Update spaCy pipeline

Browse files

Files changed (15) hide show

README.md +28 -28
accuracy.json +167 -167
config.cfg +57 -28
lemmatizer/cfg +343 -354
lemmatizer/model +2 -2
lemmatizer/trees +0 -0
meta.json +174 -172
morphologizer/model +2 -2
ner/model +0 -0
parser/model +0 -0
sl_core_news_trf-any-py3-none-any.whl +2 -2
tagger/model +2 -2
transformer/cfg +1 -1
transformer/model +2 -2
vocab/strings.json +0 -0

README.md CHANGED Viewed

@@ -14,72 +14,72 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.8841463415
     - name: NER Recall
       type: recall
-      value: 0.917721519
     - name: NER F Score
       type: f_score
-      value: 0.900621118
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9770274602
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9899348221
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9788652634
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.9679666631
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.93363503
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.9170251386
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
-      value: 0.9373219373
 ---
 ### Details: https://spacy.io/models/sl#sl_core_news_trf
-Slovenian transformer pipeline (EMBEDDIA/sloberta). Components: transformer, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner.
 | Feature | Description |
 | --- | --- |
 | **Name** | `sl_core_news_trf` |
-| **Version** | `3.6.1` |
-| **spaCy** | `>=3.6.0,<3.7.0` |
 | **Default Pipeline** | `transformer`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
 | **Components** | `transformer`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
 | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -110,18 +110,18 @@ Slovenian transformer pipeline (EMBEDDIA/sloberta). Components: transformer, tag
 | `TOKEN_P` | 99.81 |
 | `TOKEN_R` | 99.57 |
 | `TOKEN_F` | 99.69 |
-| `TAG_ACC` | 97.70 |
-| `POS_ACC` | 98.99 |
-| `MORPH_ACC` | 97.89 |
-| `MORPH_MICRO_P` | 99.01 |
-| `MORPH_MICRO_R` | 98.89 |
-| `MORPH_MICRO_F` | 98.95 |
-| `SENTS_P` | 93.20 |
-| `SENTS_R` | 94.27 |
-| `SENTS_F` | 93.73 |
-| `DEP_UAS` | 93.36 |
-| `DEP_LAS` | 91.70 |
-| `LEMMA_ACC` | 96.80 |
-| `ENTS_P` | 88.41 |
-| `ENTS_R` | 91.77 |
-| `ENTS_F` | 90.06 |

     metrics:
     - name: NER Precision
       type: precision
+      value: 0.9316770186
     - name: NER Recall
       type: recall
+      value: 0.9493670886
     - name: NER F Score
       type: f_score
+      value: 0.9404388715
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
+      value: 0.9802329309
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
+      value: 0.9908323539
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
+      value: 0.981857036
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
+      value: 0.9694198098
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
+      value: 0.9361807921
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
+      value: 0.9223081322
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
+      value: 0.9325789722
 ---
 ### Details: https://spacy.io/models/sl#sl_core_news_trf
+Slovenian transformer pipeline (Transformer(name='EMBEDDIA/sloberta', piece_encoder='camembert-sentencepiece', stride=128, type='camembert', width=768, window=168, vocab_size=32005)). Components: transformer, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner.
 | Feature | Description |
 | --- | --- |
 | **Name** | `sl_core_news_trf` |
+| **Version** | `3.7.2` |
+| **spaCy** | `>=3.7.0,<3.8.0` |
 | **Default Pipeline** | `transformer`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
 | **Components** | `transformer`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
 | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
 | `TOKEN_P` | 99.81 |
 | `TOKEN_R` | 99.57 |
 | `TOKEN_F` | 99.69 |
+| `TAG_ACC` | 98.02 |
+| `POS_ACC` | 99.08 |
+| `MORPH_ACC` | 98.19 |
+| `MORPH_MICRO_P` | 99.15 |
+| `MORPH_MICRO_R` | 99.04 |
+| `MORPH_MICRO_F` | 99.09 |
+| `SENTS_P` | 92.09 |
+| `SENTS_R` | 94.46 |
+| `SENTS_F` | 93.26 |
+| `DEP_UAS` | 93.62 |
+| `DEP_LAS` | 92.23 |
+| `LEMMA_ACC` | 96.94 |
+| `ENTS_P` | 93.17 |
+| `ENTS_R` | 94.94 |
+| `ENTS_F` | 94.04 |

