ljcamargo commited on
Commit
2aa5416
·
verified ·
1 Parent(s): 94002fd

Upload recipe/corpus_checksums.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. recipe/corpus_checksums.json +352 -0
recipe/corpus_checksums.json ADDED
@@ -0,0 +1,352 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modern:all": {
3
+ "path": "/content/corpus/modern/all/tachiwin.txt",
4
+ "bytes": 757286,
5
+ "sha256": "eaa63f248ced9d75480195dea826f79555a28d028d111c01a73a8420b69b6e31"
6
+ },
7
+ "modern:amu": {
8
+ "path": "/content/corpus/modern/amu/tachiwin.txt",
9
+ "bytes": 706788,
10
+ "sha256": "575cd8f9af2bbc85888e37b9b43cb7289de6cce9e852b975fb71837aeb6bcadc"
11
+ },
12
+ "modern:amu0": {
13
+ "path": "/content/corpus/modern/amu0/tachiwin.txt",
14
+ "bytes": 19180,
15
+ "sha256": "d19bd2ade6551b7971e2b9cca5ca6edc61fcff0895578bf9811347e7d4b78869"
16
+ },
17
+ "modern:azn0": {
18
+ "path": "/content/corpus/modern/azn0/tachiwin.txt",
19
+ "bytes": 273361,
20
+ "sha256": "57374859f3f4eb6307cc579c977170853c42adf5c616945b6139c2d2d48e57b9"
21
+ },
22
+ "modern:azz": {
23
+ "path": "/content/corpus/modern/azz/tachiwin.txt",
24
+ "bytes": 56817,
25
+ "sha256": "0ec8dc251b709fa5cd1865550cbb8e83eff482dd215babb40fe3030dac5e299c"
26
+ },
27
+ "modern:cco0": {
28
+ "path": "/content/corpus/modern/cco0/tachiwin.txt",
29
+ "bytes": 866918,
30
+ "sha256": "b5b6e5f1e3750495afc1b844eaffe2d48df30b9bd6b5180d759ec5beefe930ff"
31
+ },
32
+ "modern:chf": {
33
+ "path": "/content/corpus/modern/chf/tachiwin.txt",
34
+ "bytes": 470400,
35
+ "sha256": "471e58382d62995cfe1dd29d9cf328f9a1392bc629c2d99f52ee5a32f7cfe962"
36
+ },
37
+ "modern:chf0": {
38
+ "path": "/content/corpus/modern/chf0/tachiwin.txt",
39
+ "bytes": 2948,
40
+ "sha256": "5dfc68f9081368cd7c4a626d0779f63ff364d9fe097b00f5c80fbdd51e0599f8"
41
+ },
42
+ "modern:coz": {
43
+ "path": "/content/corpus/modern/coz/tachiwin.txt",
44
+ "bytes": 2245,
45
+ "sha256": "4c3a8b4d44b2d95a063e85005d48d061fef5178b06bba21d1349db22baf02a51"
46
+ },
47
+ "modern:ctp0": {
48
+ "path": "/content/corpus/modern/ctp0/tachiwin.txt",
49
+ "bytes": 551915,
50
+ "sha256": "bb9a92ce22c189c1a065567b0a1d215b300c8d45c626be77b351143c048f0479"
51
+ },
52
+ "modern:ctu": {
53
+ "path": "/content/corpus/modern/ctu/tachiwin.txt",
54
+ "bytes": 529593,
55
+ "sha256": "5b6d7aab99644797ceeeff463bd0e89b914c1d0860e45bd5c47ff505e08a36fe"
56
+ },
57
+ "modern:cux": {
58
+ "path": "/content/corpus/modern/cux/tachiwin.txt",
59
+ "bytes": 508640,
60
+ "sha256": "b052d56635eff77b1b1abfd2c85f67f9447468bfe661ed271ee14df174a88032"
61
+ },
62
+ "modern:de": {
63
+ "path": "/content/corpus/modern/de/tachiwin.txt",
64
+ "bytes": 675283,
65
+ "sha256": "080a205ef5d5b98b8ac227ebb03fef5fb788f12c051134b421787709e1fe5f7a"
66
