Hugging Face's logo

spacy
/
da_core_news_md

Token Classification
spaCy
Danish
Eval Results
Model card Files Community
adrianeboyd commited on
Commit
5c06770
•
1 Parent(s): 2230db5

Update spaCy pipeline

Browse files
Files changed (14) hide show
  1. README.md +28 -28
  2. accuracy.json +157 -157
  3. attribute_ruler/patterns +0 -0
  4. config.cfg +5 -4
  5. da_core_news_md-any-py3-none-any.whl +2 -2
  6. lemmatizer/model +1 -1
  7. meta.json +160 -160
  8. morphologizer/model +1 -1
  9. ner/model +2 -2
  10. parser/model +1 -1
  11. senter/model +1 -1
  12. tok2vec/model +2 -2
  13. tokenizer +0 -0
  14. vocab/strings.json +2 -2
README.md CHANGED
@@ -14,62 +14,62 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8063829787
18
  - name: NER Recall
19
  type: recall
20
- value: 0.7895833333
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.7978947368
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9618401937
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9618401937
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
- value: 0.948377724
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 0.9497336562
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.8215642458
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.7802234637
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9103942652
73
  ---
74
  ### Details: https://spacy.io/models/da#da_core_news_md
75
 
@@ -78,8 +78,8 @@ Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `da_core_news_md` |
81
- | **Version** | `3.4.0` |
82
- | **spaCy** | `>=3.4.0,<3.5.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
@@ -105,22 +105,22 @@ Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
105
 
106
  | Type | Score |
107
  | --- | --- |
108
- | `TOKEN_ACC` | 99.95 |
109
  | `TOKEN_P` | 99.78 |
110
  | `TOKEN_R` | 99.75 |
111
  | `TOKEN_F` | 99.76 |
112
- | `POS_ACC` | 96.18 |
113
- | `MORPH_ACC` | 94.84 |
114
- | `MORPH_MICRO_P` | 96.75 |
115
- | `MORPH_MICRO_R` | 96.22 |
116
- | `MORPH_MICRO_F` | 96.49 |
117
- | `SENTS_P` | 92.03 |
118
- | `SENTS_R` | 90.07 |
119
- | `SENTS_F` | 91.04 |
120
- | `DEP_UAS` | 82.16 |
121
- | `DEP_LAS` | 78.02 |
122
- | `LEMMA_ACC` | 94.97 |
123
- | `TAG_ACC` | 96.18 |
124
- | `ENTS_P` | 80.64 |
125
- | `ENTS_R` | 78.96 |
126
- | `ENTS_F` | 79.79 |
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8020833333
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.8020833333
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8020833333
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9634866828
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9634866828
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
+ value: 0.9515738499
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9476997579
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.8226680825
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.7821616184
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9056603774
73
  ---
74
  ### Details: https://spacy.io/models/da#da_core_news_md
75
 
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `da_core_news_md` |
81
+ | **Version** | `3.5.0` |
82
+ | **spaCy** | `>=3.5.0,<3.6.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
 
