalized": false,
|
171 |
-
"special": true
|
172 |
-
},
|
173 |
-
{
|
174 |
-
"id": 57534,
|
175 |
-
"content": "</s_tax>",
|
176 |
-
"single_word": false,
|
177 |
-
"lstrip": false,
|
178 |
-
"rstrip": false,
|
179 |
-
"normalized": false,
|
180 |
-
"special": true
|
181 |
-
},
|
182 |
-
{
|
183 |
-
"id": 57535,
|
184 |
-
"content": "<s_subtotal>",
|
185 |
-
"single_word": false,
|
186 |
-
"lstrip": false,
|
187 |
-
"rstrip": false,
|
188 |
-
"normalized": false,
|
189 |
-
"special": true
|
190 |
-
},
|
191 |
-
{
|
192 |
-
"id": 57536,
|
193 |
-
"content": "</s_subtotal>",
|
194 |
"single_word": false,
|
195 |
"lstrip": false,
|
196 |
"rstrip": false,
|
197 |
-
"normalized":
|
198 |
-
"special":
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"id": 57537,
|
202 |
-
"content": "<s_store_name>",
|
203 |
-
"single_word": false,
|
204 |
-
"lstrip": false,
|
205 |
-
"rstrip": false,
|
206 |
-
"normalized": false,
|
207 |
-
"special": true
|
208 |
-
},
|
209 |
-
{
|
210 |
-
"id": 57538,
|
211 |
-
"content": "</s_store_name>",
|
212 |
-
"single_word": false,
|
213 |
-
"lstrip": false,
|
214 |
-
"rstrip": false,
|
215 |
-
"normalized": false,
|
216 |
-
"special": true
|
217 |
-
},
|
218 |
-
{
|
219 |
-
"id": 57539,
|
220 |
-
"content": "<s_store_addr>",
|
221 |
-
"single_word": false,
|
222 |
-
"lstrip": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"normalized": false,
|
225 |
-
"special": true
|
226 |
-
},
|
227 |
-
{
|
228 |
-
"id": 57540,
|
229 |
-
"content": "</s_store_addr>",
|
230 |
-
"single_word": false,
|
231 |
-
"lstrip": false,
|
232 |
-
"rstrip": false,
|
233 |
-
"normalized": false,
|
234 |
-
"special": true
|
235 |
-
},
|
236 |
-
{
|
237 |
-
"id": 57541,
|
238 |
-
"content": "<s_others>",
|
239 |
-
"single_word": false,
|
240 |
-
"lstrip": false,
|
241 |
-
"rstrip": false,
|
242 |
-
"normalized": false,
|
243 |
-
"special": true
|
244 |
-
},
|
245 |
-
{
|
246 |
-
"id": 57542,
|
247 |
-
"content": "</s_others>",
|
248 |
-
"single_word": false,
|
249 |
-
"lstrip": false,
|
250 |
-
"rstrip": false,
|
251 |
-
"normalized": false,
|
252 |
-
"special": true
|
253 |
-
},
|
254 |
-
{
|
255 |
-
"id": 57543,
|
256 |
-
"content": "<s_text>",
|
257 |
-
"single_word": false,
|
258 |
-
"lstrip": false,
|
259 |
-
"rstrip": false,
|
260 |
-
"normalized": false,
|
261 |
-
"special": true
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"id": 57544,
|
265 |
-
"content": "</s_text>",
|
266 |
-
"single_word": false,
|
267 |
-
"lstrip": false,
|
268 |
-
"rstrip": false,
|
269 |
-
"normalized": false,
|
270 |
-
"special": true
|
271 |
-
},
|
272 |
-
{
|
273 |
-
"id": 57545,
|
274 |
-
"content": "<s_line_items>",
|
275 |
-
"single_word": false,
|
276 |
-
"lstrip": false,
|
277 |
-
"rstrip": false,
|
278 |
-
"normalized": false,
|
279 |
-
"special": true
|
280 |
-
},
|
281 |
-
{
|
282 |
-
"id": 57546,
|
283 |
-
"content": "</s_line_items>",
|
284 |
-
"single_word": false,
|
285 |
-
"lstrip": false,
|
286 |
-
"rstrip": false,
|
287 |
-
"normalized": false,
|
288 |
-
"special": true
|
289 |
-
},
|
290 |
-
{
|
291 |
-
"id": 57547,
|
292 |
-
"content": "<s_item_value>",
|
293 |
-
"single_word": false,
|
294 |
-
"lstrip": false,
|
295 |
-
"rstrip": false,
|
296 |
-