+ },
67
+ "modern:en-US": {
68
+ "path": "/content/corpus/modern/en-US/tachiwin.txt",
69
+ "bytes": 610624,
70
+ "sha256": "8837e45b09c6e8e392a7cd386206a39d4f65f45ee3b8115223cf32280d440f0e"
71
+ },
72
+ "modern:es-MX": {
73
+ "path": "/content/corpus/modern/es-MX/tachiwin.txt",
74
+ "bytes": 612289,
75
+ "sha256": "ef7da6994006eb0069e3a0acb07b8d8e6605e969704d238c43918844a5d33152"
76
+ },
77
+ "modern:fr": {
78
+ "path": "/content/corpus/modern/fr/tachiwin.txt",
79
+ "bytes": 760566,
80
+ "sha256": "ea8a7090480009f76aeeb9eae4b0ef5a6c75e78bf51355eeee2f15215097539f"
81
+ },
82
+ "modern:hch": {
83
+ "path": "/content/corpus/modern/hch/tachiwin.txt",
84
+ "bytes": 428093,
85
+ "sha256": "10e66c3bb9bb76e0322629c22256a04a6212f8b16e601fb50dfe869d53696bf0"
86
+ },
87
+ "modern:hus": {
88
+ "path": "/content/corpus/modern/hus/tachiwin.txt",
89
+ "bytes": 464435,
90
+ "sha256": "d3bd2822ffab0559b26d1526cf1e58d308dec1d6a80d44150fd20691a60949f3"
91
+ },
92
+ "modern:huv": {
93
+ "path": "/content/corpus/modern/huv/tachiwin.txt",
94
+ "bytes": 553940,
95
+ "sha256": "204141004c0292f343b7b513a41247f58cb45e16d3a3cdc5efebcbcfece9bf6b"
96
+ },
97
+ "modern:lac": {
98
+ "path": "/content/corpus/modern/lac/tachiwin.txt",
99
+ "bytes": 505177,
100
+ "sha256": "9d00ee2759a22b22be33cd869e9b8c096dbcb3d27da21ff0517f215b94ff7f53"
101
+ },
102
+ "modern:mam": {
103
+ "path": "/content/corpus/modern/mam/tachiwin.txt",
104
+ "bytes": 403218,
105
+ "sha256": "9536262fe2f582236d6d34c1f7dd7432b0d607dda9697b3c30e8a9b632d8e60f"
106
+ },
107
+ "modern:mau": {
108
+ "path": "/content/corpus/modern/mau/tachiwin.txt",
109
+ "bytes": 21739,
110
+ "sha256": "ea96983ae0de50ab365209039c24f576f6b4cb2af3cf20e9476893cb9d583940"
111
+ },
112
+ "modern:maz": {
113
+ "path": "/content/corpus/modern/maz/tachiwin.txt",
114
+ "bytes": 495979,
115
+ "sha256": "3678d0993a7cbe28420592520a3f062c178208b5c5743e8c091d843a4a00d054"
116
+ },
117
+ "modern:meh": {
118
+ "path": "/content/corpus/modern/meh/tachiwin.txt",
119
+ "bytes": 193877,
120
+ "sha256": "4b41d7d660a5126de056d082d1b9cb59b3ff6f8a7d611a978c56db224ef25b47"
121
+ },
122
+ "modern:mfy": {
123
+ "path": "/content/corpus/modern/mfy/tachiwin.txt",
124
+ "bytes": 411917,
125
+ "sha256": "3cf753745c965c1f05c2e0409ba81e26ad5b6c234433734da8f4a00b761f4b21"
126
+ },
127
+ "modern:mix": {
128
+ "path": "/content/corpus/modern/mix/tachiwin.txt",
129
+ "bytes": 64421,
130
+ "sha256": "59826b0f98867336f17d5aacfaa0b81aea7f6527d829d10e6b6d1ff73f390d84"
131
+ },
132
+ "modern:mmc": {
133
+ "path": "/content/corpus/modern/mmc/tachiwin.txt",
134
+ "bytes": 5817,
135
+ "sha256": "83c383e43ca217585b5a70de1ecd1edc8637cae399f0c302093fe21bdccbba66"
136
+ },
137
+ "modern:nch": {
138