105
 
106
  | Type | Score |
107
  | --- | --- |
108
+ | `TOKEN_ACC` | 99.89 |
109
  | `TOKEN_P` | 99.78 |
110
  | `TOKEN_R` | 99.75 |
111
  | `TOKEN_F` | 99.76 |
112
+ | `POS_ACC` | 96.35 |
113
+ | `MORPH_ACC` | 95.16 |
114
+ | `MORPH_MICRO_P` | 96.91 |
115
+ | `MORPH_MICRO_R` | 96.34 |
116
+ | `MORPH_MICRO_F` | 96.62 |
117
+ | `SENTS_P` | 91.80 |
118
+ | `SENTS_R` | 89.36 |
119
+ | `SENTS_F` | 90.57 |
120
+ | `DEP_UAS` | 82.27 |
121
+ | `DEP_LAS` | 78.22 |
122
+ | `LEMMA_ACC` | 94.77 |
123
+ | `TAG_ACC` | 96.35 |
124
+ | `ENTS_P` | 80.21 |
125
+ | `ENTS_R` | 80.21 |
126
+ | `ENTS_F` | 80.21 |
accuracy.json CHANGED
@@ -1,53 +1,53 @@
1
  {
2
- "token_acc": 0.9994672349,
3
  "token_p": 0.9977732598,
4
  "token_r": 0.9974835463,
5
  "token_f": 0.997628382,
6
- "pos_acc": 0.9618401937,
7
- "morph_acc": 0.948377724,
8
- "morph_micro_p": 0.9675176369,
9
- "morph_micro_r": 0.9622431982,
10
- "morph_micro_f": 0.9648732095,
11
  "morph_per_feat": {
12
  "Mood": {
13
- "p": 0.9799235182,
14
- "r": 0.9771210677,
15
- "f": 0.9785202864
16
  },
17
  "Tense": {
18
- "p": 0.9743396226,
19
- "r": 0.9721385542,
20
- "f": 0.973237844
21
  },
22
  "VerbForm": {
23
- "p": 0.9643953346,
24
- "r": 0.9614443084,
25
- "f": 0.9629175605
26
  },
27
  "Voice": {
28
- "p": 0.976083707,
29
- "r": 0.976083707,
30
- "f": 0.976083707
31
  },
32
  "Definite": {
33
- "p": 0.9622716442,
34
- "r": 0.9573291189,
35
- "f": 0.9597940186
36
  },
37
  "Gender": {
38
- "p": 0.9466310874,
39
- "r": 0.9431704885,
40
- "f": 0.9448976194
41
  },
42
  "Number": {
43
- "p": 0.9613361389,
44
- "r": 0.9533124674,
45
- "f": 0.9573074908
46
  },
47
  "AdpType": {
48
- "p": 0.9982206406,
49
- "r": 0.9920424403,
50
- "f": 0.9951219512
51
  },
52
  "PartType": {
53
  "p": 1.0,
@@ -55,29 +55,29 @@
55
  "f": 1.0
56
  },
57
  "Case": {
58
- "p": 0.9741935484,
59
- "r": 0.9541864139,
60
- "f": 0.9640861931
61
  },
62
  "Person": {
63
- "p": 0.9788732394,
64
  "r": 0.9875666075,
65
- "f": 0.9832007073
66
  },
67
  "PronType": {
68
- "p": 0.9860197368,
69
- "r": 0.9860197368,
70
- "f": 0.9860197368
71
  },
72
  "NumType": {
73
- "p": 0.9931034483,
74
  "r": 0.9536423841,
75
- "f": 0.972972973
76
  },
77
  "Degree": {
78
- "p": 0.9545454545,
79
  "r": 0.9361445783,
80
- "f": 0.9452554745
81
  },
82
  "Reflex": {
83
  "p": 1.0,
@@ -85,19 +85,19 @@
85
  "f": 1.0
86
  },
87
  "Number[psor]": {
88
- "p": 0.9772727273,
89
  "r": 1.0,
90
- "f": 0.9885057471
91
  },
92
  "Poss": {
93
- "p": 0.9887640449,
94
  "r": 1.0,
95
- "f": 0.9943502825
96
  },
97
  "Foreign": {
98
- "p": 0.5,
99
  "r": 0.4,
100
- "f": 0.4444444444
101
  },
102
  "Abbr": {
103
  "p": 0.0,
@@ -115,141 +115,141 @@
115
  "f": 0.75
116
  }
117
  },
118
- "sents_p": 0.9202898551,
119
- "sents_r": 0.9007092199,
120
- "sents_f": 0.9103942652,
121
- "dep_uas": 0.8215642458,
122
- "dep_las": 0.7802234637,
123
  "dep_las_per_type": {
124
  "advmod": {
125
- "p": 0.7128851541,
126
- "r": 0.7189265537,
127
- "f": 0.7158931083
128
  },
129
  "root": {
130
- "p": 0.8483754513,
131
- "r": 0.8333333333,
132
- "f": 0.8407871199
133
  },
134
  "nsubj": {
135
- "p": 0.8333333333,
136
- "r": 0.8333333333,
137
- "f": 0.8333333333
138
  },
139
  "case": {
140
- "p": 0.8933859822,
141
- "r": 0.892504931,
142
- "f": 0.8929452393
143
  },
144
  "obl": {
145
- "p": 0.6905901116,
146
- "r": 0.6723602484,
147
- "f": 0.6813532651
148
  },
149
  "cc": {
150
- "p": 0.7803468208,
151
- "r": 0.7848837209,
152
- "f": 0.7826086957
153
  },
154
  "conj": {
155
- "p": 0.6422764228,
156
- "r": 0.632,
157
- "f": 0.6370967742
158
  },
159
  "obj": {
160
- "p": 0.7892791128,
161
- "r": 0.8291262136,
162
- "f": 0.8087121212
163
  },
164
  "aux": {
165
- "p": 0.8858858859,
166
- "r": 0.860058309,
167
- "f": 0.8727810651
168
  },
169
  "acl:relcl": {
170
- "p": 0.5837837838,
171
- "r": 0.5837837838,
172
- "f": 0.5837837838
173
  },
174
  "advmod:lmod": {
175
- "p": 0.7164179104,
176
- "r": 0.7164179104,
177
- "f": 0.7164179104
178
  },
179
  "det": {
180
- "p": 0.9126853377,
181
- "r": 0.9126853377,
182
- "f": 0.9126853377
183
  },
184
  "amod": {
185
- "p": 0.8155668359,
186
- "r": 0.8225255973,
187
- "f": 0.8190314359
188
  },
189
  "nmod:poss": {
190
- "p": 0.6730769231,
191
- "r": 0.6930693069,
192
- "f": 0.6829268293
193
  },
194
  "ccomp": {
195
- "p": 0.5967741935,
196
- "r": 0.5967741935,
197
- "f": 0.5967741935
198
  },
199
  "nummod": {
200
- "p": 0.8416666667,
201
- "r": 0.8416666667,
202
- "f": 0.8416666667
203
  },
204
  "flat": {
205
- "p": 0.765060241,
206
- "r": 0.8410596026,
207
- "f": 0.8012618297
208
  },
209
  "compound:prt": {
210
- "p": 0.625,
211
- "r": 0.3658536585,
212
- "f": 0.4615384615
213
  },
214
  "advcl": {
215
- "p": 0.6126126126,
216
- "r": 0.5862068966,
217
- "f": 0.5991189427
218
  },
219
  "mark": {
220
- "p": 0.8553719008,
221
- "r": 0.8501026694,
222
- "f": 0.8527291452
223
  },
224
  "cop": {
225
- "p": 0.825136612,
226
- "r": 0.8628571429,
227
- "f": 0.843575419
228
  },
229
  "dep": {
230
- "p": 0.1875,
231
- "r": 0.2830188679,
232
- "f": 0.2255639098
233
  },
234
  "nmod": {
235
- "p": 0.6581532417,
236
- "r": 0.654296875,
237
- "f": 0.6562193928
238
  },
239
  "iobj": {
240
- "p": 0.7692307692,
241
- "r": 0.4545454545,
242
- "f": 0.5714285714
243
  },
244
  "xcomp": {
245
- "p": 0.4705882353,
246
- "r": 0.406779661,
247
- "f": 0.4363636364
248
  },
249
  "list": {
250
- "p": 0.4615384615,
251
- "r": 0.3333333333,
252
- "f": 0.3870967742
253
  },
254
  "vocative": {
255
  "p": 0.0,
@@ -257,56 +257,56 @@
257
  "f": 0.0
258
  },
259
  "fixed": {
260
- "p": 0.9166666667,
261
  "r": 0.8048780488,
262
- "f": 0.8571428571
263
  },
264
  "expl": {
265
- "p": 0.8,
266
  "r": 0.8235294118,
267
- "f": 0.8115942029
268
  },
269
  "appos": {
270
- "p": 0.4166666667,
271
- "r": 0.4545454545,
272
- "f": 0.4347826087
273
  },
274
  "obl:tmod": {
275
- "p": 0.75,
276
- "r": 0.3333333333,
277
- "f": 0.4615384615
278
  },
279
- "discourse": {
280
  "p": 0.0,
281
  "r": 0.0,
282
  "f": 0.0
283
  },
284
- "obl:lmod": {
285
  "p": 0.0,
286
  "r": 0.0,
287
  "f": 0.0
288
  }
289
  },
290
- "lemma_acc": 0.9497336562,
291
- "tag_acc": 0.9618401937,
292
- "ents_p": 0.8063829787,
293
- "ents_r": 0.7895833333,
294
- "ents_f": 0.7978947368,
295
  "ents_per_type": {
296
  "PER": {
297
- "p": 0.8924050633,
298
- "r": 0.8493975904,
299
- "f": 0.8703703704
300
  },
301
  "ORG": {
302
- "p": 0.7073170732,
303
- "r": 0.6444444444,
304
- "f": 0.6744186047
305
  },
306
  "MISC": {
307
- "p": 0.7142857143,
308
  "r": 0.7079646018,
309
- "f": 0.7111111111
310
  },
311
  "LOC": {
312
  "p": 0.8474576271,
@@ -314,5 +314,5 @@
314
  "f": 0.8733624454
315
  }
316
  },
317
- "speed": 12214.1305450038
318
  }
 