accuracy.json CHANGED Viewed

@@ -3,57 +3,57 @@
   "token_p": 0.9980762654,
   "token_r": 0.9956925964,
   "token_f": 0.996883006,
-  "tag_acc": 0.9770274602,
-  "pos_acc": 0.9899348221,
-  "morph_acc": 0.9788652634,
-  "morph_micro_p": 0.9900582551,
-  "morph_micro_r": 0.9888854047,
-  "morph_micro_f": 0.9894714824,
   "morph_per_feat": {
     "Case": {
-      "p": 0.9839550079,
-      "r": 0.9840363937,
-      "f": 0.9839956991
     },
     "Gender": {
-      "p": 0.9841089671,
-      "r": 0.9844814534,
-      "f": 0.984295175
     },
     "Number": {
-      "p": 0.9930539296,
-      "r": 0.9932864949,
-      "f": 0.9931701986
     },
     "Aspect": {
-      "p": 0.9868204283,
-      "r": 0.9933665008,
-      "f": 0.9900826446
     },
     "Mood": {
-      "p": 0.9951520494,
-      "r": 0.9947136564,
-      "f": 0.9949328046
     },
     "Person": {
-      "p": 0.9972166998,
-      "r": 0.9964243147,
-      "f": 0.9968203498
     },
     "Tense": {
-      "p": 0.9980582524,
-      "r": 0.9951597289,
-      "f": 0.9966068832
     },
     "VerbForm": {
-      "p": 0.997615894,
-      "r": 0.9949801849,
-      "f": 0.9962962963
     },
     "PronType": {
-      "p": 0.9929214929,
       "r": 0.995483871,
-      "f": 0.9942010309
     },
     "Variant": {
       "p": 0.9981412639,
@@ -62,18 +62,18 @@
     },
     "NumForm": {
       "p": 1.0,
-      "r": 0.9617834395,
-      "f": 0.9805194805
     },
     "NumType": {
       "p": 1.0,
-      "r": 0.9653179191,
-      "f": 0.9823529412
     },
     "Degree": {
-      "p": 0.9925989183,
-      "r": 0.9923164485,
-      "f": 0.9924576633
     },
     "Polarity": {
       "p": 1.0,
@@ -81,14 +81,14 @@
       "f": 0.9992902768
     },
     "Number[psor]": {
-      "p": 0.9375,
-      "r": 0.9375,
-      "f": 0.9375
     },
     "Poss": {
-      "p": 1.0,
-      "r": 0.995,
-      "f": 0.9974937343
     },
     "Reflex": {
       "p": 0.9975,
@@ -101,9 +101,9 @@
       "f": 0.9896551724
     },
     "Animacy": {
-      "p": 0.9634831461,
-      "r": 0.9346049046,
-      "f": 0.948824343
     },
     "Abbr": {
       "p": 1.0,
@@ -111,186 +111,186 @@
       "f": 1.0
     },
     "Foreign": {
-      "p": 0.8947368421,
-      "r": 0.4473684211,
-      "f": 0.5964912281
     },
     "Gender[psor]": {
-      "p": 0.9090909091,
       "r": 0.9090909091,
-      "f": 0.9090909091
     }
   },
-  "sents_p": 0.9320113314,
-  "sents_r": 0.9426934097,
-  "sents_f": 0.9373219373,
-  "dep_uas": 0.93363503,
-  "dep_las": 0.9170251386,
   "dep_las_per_type": {
     "nsubj": {
-      "p": 0.942804428,
-      "r": 0.9560336763,
-      "f": 0.949372968
     },
     "nmod": {
-      "p": 0.8998951782,
-      "r": 0.8850515464,
-      "f": 0.8924116424
     },
     "root": {
-      "p": 0.9437022901,
-      "r": 0.9446036294,
-      "f": 0.9441527446
     },
     "obj": {
-      "p": 0.9335899904,
-      "r": 0.9371980676,
-      "f": 0.9353905497
     },
     "iobj": {
-      "p": 0.8732394366,
-      "r": 0.7209302326,
-      "f": 0.7898089172
     },
     "case": {
-      "p": 0.9897260274,
-      "r": 0.9863481229,
-      "f": 0.988034188
     },
     "cc": {
-      "p": 0.9503546099,
-      "r": 0.9447708578,