+ "path": "/content/corpus/modern/nch/tachiwin.txt",
139
+ "bytes": 400157,
140
+ "sha256": "e3e087d2041795dba46eb06f9e6ac8d2a00841d57ad2b804dd095564fccae8bc"
141
+ },
142
+ "modern:ntp": {
143
+ "path": "/content/corpus/modern/ntp/tachiwin.txt",
144
+ "bytes": 527751,
145
+ "sha256": "be450f93267e6832729154a9cec9a98af4eda30867d15a35b6118b054b56f625"
146
+ },
147
+ "modern:ocu": {
148
+ "path": "/content/corpus/modern/ocu/tachiwin.txt",
149
+ "bytes": 397733,
150
+ "sha256": "bb7f6b08a0911c8c220b1c9e0ac854cdb7a8ad6e9fa45adeb864e8fece657fce"
151
+ },
152
+ "modern:ots": {
153
+ "path": "/content/corpus/modern/ots/tachiwin.txt",
154
+ "bytes": 476148,
155
+ "sha256": "59d182297d6270dd4155fe594104f95d988382c4a1283b2e37ee9c89fe032976"
156
+ },
157
+ "modern:pei": {
158
+ "path": "/content/corpus/modern/pei/tachiwin.txt",
159
+ "bytes": 501655,
160
+ "sha256": "00efb09742356c78aa58b892d6e172d72ae9bd9c117b27e970ab046ab7601631"
161
+ },
162
+ "modern:pia": {
163
+ "path": "/content/corpus/modern/pia/tachiwin.txt",
164
+ "bytes": 334730,
165
+ "sha256": "4dea40a06452e8f3eb13f298a947919d90435a21e63f1c2d0ebd4be002a475d0"
166
+ },
167
+ "modern:pmq": {
168
+ "path": "/content/corpus/modern/pmq/tachiwin.txt",
169
+ "bytes": 509773,
170
+ "sha256": "a446ce67f08eec9f4ee5ecda0451e31e23f71288794fdd0df8c5a69bcff558dc"
171
+ },
172
+ "modern:poi": {
173
+ "path": "/content/corpus/modern/poi/tachiwin.txt",
174
+ "bytes": 708703,
175
+ "sha256": "2ce83d37a2a49a76aa399c7684be696266be542107004c8077a58ff942259b10"
176
+ },
177
+ "modern:pt-BR": {
178
+ "path": "/content/corpus/modern/pt-BR/tachiwin.txt",
179
+ "bytes": 633129,
180
+ "sha256": "399709d37d53154d1b6aef4cd0075f21a4c854c7a09ef6832252275d81bb5fce"
181
+ },
182
+ "modern:pua": {
183
+ "path": "/content/corpus/modern/pua/tachiwin.txt",
184
+ "bytes": 40741,
185
+ "sha256": "990576a76408391068f3804006e096ae85d829dc5752fb5a29a7d0ddbe85fa76"
186
+ },
187
+ "modern:quc": {
188
+ "path": "/content/corpus/modern/quc/tachiwin.txt",
189
+ "bytes": 62407,
190
+ "sha256": "86561c2c66dcb6884e742bde2d66b230011038111ca95755f3e45e95e823f0cd"
191
+ },
192
+ "modern:sei": {
193
+ "path": "/content/corpus/modern/sei/tachiwin.txt",
194
+ "bytes": 786940,
195
+ "sha256": "3f288232d531fd9f6f2df2a40a1edc19ce51d8f429b0c455677c776cd7ef57c5"
196
+ },
197
+ "modern:spa": {
198
+ "path": "/content/corpus/modern/spa/tachiwin.txt",
199
+ "bytes": 451611,
200
+ "sha256": "58f3dfd7104b4371657cff4303de50d0af490c4a7740378a80fd41c5bd33ba4e"
201
+ },
202
+ "modern:tar0": {
203
+ "path": "/content/corpus/modern/tar0/tachiwin.txt",
204
+ "bytes": 484648,
205
+ "sha256": "262eb606934c086d372fc447ee4f0d7c3c166578e4f3f1ca6fa634bccdd75fdb"
206
+ },
207
+ "modern:toj": {
208
+ "path": "/content/corpus/modern/toj/tachiwin.txt",