1
  {
2
+ "token_acc": 0.9989350373,
3
  "token_p": 0.9977732598,
4
  "token_r": 0.9974835463,
5
  "token_f": 0.997628382,
6
+ "pos_acc": 0.9634866828,
7
+ "morph_acc": 0.9515738499,
8
+ "morph_micro_p": 0.9690784463,
9
+ "morph_micro_r": 0.9634041694,
10
+ "morph_micro_f": 0.9662329773,
11
  "morph_per_feat": {
12
  "Mood": {
13
+ "p": 0.9826923077,
14
+ "r": 0.9742612011,
15
+ "f": 0.9784585926
16
  },
17
  "Tense": {
18
+ "p": 0.9704992436,
19
+ "r": 0.9661144578,
20
+ "f": 0.9683018868
21
  },
22
  "VerbForm": {
23
+ "p": 0.9661330049,
24
+ "r": 0.9602203182,
25
+ "f": 0.9631675875
26
  },
27
  "Voice": {
28
+ "p": 0.9834586466,
29
+ "r": 0.9775784753,
30
+ "f": 0.9805097451
31
  },
32
  "Definite": {
33
+ "p": 0.9639175258,
34
+ "r": 0.9604899249,
35
+ "f": 0.9622006729
36
  },
37
  "Gender": {
38
+ "p": 0.9516505502,
39
+ "r": 0.9484878697,
40
+ "f": 0.9500665779
41
  },
42
  "Number": {
43
+ "p": 0.9599056604,
44
+ "r": 0.955399061,
45
+ "f": 0.9576470588
46
  },
47
  "AdpType": {
48
+ "p": 0.9991087344,
49
+ "r": 0.991158267,
50
+ "f": 0.9951176209
51
  },
52
  "PartType": {
53
  "p": 1.0,
 
55
  "f": 1.0
56
  },
57
  "Case": {
58
+ "p": 0.9774919614,
59
+ "r": 0.9605055292,
60
+ "f": 0.9689243028
61
  },
62
  "Person": {
63
+ "p": 0.9805996473,
64
  "r": 0.9875666075,
65
+ "f": 0.9840707965
66
  },
67
  "PronType": {
68
+ "p": 0.9876339654,
69
+ "r": 0.9851973684,
70
+ "f": 0.9864141622
71
  },
72
  "NumType": {
73
+ "p": 0.972972973,
74
  "r": 0.9536423841,
75
+ "f": 0.9632107023
76
  },
77
  "Degree": {
78
+ "p": 0.9533742331,
79
  "r": 0.9361445783,
80
+ "f": 0.9446808511
81
  },
82
  "Reflex": {
83
  "p": 1.0,
 
85
  "f": 1.0
86
  },
87
  "Number[psor]": {
88
+ "p": 0.9885057471,
89
  "r": 1.0,
90
+ "f": 0.9942196532
91
  },
92
  "Poss": {
93
+ "p": 1.0,
94
  "r": 1.0,
95
+ "f": 1.0
96
  },
97
  "Foreign": {
98
+ "p": 0.8,
99
  "r": 0.4,
100
+ "f": 0.5333333333
101
  },
102
  "Abbr": {
103
  "p": 0.0,
 