-      "f": 0.947554508
     },
     "conj": {
-      "p": 0.8023483366,
-      "r": 0.8,
-      "f": 0.8011724475
     },
     "mark": {
-      "p": 0.9721115538,
-      "r": 0.9721115538,
-      "f": 0.9721115538
     },
     "obl": {
-      "p": 0.9013806706,
-      "r": 0.8984272608,
-      "f": 0.8999015425
     },
     "nummod": {
-      "p": 0.9423076923,
-      "r": 0.9171122995,
-      "f": 0.9295392954
     },
     "acl": {
-      "p": 0.8353221957,
-      "r": 0.8177570093,
-      "f": 0.826446281
     },
     "amod": {
-      "p": 0.9797830375,
-      "r": 0.9895418327,
-      "f": 0.9846382557
     },
     "aux": {
-      "p": 0.9900552486,
-      "r": 0.9900552486,
-      "f": 0.9900552486
     },
     "det": {
-      "p": 0.9719222462,
-      "r": 0.9846827133,
-      "f": 0.9782608696
     },
     "advmod": {
-      "p": 0.8700209644,
-      "r": 0.8718487395,
-      "f": 0.870933893
     },
     "parataxis": {
-      "p": 0.7,
       "r": 0.6549707602,
-      "f": 0.6767371601
     },
     "flat:name": {
-      "p": 0.9681528662,
-      "r": 0.987012987,
-      "f": 0.9774919614
     },
     "cop": {
-      "p": 0.9393939394,
-      "r": 0.9482352941,
-      "f": 0.943793911
     },
     "csubj": {
-      "p": 0.8863636364,
-      "r": 0.8764044944,
-      "f": 0.8813559322
     },
     "expl": {
-      "p": 0.9272151899,
-      "r": 0.9391025641,
-      "f": 0.9331210191
     },
     "xcomp": {
-      "p": 0.9496855346,
-      "r": 0.94375,
-      "f": 0.9467084639
     },
     "ccomp": {
-      "p": 0.9438202247,
-      "r": 0.9130434783,
-      "f": 0.9281767956
     },
     "appos": {
-      "p": 0.5921052632,
-      "r": 0.625,
-      "f": 0.6081081081
     },
     "flat": {
-      "p": 0.6086956522,
-      "r": 0.7368421053,
-      "f": 0.6666666667
     },
     "orphan": {
-      "p": 0.6470588235,
-      "r": 0.4583333333,
-      "f": 0.5365853659
     },
     "advcl": {
-      "p": 0.75,
-      "r": 0.7285714286,
-      "f": 0.7391304348
     },
     "fixed": {
-      "p": 0.9090909091,
-      "r": 0.9090909091,
-      "f": 0.9090909091
     },
     "list": {
-      "p": 0.7717391304,
       "r": 0.8658536585,
-      "f": 0.816091954
     },
     "flat:foreign": {
-      "p": 0.625,
-      "r": 0.625,
-      "f": 0.625
-    },
-    "dep": {
-      "p": 0.0344827586,
-      "r": 0.1666666667,
-      "f": 0.0571428571
     },
     "discourse": {
-      "p": 0.6,
       "r": 0.6428571429,
-      "f": 0.6206896552
     },
     "vocative": {
-      "p": 1.0,
       "r": 0.2,
-      "f": 0.3333333333
     },
     "cc:preconj": {
       "p": 1.0,
@@ -298,25 +298,25 @@
       "f": 0.8421052632
     }
   },
-  "lemma_acc": 0.9679666631,
-  "ents_p": 0.8841463415,
-  "ents_r": 0.917721519,
-  "ents_f": 0.900621118,
   "ents_per_type": {
     "ORG": {
-      "p": 0.7692307692,
-      "r": 0.75,
-      "f": 0.7594936709
     },
     "PER": {
       "p": 1.0,
-      "r": 0.9833333333,
-      "f": 0.9915966387
     },
     "LOC": {
-      "p": 0.8666666667,
       "r": 0.962962963,
-      "f": 0.9122807018
     },
     "MISC": {
       "p": 0.75,
@@ -329,5 +329,5 @@
       "f": 0.6666666667
     }
   },
-  "speed": 1211.6699495749
 }