209
+ "bytes": 675870,
210
+ "sha256": "32aa2149e0711b964586018115cda8d4d144db5901776cc43f7df525d598b25e"
211
+ },
212
+ "modern:top": {
213
+ "path": "/content/corpus/modern/top/tachiwin.txt",
214
+ "bytes": 495877,
215
+ "sha256": "9b9801ccef1b7bb07c4fe51800357a5494aaf34eb67c0c3c7cb621ae28a0db18"
216
+ },
217
+ "modern:tpp": {
218
+ "path": "/content/corpus/modern/tpp/tachiwin.txt",
219
+ "bytes": 529336,
220
+ "sha256": "0e7b21a5c106bee19de4278e05cf7ea1bb5695c11dbd95e86ce59aa377666e1c"
221
+ },
222
+ "modern:tpx": {
223
+ "path": "/content/corpus/modern/tpx/tachiwin.txt",
224
+ "bytes": 439219,
225
+ "sha256": "9105b345db5959dd6205df7905ea82460ab220cf94822ecd6923c4694c8b0047"
226
+ },
227
+ "modern:trs": {
228
+ "path": "/content/corpus/modern/trs/tachiwin.txt",
229
+ "bytes": 1289319,
230
+ "sha256": "4b87b99fa626607936c0499a7b9e9e2a982eed514bd9b057d000e1e252a20e3d"
231
+ },
232
+ "modern:tsz": {
233
+ "path": "/content/corpus/modern/tsz/tachiwin.txt",
234
+ "bytes": 515044,
235
+ "sha256": "81a8789c22bd21a105843e1f295deac40f071520f3a021099f60dcb219a7d2cd"
236
+ },
237
+ "modern:tzh": {
238
+ "path": "/content/corpus/modern/tzh/tachiwin.txt",
239
+ "bytes": 531809,
240
+ "sha256": "973a8284eb75cb545442093318ca249d8257b53354d417d8609dfcb2ccbaed22"
241
+ },
242
+ "modern:tzo": {
243
+ "path": "/content/corpus/modern/tzo/tachiwin.txt",
244
+ "bytes": 587554,
245
+ "sha256": "b4d2dd95b805394f9b9bdc1481b01f183e6c57da27953f5b11c5f58b13313601"
246
+ },
247
+ "modern:unk": {
248
+ "path": "/content/corpus/modern/unk/tachiwin.txt",
249
+ "bytes": 472386,
250
+ "sha256": "c38d18fa4fa83d228f92f31f8166971c9d219e00981828d0f5a5b8228c6142d7"
251
+ },
252
+ "modern:var": {
253
+ "path": "/content/corpus/modern/var/tachiwin.txt",
254
+ "bytes": 35913,
255
+ "sha256": "924ccc91d299a1b0540fe745cdb3d851c96107c5838b3b34a5e8dddaa94d5cb4"
256
+ },
257
+ "modern:yaq": {
258
+ "path": "/content/corpus/modern/yaq/tachiwin.txt",
259
+ "bytes": 451003,
260
+ "sha256": "643755beeff11e468457877a825c8052f574165e264565d4a4bad1b680215b77"
261
+ },
262
+ "modern:yua": {
263
+ "path": "/content/corpus/modern/yua/tachiwin.txt",
264
+ "bytes": 692957,
265
+ "sha256": "80ecdfa0810f93efcfb5f4b86e9fa36e16f63c31fb139ab10f0b61ab8c637727"
266
+ },
267
+ "modern:zai": {
268
+ "path": "/content/corpus/modern/zai/tachiwin.txt",
269
+ "bytes": 515465,
270
+ "sha256": "ec49fd6fba6658480414a106d67e1fc5e70bfb2c5068cc434032565c1a8227da"
271
+ },
272
+ "modern:zam": {
273
+ "path": "/content/corpus/modern/zam/tachiwin.txt",
274
+ "bytes": 101201,
275
+ "sha256": "d16654f6dc4b520190d9973dd346c6bb7ae106d284fc4ddb6244367ffb906406"
276
+ },
277
+ "modern:zoc": {
278
+ "path": "/content/corpus/modern/zoc/tachiwin.txt",
279