115
  "f": 0.75
116
  }
117
  },
118
+ "sents_p": 0.9180327869,
119
+ "sents_r": 0.8936170213,
120
+ "sents_f": 0.9056603774,
121
+ "dep_uas": 0.8226680825,
122
+ "dep_las": 0.7821616184,
123
  "dep_las_per_type": {
124
  "advmod": {
125
+ "p": 0.702739726,
126
+ "r": 0.7245762712,
127
+ "f": 0.7134909597
128
  },
129
  "root": {
130
+ "p": 0.8519195612,
131
+ "r": 0.8262411348,
132
+ "f": 0.8388838884
133
  },
134
  "nsubj": {
135
+ "p": 0.8474576271,
136
+ "r": 0.8438818565,
137
+ "f": 0.8456659619
138
  },
139
  "case": {
140
+ "p": 0.8813229572,
141
+ "r": 0.8934911243,
142
+ "f": 0.8873653281
143
  },
144
  "obl": {
145
+ "p": 0.7200647249,
146
+ "r": 0.6909937888,
147
+ "f": 0.705229794
148
  },
149
  "cc": {
150
+ "p": 0.7608069164,
151
+ "r": 0.7674418605,
152
+ "f": 0.7641099855
153
  },
154
  "conj": {
155
+ "p": 0.624,
156
+ "r": 0.624,
157
+ "f": 0.624
158
  },
159
  "obj": {
160
+ "p": 0.802946593,
161
+ "r": 0.8466019417,
162
+ "f": 0.8241965974
163
  },
164
  "aux": {
165
+ "p": 0.8869047619,
166
+ "r": 0.8688046647,
167
+ "f": 0.8777614138
168
  },
169
  "acl:relcl": {
170
+ "p": 0.5872093023,
171
+ "r": 0.5459459459,
172
+ "f": 0.5658263305
173
  },
174
  "advmod:lmod": {
175
+ "p": 0.7704918033,
176
+ "r": 0.7014925373,
177
+ "f": 0.734375
178
  },
179
  "det": {
180
+ "p": 0.9161184211,
181
+ "r": 0.9176276771,
182
+ "f": 0.916872428
183
  },
184
  "amod": {
185
+ "p": 0.8010033445,
186
+ "r": 0.8174061433,
187
+ "f": 0.8091216216
188
  },
189
  "nmod:poss": {
190
+ "p": 0.619047619,
191
+ "r": 0.6435643564,
192
+ "f": 0.6310679612
193
  },
194
  "ccomp": {
195
+ "p": 0.6417910448,
196
+ "r": 0.6935483871,
197
+ "f": 0.6666666667
198
  },
199
  "nummod": {
200
+ "p": 0.8571428571,
201
+ "r": 0.85,
202
+ "f": 0.8535564854
203
  },
204
  "flat": {
205
+ "p": 0.7962962963,
206
+ "r": 0.8543046358,
207
+ "f": 0.8242811502
208
  },
209
  "compound:prt": {
210
+ "p": 0.5517241379,
211
+ "r": 0.3902439024,
212
+ "f": 0.4571428571
213
  },
214
  "advcl": {
215
+ "p": 0.6666666667,
216
+ "r": 0.6724137931,
217
+ "f": 0.669527897
218
  },
219
  "mark": {
220
+ "p": 0.885106383,
221
+ "r": 0.8542094456,
222
+ "f": 0.8693834901
223
  },
224
  "cop": {
225
+ "p": 0.8,
226
+ "r": 0.8457142857,
227
+ "f": 0.8222222222
228
  },
229
  "dep": {
230
+ "p": 0.175,
231
+ "r": 0.2641509434,
232
+ "f": 0.2105263158
233
  },
234
  "nmod": {
235
+ "p": 0.6332665331,
236
+ "r": 0.6171875,
237
+ "f": 0.62512364
238
  },
239
  "iobj": {
240
+ "p": 0.9166666667,
241
+ "r": 0.5,
242
+ "f": 0.6470588235
243
  },
244
  "xcomp": {
245
+ "p": 0.5555555556,
246
+ "r": 0.3389830508,
247
+ "f": 0.4210526316
248
  },
249
  "list": {
250
+ "p": 0.3333333333,
251
+ "r": 0.2777777778,
252
+ "f": 0.303030303
253
  },
254
  "vocative": {
255
  "p": 0.0,
 
257
  "f": 0.0
258
  },
259
  "fixed": {
260
+ "p": 0.8684210526,
261
  "r": 0.8048780488,
262
+ "f": 0.835443038
263
  },
264
  "expl": {
265
+ "p": 0.8484848485,
266
  "r": 0.8235294118,
267
+ "f": 0.8358208955
268
  },
269
  "appos": {
270
+ "p": 0.5405405405,
271
+ "r": 0.6060606061,
272
+ "f": 0.5714285714
273
  },
274
  "obl:tmod": {
275
+ "p": 0.8888888889,
276
+ "r": 0.4444444444,
277
+ "f": 0.5925925926
278
  },
279
+ "obl:lmod": {
280
  "p": 0.0,
281
  "r": 0.0,
282
  "f": 0.0
283
  },
284
+ "discourse": {
285
  "p": 0.0,
286
  "r": 0.0,
287
  "f": 0.0
288
  }
289
  },
290
+ "lemma_acc": 0.9476997579,
291
+ "tag_acc": 0.9634866828,
292
+ "ents_p": 0.8020833333,
293
+ "ents_r": 0.8020833333,
294
+ "ents_f": 0.8020833333,
295
  "ents_per_type": {
296
  "PER": {
297
+ "p": 0.9,
298
+ "r": 0.8674698795,
299
+ "f": 0.8834355828
300
  },
301
  "ORG": {
302
+ "p": 0.7011494253,
303
+ "r": 0.6777777778,
304
+ "f": 0.6892655367
305
  },
306
  "MISC": {
307
+ "p": 0.6956521739,
308
  "r": 0.7079646018,
309
+ "f": 0.701754386
310
  },
311
  "LOC": {
312
  "p": 0.8474576271,
 