"normalized": false,
|
297 |
-
"special": true
|
298 |
-
},
|
299 |
-
{
|
300 |
-
"id": 57548,
|
301 |
-
"content": "</s_item_value>",
|
302 |
-
"single_word": false,
|
303 |
-
"lstrip": false,
|
304 |
-
"rstrip": false,
|
305 |
-
"normalized": false,
|
306 |
-
"special": true
|
307 |
-
},
|
308 |
-
{
|
309 |
-
"id": 57549,
|
310 |
-
"content": "<s_item_quantity>",
|
311 |
-
"single_word": false,
|
312 |
-
"lstrip": false,
|
313 |
-
"rstrip": false,
|
314 |
-
"normalized": false,
|
315 |
-
"special": true
|
316 |
-
},
|
317 |
-
{
|
318 |
-
"id": 57550,
|
319 |
-
"content": "</s_item_quantity>",
|
320 |
-
"single_word": false,
|
321 |
-
"lstrip": false,
|
322 |
-
"rstrip": false,
|
323 |
-
"normalized": false,
|
324 |
-
"special": true
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"id": 57551,
|
328 |
-
"content": "<s_item_name>",
|
329 |
-
"single_word": false,
|
330 |
-
"lstrip": false,
|
331 |
-
"rstrip": false,
|
332 |
-
"normalized": false,
|
333 |
-
"special": true
|
334 |
-
},
|
335 |
-
{
|
336 |
-
"id": 57552,
|
337 |
-
"content": "</s_item_name>",
|
338 |
-
"single_word": false,
|
339 |
-
"lstrip": false,
|
340 |
-
"rstrip": false,
|
341 |
-
"normalized": false,
|
342 |
-
"special": true
|
343 |
-
},
|
344 |
-
{
|
345 |
-
"id": 57553,
|
346 |
-
"content": "<s_item_key>",
|
347 |
-
"single_word": false,
|
348 |
-
"lstrip": false,
|
349 |
-
"rstrip": false,
|
350 |
-
"normalized": false,
|
351 |
-
"special": true
|
352 |
-
},
|
353 |
-
{
|
354 |
-
"id": 57554,
|
355 |
-
"content": "</s_item_key>",
|
356 |
-
"single_word": false,
|
357 |
-
"lstrip": false,
|
358 |
-
"rstrip": false,
|
359 |
-
"normalized": false,
|
360 |
-
"special": true
|
361 |
-
},
|
362 |
-
{
|
363 |
-
"id": 57555,
|
364 |
-
"content": "<s_ignore>",
|
365 |
-
"single_word": false,
|
366 |
-
"lstrip": false,
|
367 |
-
"rstrip": false,
|
368 |
-
"normalized": false,
|
369 |
-
"special": true
|
370 |
-
},
|
371 |
-
{
|
372 |
-
"id": 57556,
|
373 |
-
"content": "</s_ignore>",
|
374 |
-
"single_word": false,
|
375 |
-
"lstrip": false,
|
376 |
-
"rstrip": false,
|
377 |
-
"normalized": false,
|
378 |
-
"special": true
|
379 |
-
},
|
380 |
-
{
|
381 |
-
"id": 57557,
|
382 |
-
"content": "<s_date>",
|
383 |
-
"single_word": false,
|
384 |
-
"lstrip": false,
|
385 |
-
"rstrip": false,
|
386 |
-
"normalized": false,
|
387 |
-
"special": true
|
388 |
-
},
|
389 |
-
{
|
390 |
-
"id": 57558,
|
391 |
-
"content": "</s_date>",
|
392 |
-
"single_word": false,
|
393 |
-
"lstrip": false,
|
394 |
-
"rstrip": false,
|
395 |
-
"normalized": false,
|
396 |
-
"special": true
|
397 |
}
|
398 |
],
|
399 |
"normalizer": {
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
77 |
},
|
78 |
{
|
79 |
"id": 57525,
|
80 |
+
"content": "<s_receipt>",
|
81 |
"single_word": false,
|
82 |
"lstrip": false,
|
83 |
"rstrip": false,
|
84 |
+
"normalized": true,
|
85 |
+
"special": false
|
86 |
},
|
87 |
{
|
88 |
"id": 57526,
|
89 |
+
"content": "</s_receipt>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
90 |
"single_word": false,
|
91 |
"lstrip": false,
|
92 |
"rstrip": false,
|
93 |
+
"normalized": true,
|
94 |
+
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
95 |
}
|
96 |
],
|
97 |
"normalizer": {
|