+ "bytes": 40330,
280
+ "sha256": "02595710df6e4da5a2a6ec7c2abadeae1b3438c74c1685ac537b45dee90abf04"
281
+ },
282
+ "modern:zoq": {
283
+ "path": "/content/corpus/modern/zoq/tachiwin.txt",
284
+ "bytes": 363388,
285
+ "sha256": "b5e32794b718e64f059846694e060988a002d0144a9a3a56aa8903813f743a86"
286
+ },
287
+ "old:amu": {
288
+ "path": "/content/corpus/old/amu/tachiwin.txt",
289
+ "bytes": 1863269,
290
+ "sha256": "d23078a47b4e76ab6e476f302d409a5f8c01527dd396e0c827f268352ce269c1"
291
+ },
292
+ "old:azg": {
293
+ "path": "/content/corpus/old/azg/tachiwin.txt",
294
+ "bytes": 2092504,
295
+ "sha256": "03febf0a4bf4e0c03c689b8fafd2eac1647ba173fb992d02ba6658751739165b"
296
+ },
297
+ "old:azz": {
298
+ "path": "/content/corpus/old/azz/tachiwin.txt",
299
+ "bytes": 2025011,
300
+ "sha256": "f56a654debfae91a95e0fff31fae92f62200f6a353df49cd1d6683b3c5c6cc82"
301
+ },
302
+ "old:cco": {
303
+ "path": "/content/corpus/old/cco/tachiwin.txt",
304
+ "bytes": 2646127,
305
+ "sha256": "6c0f0fc456d5ddd66ab550747f50235fd373c5367a9b8a850ac01a181c836bd0"
306
+ },
307
+ "old:chd": {
308
+ "path": "/content/corpus/old/chd/tachiwin.txt",
309
+ "bytes": 1466443,
310
+ "sha256": "41f7c3f9b38ccffa8333215898de71ec8e07ff7f9ac72b651c17b56c0c3668a0"
311
+ },
312
+ "old:chq": {
313
+ "path": "/content/corpus/old/chq/tachiwin.txt",
314
+ "bytes": 1530589,
315
+ "sha256": "c3d48a74c5e953eb61307e4a1bf4096f57e77f994acd5ec5055c9a6dc8de5357"
316
+ },
317
+ "old:cle": {
318
+ "path": "/content/corpus/old/cle/tachiwin.txt",
319
+ "bytes": 2206770,
320
+ "sha256": "3fc084e9d70ee12033cc8b710e8749b09065bb52767e064ae5ef85f3a5131c0b"
321
+ },
322
+ "old:cnl": {
323
+ "path": "/content/corpus/old/cnl/tachiwin.txt",
324
+ "bytes": 2215651,
325
+ "sha256": "7f5dc76ff022c0b7b21e72a9345f9036fc4f9aea2e995f51da0eab2c44d92a7c"
326
+ },
327
+ "old:cnt": {
328
+ "path": "/content/corpus/old/cnt/tachiwin.txt",
329
+ "bytes": 2012833,
330
+ "sha256": "2ae45e0087d10a81a719f2e1ee4f7cd4466935780b73dccd862869dd4ce08de3"
331
+ },
332
+ "old:cpa": {
333
+ "path": "/content/corpus/old/cpa/tachiwin.txt",
334
+ "bytes": 203169,
335
+ "sha256": "f20796aced08743afbceb4d3a5e0179960dfb876eba3d20ea5988d6b7915add1"
336
+ },
337
+ "eng": {
338
+ "path": "/content/corpus/eng/shard_000.txt",
339
+ "bytes": 6179346,
340
+ "sha256": "8ad9bbba4350b33ee93eb134ac02f1591b90b84fb3728c10ac26c933591e9c58"
341
+ },
342
+ "spa": {
343
+ "path": "/content/corpus/spa/shard_000.txt",
344
+ "bytes": 6179623,
345
+ "sha256": "ec775933644605505585ad3dafe87773f43f55e022e76faad591d471a850128e"
346
+ },
347
+ "code": {
348
+ "path": "/content/corpus/code/shard_000.txt",
349
+ "bytes": 6157024,
350
+ "sha256": "cbc011d5d675f4dd9727d51f7367c12bdb38ebedca21d62a2c6f293ae2b474d2"
351
+ }
352
+ }