314
  "f": 0.8733624454
315
  }
316
  },
317
+ "speed": 12067.6587888281
318
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -81,8 +81,8 @@ nO = null
81
  [components.ner.model.tok2vec.embed]
82
  @architectures = "spacy.MultiHashEmbed.v2"
83
  width = 96
84
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
85
- rows = [5000,1000,2500,2500,50]
86
  include_static_vectors = true
87
 
88
  [components.ner.model.tok2vec.encode]
@@ -150,8 +150,8 @@ factory = "tok2vec"
150
  [components.tok2vec.model.embed]
151
  @architectures = "spacy.MultiHashEmbed.v2"
152
  width = ${components.tok2vec.model.encode:width}
153
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
154
- rows = [5000,1000,2500,2500,50]
155
  include_static_vectors = true
156
 
157
  [components.tok2vec.model.encode]
@@ -193,6 +193,7 @@ eval_frequency = 1000
193
  frozen_components = []
194
  before_to_disk = null
195
  annotating_components = []
 
196
 
197
  [training.batcher]
198
  @batchers = "spacy.batch_by_words.v1"
 
81
  [components.ner.model.tok2vec.embed]
82
  @architectures = "spacy.MultiHashEmbed.v2"
83
  width = 96
84
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
85
+ rows = [5000,1000,2500,2500]
86
  include_static_vectors = true
87
 
88
  [components.ner.model.tok2vec.encode]
 
150
  [components.tok2vec.model.embed]
151
  @architectures = "spacy.MultiHashEmbed.v2"
152
  width = ${components.tok2vec.model.encode:width}
153
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
154
+ rows = [5000,1000,2500,2500,50,50]
155
  include_static_vectors = true
156
 
157
  [components.tok2vec.model.encode]
 
193
  frozen_components = []
194
  before_to_disk = null
195
  annotating_components = []
196
+ before_update = null
197
 
198
  [training.batcher]
199
  @batchers = "spacy.batch_by_words.v1"
da_core_news_md-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ab33cc4d15f68126d012a01c972736fd789a76a7ade79425877a58f9f10797a
3
- size 42193115
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ababcf3d420d49c037c665447567532fde6f6f392d79c180c0220b685256d4
3
+ size 42207007
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:356c369c9c50b0510e9dfab74689db20b2e0cb65718095e901e600f4d74aa9b0
3
  size 175818
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7622f71d40d8eff5dea9672f0ed57d9bd57eb56a7658999b1989a8fbc1d7bfd2
3
  size 175818
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"da",
3
  "name":"core_news_md",
4
- "version":"3.4.0",
5
  "description":"Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"CC BY-SA 4.0",
10
- "spacy_version":">=3.4.0,<3.5.0",
11
- "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
@@ -244,55 +244,55 @@
244
  "senter"
245
  ],
246
  "performance":{
247
- "token_acc":0.9994672349,
248
  "token_p":0.9977732598,
249
  "token_r":0.9974835463,
250
  "token_f":0.997628382,
251
- "pos_acc":0.9618401937,
252
- "morph_acc":0.948377724,
253
- "morph_micro_p":0.9675176369,
254
- "morph_micro_r":0.9622431982,
255
- "morph_micro_f":0.9648732095,
256
  "morph_per_feat":{
257
  "Mood":{
258
- "p":0.9799235182,
259
- "r":0.9771210677,
260
- "f":0.9785202864
261
  },
262
  "Tense":{
263
- "p":0.9743396226,
264
- "r":0.9721385542,
265
- "f":0.973237844
266
  },
267
  "VerbForm":{
268
- "p":0.9643953346,
269
- "r":0.9614443084,
270
- "f":0.9629175605
271
  },
272
  "Voice":{
273
- "p":0.976083707,
274
- "r":0.976083707,
275
- "f":0.976083707
276
  },
277
  "Definite":{
278
- "p":0.9622716442,
279
- "r":0.9573291189,
280
- "f":0.9597940186
281
  },
282
  "Gender":{
283
- "p":0.9466310874,
284
- "r":0.9431704885,
285
- "f":0.9448976194
286
  },
287
  "Number":{
288
- "p":0.9613361389,
289
- "r":0.9533124674,
290
- "f":0.9573074908
291
  },
292
  "AdpType":{
293
- "p":0.9982206406,
294
- "r":0.9920424403,
295
- "f":0.9951219512
296
  },
297
  "PartType":{
298
  "p":1.0,
@@ -300,29 +300,29 @@
300
  "f":1.0
301
  },
302
  "Case":{
303
- "p":0.9741935484,
304
- "r":0.9541864139,
305
- "f":0.9640861931
306
  },
307
  "Person":{
308
- "p":0.9788732394,
309
  "r":0.9875666075,
310
- "f":0.9832007073
311
  },
312
  "PronType":{
313
- "p":0.9860197368,
314
- "r":0.9860197368,
315
- "f":0.9860197368
316
  },
317
  "NumType":{
318
- "p":0.9931034483,
319
  "r":0.9536423841,
320
- "f":0.972972973
321
  },
322
  "Degree":{
323
- "p":0.9545454545,
324
  "r":0.9361445783,
325
- "f":0.9452554745
326
  },
327
  "Reflex":{
328
  "p":1.0,
@@ -330,19 +330,19 @@
330
  "f":1.0
331
  },
332
  "Number[psor]":{
333
- "p":0.9772727273,
334
  "r":1.0,
335
- "f":0.9885057471
336
  },
337
  "Poss":{
338
- "p":0.9887640449,
339
  "r":1.0,
340
- "f":0.9943502825
341
  },
342
  "Foreign":{
343
- "p":0.5,
344
  "r":0.4,
345
- "f":0.4444444444
346
  },
347
  "Abbr":{
348
  "p":0.0,
@@ -360,141 +360,141 @@
360
  "f":0.75
361
  }
362
  },
363
- "sents_p":0.9202898551,
364
- "sents_r":0.9007092199,
365
- "sents_f":0.9103942652,
366
- "dep_uas":0.8215642458,
367
- "dep_las":0.7802234637,
368
  "dep_las_per_type":{
369
  "advmod":{
370
- "p":0.7128851541,
371
- "r":0.7189265537,
372
- "f":0.7158931083
373
  },
374
  "root":{
375
- "p":0.8483754513,
376
- "r":0.8333333333,
377
- "f":0.8407871199
378
  },
379
  "nsubj":{
380
- "p":0.8333333333,
381
- "r":0.8333333333,
382
- "f":0.8333333333
383
  },
384
  "case":{
385
- "p":0.8933859822,
386
- "r":0.892504931,
387
- "f":0.8929452393
388
  },
389
  "obl":{
390
- "p":0.6905901116,
391
- "r":0.6723602484,
392
- "f":0.6813532651
393
  },
394
  "cc":{
395
- "p":0.7803468208,
396
- "r":0.7848837209,
397
- "f":0.7826086957
398
  },
399
  "conj":{
400
- "p":0.6422764228,
401
- "r":0.632,
402
- "f":0.6370967742
403
  },
404
  "obj":{
405
- "p":0.7892791128,
406
- "r":0.8291262136,
407
- "f":0.8087121212
408
  },
409
  "aux":{
410
- "p":0.8858858859,
411
- "r":0.860058309,
412
- "f":0.8727810651
413
  },
414
  "acl:relcl":{
415
- "p":0.5837837838,
416
- "r":0.5837837838,
417
- "f":0.5837837838
418
  },
419
  "advmod:lmod":{
420
- "p":0.7164179104,
421
- "r":0.7164179104,
422
- "f":0.7164179104
423
  },
424
  "det":{
425
- "p":0.9126853377,
426
- "r":0.9126853377,
427
- "f":0.9126853377
428
  },
429
  "amod":{
430
- "p":0.8155668359,
431
- "r":0.8225255973,
432
- "f":0.8190314359
433
  },
434
  "nmod:poss":{
435
- "p":0.6730769231,
436
- "r":0.6930693069,
437
- "f":0.6829268293
438
  },
439
  "ccomp":{
440
- "p":0.5967741935,
441
- "r":0.5967741935,
442
- "f":0.5967741935
443
  },
444
  "nummod":{
445
- "p":0.8416666667,
446
- "r":0.8416666667,
447
- "f":0.8416666667
448
  },
449
  "flat":{
450
- "p":0.765060241,
451
- "r":0.8410596026,
452
- "f":0.8012618297
453
  },
454
  "compound:prt":{
455
- "p":0.625,
456
- "r":0.3658536585,
457
- "f":0.4615384615
458
  },
459
  "advcl":{
460
- "p":0.6126126126,
461
- "r":0.5862068966,
462
- "f":0.5991189427
463
  },
464
  "mark":{
465
- "p":0.8553719008,
466
- "r":0.8501026694,
467
- "f":0.8527291452
468
  },
469
  "cop":{
470
- "p":0.825136612,
471
- "r":0.8628571429,
472
- "f":0.843575419
473
  },
474
  "dep":{
475
- "p":0.1875,
476
- "r":0.2830188679,
477
- "f":0.2255639098
478
  },
479
  "nmod":{
480
- "p":0.6581532417,
481
- "r":0.654296875,
482
- "f":0.6562193928
483
  },
484
  "iobj":{
485
- "p":0.7692307692,
486
- "r":0.4545454545,
487
- "f":0.5714285714
488
  },
489
  "xcomp":{
490
- "p":0.4705882353,
491
- "r":0.406779661,
492
- "f":0.4363636364
493
  },
494
  "list":{
495
- "p":0.4615384615,
496
- "r":0.3333333333,
497
- "f":0.3870967742
498
  },
499
  "vocative":{
500
  "p":0.0,
@@ -502,56 +502,56 @@
502
  "f":0.0
503
  },
504
  "fixed":{
505
- "p":0.9166666667,
506
  "r":0.8048780488,
507
- "f":0.8571428571
508
  },
509
  "expl":{
510
- "p":0.8,
511
  "r":0.8235294118,
512
- "f":0.8115942029
513
  },
514
  "appos":{
515
- "p":0.4166666667,
516
- "r":0.4545454545,
517
- "f":0.4347826087
518
  },
519
  "obl:tmod":{
520
- "p":0.75,
521
- "r":0.3333333333,
522
- "f":0.4615384615
523
  },
524
- "discourse":{
525
  "p":0.0,
526
  "r":0.0,
527
  "f":0.0
528
  },
529
- "obl:lmod":{
530
  "p":0.0,
531
  "r":0.0,
532
  "f":0.0
533
  }
534
  },
535
- "lemma_acc":0.9497336562,
536
- "tag_acc":0.9618401937,
537
- "ents_p":0.8063829787,
538
- "ents_r":0.7895833333,
539
- "ents_f":0.7978947368,
540
  "ents_per_type":{
541
  "PER":{
542
- "p":0.8924050633,
543
- "r":0.8493975904,
544
- "f":0.8703703704
545
  },
546
  "ORG":{
547
- "p":0.7073170732,
548
- "r":0.6444444444,
549
- "f":0.6744186047
550
  },
551
  "MISC":{
552
- "p":0.7142857143,
553
  "r":0.7079646018,
554
- "f":0.7111111111
555
  },
556
  "LOC":{
557
  "p":0.8474576271,
@@ -559,7 +559,7 @@
559
  "f":0.8733624454
560
  }
561
  },
562
- "speed":12214.1305450038
563
  },
564
  "sources":[
565
  {
 
1
  {
2
  "lang":"da",
3
  "name":"core_news_md",
4
+ "version":"3.5.0",
5
  "description":"Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"CC BY-SA 4.0",
10
+ "spacy_version":">=3.5.0,<3.6.0",
11
+ "spacy_git_version":"9e0322de1",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
 
244
  "senter"
245
  ],
246
  "performance":{
247
+ "token_acc":0.9989350373,
248
  "token_p":0.9977732598,
249
  "token_r":0.9974835463,
250
  "token_f":0.997628382,
251
+ "pos_acc":0.9634866828,
252
+ "morph_acc":0.9515738499,
253
+ "morph_micro_p":0.9690784463,
254
+ "morph_micro_r":0.9634041694,
255
+ "morph_micro_f":0.9662329773,
256
  "morph_per_feat":{
257
  "Mood":{
258
+ "p":0.9826923077,
259
+ "r":0.9742612011,
260
+ "f":0.9784585926
261
  },
262
  "Tense":{
263
+ "p":0.9704992436,
264
+ "r":0.9661144578,
265
+ "f":0.9683018868
266
  },
267
  "VerbForm":{
268
+ "p":0.9661330049,
269
+ "r":0.9602203182,
270
+ "f":0.9631675875
271
  },
272
  "Voice":{
273
+ "p":0.9834586466,
274
+ "r":0.9775784753,
275
+ "f":0.9805097451
276
  },
277
  "Definite":{
278
+ "p":0.9639175258,
279
+ "r":0.9604899249,
280
+ "f":0.9622006729
281
  },
282
  "Gender":{
283
+ "p":0.9516505502,
284
+ "r":0.9484878697,
285
+ "f":0.9500665779
286
  },
287
  "Number":{
288
+ "p":0.9599056604,
289
+ "r":0.955399061,
290
+ "f":0.9576470588
291
  },
292
  "AdpType":{
293
+ "p":0.9991087344,
294
+ "r":0.991158267,
295
+ "f":0.9951176209
296
  },
297
  "PartType":{
298
  "p":1.0,
 
300
  "f":1.0
301
  },
302
  "Case":{
303
+ "p":0.9774919614,
304
+ "r":0.9605055292,
305
+ "f":0.9689243028
306
  },
307
  "Person":{
308
+ "p":0.9805996473,
309
  "r":0.9875666075,
310
+ "f":0.9840707965
311
  },
312
  "PronType":{
313
+ "p":0.9876339654,
314
+ "r":0.9851973684,
315
+ "f":0.9864141622
316
  },
317
  "NumType":{
318
+ "p":0.972972973,
319
  "r":0.9536423841,
320
+ "f":0.9632107023
321
  },
322
  "Degree":{
323
+ "p":0.9533742331,
324
  "r":0.9361445783,
325
+ "f":0.9446808511
326
  },
327
  "Reflex":{
328
  "p":1.0,
 
330
  "f":1.0
331
  },
332
  "Number[psor]":{
333
+ "p":0.9885057471,
334
  "r":1.0,
335
+ "f":0.9942196532
336
  },
337
  "Poss":{
338
+ "p":1.0,
339
  "r":1.0,
340
+ "f":1.0
341
  },
342
  "Foreign":{
343
+ "p":0.8,
344
  "r":0.4,
345
+ "f":0.5333333333
346
  },
347
  "Abbr":{
348
  "p":0.0,
 
360
  "f":0.75
361
  }
362
  },
363
+ "sents_p":0.9180327869,
364
+ "sents_r":0.8936170213,
365
+ "sents_f":0.9056603774,
366
+ "dep_uas":0.8226680825,
367
+ "dep_las":0.7821616184,
368
  "dep_las_per_type":{
369
  "advmod":{
370
+ "p":0.702739726,
371
+ "r":0.7245762712,
372
+ "f":0.7134909597
373
  },
374
  "root":{
375
+ "p":0.8519195612,
376
+ "r":0.8262411348,
377
+ "f":0.8388838884
378
  },
379
  "nsubj":{
380
+ "p":0.8474576271,
381
+ "r":0.8438818565,
382
+ "f":0.8456659619
383
  },
384
  "case":{
385
+ "p":0.8813229572,
386
+ "r":0.8934911243,
387
+ "f":0.8873653281
388
  },
389
  "obl":{
390
+ "p":0.7200647249,
391
+ "r":0.6909937888,
392
+ "f":0.705229794
393
  },
394
  "cc":{
395
+ "p":0.7608069164,
396
+ "r":0.7674418605,
397
+ "f":0.7641099855
398
  },
399
  "conj":{
400
+ "p":0.624,
401
+ "r":0.624,
402
+ "f":0.624
403
  },
404
  "obj":{
405
+ "p":0.802946593,
406
+ "r":0.8466019417,
407
+ "f":0.8241965974
408
  },
409
  "aux":{
410
+ "p":0.8869047619,
411
+ "r":0.8688046647,
412
+ "f":0.8777614138
413
  },
414
  "acl:relcl":{
415
+ "p":0.5872093023,
416
+ "r":0.5459459459,
417
+ "f":0.5658263305
418
  },
419
  "advmod:lmod":{
420
+ "p":0.7704918033,
421
+ "r":0.7014925373,
422
+ "f":0.734375
423
  },
424
  "det":{
425
+ "p":0.9161184211,
426
+ "r":0.9176276771,
427
+ "f":0.916872428
428
  },
429
  "amod":{
430
+ "p":0.8010033445,
431
+ "r":0.8174061433,
432
+ "f":0.8091216216
433
  },
434
  "nmod:poss":{
435
+ "p":0.619047619,
436
+ "r":0.6435643564,
437
+ "f":0.6310679612
438
  },
439
  "ccomp":{
440
+ "p":0.6417910448,
441
+ "r":0.6935483871,
442
+ "f":0.6666666667
443
  },
444
  "nummod":{
445
+ "p":0.8571428571,
446
+ "r":0.85,
447
+ "f":0.8535564854
448
  },
449
  "flat":{
450
+ "p":0.7962962963,
451
+ "r":0.8543046358,
452
+ "f":0.8242811502
453
  },
454
  "compound:prt":{
455
+ "p":0.5517241379,
456
+ "r":0.3902439024,
457
+ "f":0.4571428571
458
  },
459
  "advcl":{
460
+ "p":0.6666666667,
461
+ "r":0.6724137931,
462
+ "f":0.669527897
463
  },
464
  "mark":{
465
+ "p":0.885106383,
466
+ "r":0.8542094456,
467
+ "f":0.8693834901
468
  },
469
  "cop":{
470
+ "p":0.8,
471
+ "r":0.8457142857,
472
+ "f":0.8222222222
473
  },
474
  "dep":{
475
+ "p":0.175,
476
+ "r":0.2641509434,
477
+ "f":0.2105263158
478
  },
479
  "nmod":{
480
+ "p":0.6332665331,
481
+ "r":0.6171875,
482
+ "f":0.62512364
483
  },
484
  "iobj":{
485
+ "p":0.9166666667,
486
+ "r":0.5,
487
+ "f":0.6470588235
488
  },
489
  "xcomp":{
490
+ "p":0.5555555556,
491
+ "r":0.3389830508,
492
+ "f":0.4210526316
493
  },
494
  "list":{
495
+ "p":0.3333333333,
496
+ "r":0.2777777778,
497
+ "f":0.303030303
498
  },
499
  "vocative":{
500
  "p":0.0,
 
502
  "f":0.0
503
  },
504
  "fixed":{
505
+ "p":0.8684210526,
506
  "r":0.8048780488,
507
+ "f":0.835443038
508
  },
509
  "expl":{
510
+ "p":0.8484848485,
511
  "r":0.8235294118,
512
+ "f":0.8358208955
513
  },
514
  "appos":{
515
+ "p":0.5405405405,
516
+ "r":0.6060606061,
517
+ "f":0.5714285714
518
  },
519
  "obl:tmod":{
520
+ "p":0.8888888889,
521
+ "r":0.4444444444,
522
+ "f":0.5925925926
523
  },
524
+ "obl:lmod":{
525
  "p":0.0,
526
  "r":0.0,
527
  "f":0.0
528
  },
529
+ "discourse":{
530
  "p":0.0,
531
  "r":0.0,
532
  "f":0.0
533
  }
534
  },
535
+ "lemma_acc":0.9476997579,
536
+ "tag_acc":0.9634866828,
537
+ "ents_p":0.8020833333,
538
+ "ents_r":0.8020833333,
539
+ "ents_f":0.8020833333,
540
  "ents_per_type":{
541
  "PER":{
542
+ "p":0.9,
543
+ "r":0.8674698795,
544
+ "f":0.8834355828
545
  },
546
  "ORG":{
547
+ "p":0.7011494253,
548
+ "r":0.6777777778,
549
+ "f":0.6892655367
550
  },
551
  "MISC":{
552
+ "p":0.6956521739,
553
  "r":0.7079646018,
554
+ "f":0.701754386
555
  },
556
  "LOC":{
557
  "p":0.8474576271,
 
559
  "f":0.8733624454
560
  }
561
  },
562
+ "speed":12067.6587888281
563
  },
564
  "sources":[
565
  {
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f3dd440cc2b2ffe48e5129e46f7874970c6979b2c57ddb362c031a7d0292ecd
3
  size 61739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2286e4631b67ca3a9bfac8a3268683b0acff339d5dc2b640d2c20115d99ef4
3
  size 61739
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1b8f5a2faae4c56989b79b266532a0a0e010ee937865c281589fd2cf3ec912d
3
- size 6496592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dee55230c35949cc79a93c7bca910fedc77cb8bfefc175132b0d6fb8a5ae5e6a
3
+ size 6366382
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8cc422d00dc50b0be029d66e9edd548bb761248057b597b19f8f94f5f283bcd
3
  size 308728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc69524fa0eed21569a0d922f176fa448a1db163ecea64f2c86d893d436cdf0
3
  size 308728
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c50f933bed18d134dc0323a61e7baf009fb0b703108ca70f0d650a03ab0f50ef
3
  size 219953
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99708f84b340d33c4ced45d5196a7c48273c23d5c761e8adce20b638590dda0c
3
  size 219953
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69f3bc3816250579fd4b1d28475510cfeeeb068570a0c765b83199b02c6d51fd
3
- size 6365604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58aa5957c059eb90385b496a9f9f5cb49cbe5ebb83630e4a5adea1bcc54acb1b
3
+ size 6495793
tokenizer CHANGED
The diff for this file is too large to render. See raw diff
 
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dd21462fbe7a706e335e3d37fcc588191e3dd92fd2cf26856583ef5adc2ea32
3
- size 10087412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d23a5f535aa4b19fd22032236b5ac94c14e46f3d95406cdf6c9688a2b86ee5
3
+ size 10087110