   "token_p": 0.9980762654,
   "token_r": 0.9956925964,
   "token_f": 0.996883006,
+  "tag_acc": 0.9802329309,
+  "pos_acc": 0.9908323539,
+  "morph_acc": 0.981857036,
+  "morph_micro_p": 0.9914889164,
+  "morph_micro_r": 0.9903661893,
+  "morph_micro_f": 0.9909272349,
   "morph_per_feat": {
     "Case": {
+      "p": 0.9859446052,
+      "r": 0.9863523573,
+      "f": 0.9861484391
     },
     "Gender": {
+      "p": 0.986196464,
+      "r": 0.9870363361,
+      "f": 0.9866162213
     },
     "Number": {
+      "p": 0.9937587767,
+      "r": 0.9943793911,
+      "f": 0.994068987
     },
     "Aspect": {
+      "p": 0.9906439185,
+      "r": 0.9950248756,
+      "f": 0.9928295643
     },
     "Mood": {
+      "p": 0.9955927721,
+      "r": 0.995154185,
+      "f": 0.9953734303
     },
     "Person": {
+      "p": 0.9984095427,
+      "r": 0.9976162098,
+      "f": 0.9980127186
     },
     "Tense": {
+      "p": 0.9985436893,
+      "r": 0.9956437561,
+      "f": 0.9970916142
     },
     "VerbForm": {
+      "p": 0.9986772487,
+      "r": 0.9973579921,
+      "f": 0.9980171844
     },
     "PronType": {
+      "p": 0.9948420374,
       "r": 0.995483871,
+      "f": 0.9951628507
     },
     "Variant": {
       "p": 0.9981412639,
     },
     "NumForm": {
       "p": 1.0,
+      "r": 0.9681528662,
+      "f": 0.9838187702
     },
     "NumType": {
       "p": 1.0,
+      "r": 0.9710982659,
+      "f": 0.9853372434
     },
     "Degree": {
+      "p": 0.9937268321,
+      "r": 0.9917472965,
+      "f": 0.9927360775
     },
     "Polarity": {
       "p": 1.0,
       "f": 0.9992902768
     },
     "Number[psor]": {
+      "p": 0.9583333333,
+      "r": 0.9583333333,
+      "f": 0.9583333333
     },
     "Poss": {
+      "p": 0.9949748744,
+      "r": 0.99,
+      "f": 0.992481203
     },
     "Reflex": {
       "p": 0.9975,
       "f": 0.9896551724
     },
     "Animacy": {
+      "p": 0.9630681818,
+      "r": 0.9237057221,
+      "f": 0.9429763561
     },
     "Abbr": {
       "p": 1.0,
       "f": 1.0
     },
     "Foreign": {
+      "p": 1.0,
+      "r": 0.3947368421,
+      "f": 0.5660377358
     },
     "Gender[psor]": {
+      "p": 0.9375,
       "r": 0.9090909091,
+      "f": 0.9230769231
     }
   },
+  "sents_p": 0.9208566108,
+  "sents_r": 0.9446036294,
+  "sents_f": 0.9325789722,
+  "dep_uas": 0.9361807921,
+  "dep_las": 0.9223081322,
   "dep_las_per_type": {
     "nsubj": {
+      "p": 0.9579831933,
+      "r": 0.9597754911,
+      "f": 0.9588785047
     },
     "nmod": {
+      "p": 0.8976744186,
+      "r": 0.8953608247,
+      "f": 0.896516129
     },
     "root": {
+      "p": 0.9408960915,
+      "r": 0.9426934097,
+      "f": 0.9417938931
     },
     "obj": {
+      "p": 0.9537126326,
+      "r": 0.9555555556,
+      "f": 0.9546332046
     },
     "iobj": {
+      "p": 0.8441558442,
+      "r": 0.7558139535,
+      "f": 0.7975460123
     },
     "case": {
+      "p": 0.9897128161,
+      "r": 0.9850682594,
+      "f": 0.9873850759
     },
     "cc": {
+      "p": 0.9610849057,
+      "r": 0.9576968273,
+      "f": 0.9593878752
     },
     "conj": {
+      "p": 0.820909971,
+      "r": 0.8273170732,
+      "f": 0.824101069
     },
     "mark": {
+      "p": 0.9654255319,
+      "r": 0.9641434263,
+      "f": 0.9647840532
     },
     "obl": {
+      "p": 0.923128793,
+      "r": 0.8971166448,
+      "f": 0.9099368561
     },
     "nummod": {
+      "p": 0.9453551913,
+      "r": 0.9251336898,
+      "f": 0.9351351351
     },
     "acl": {
+      "p": 0.8486997636,
+      "r": 0.8387850467,
+      "f": 0.8437132785
     },
     "amod": {
+      "p": 0.9846000994,
+      "r": 0.9870517928,
+      "f": 0.9858244218
     },
     "aux": {
+      "p": 0.9911406423,
+      "r": 0.9889502762,
+      "f": 0.9900442478
     },
     "det": {
+      "p": 0.9739696312,
+      "r": 0.9824945295,
+      "f": 0.9782135076
     },
     "advmod": {
+      "p": 0.8706004141,
+      "r": 0.8834033613,
+      "f": 0.8769551616
     },
     "parataxis": {
+      "p": 0.6892307692,
       "r": 0.6549707602,
+      "f": 0.6716641679
     },
     "flat:name": {
+      "p": 0.9741935484,
+      "r": 0.9805194805,
+      "f": 0.9773462783
     },
     "cop": {
+      "p": 0.9443155452,
+      "r": 0.9576470588,
+      "f": 0.9509345794
     },
     "csubj": {
+      "p": 0.9101123596,
+      "r": 0.9101123596,
+      "f": 0.9101123596
     },
     "expl": {
+      "p": 0.961414791,
+      "r": 0.9583333333,
+      "f": 0.9598715891
     },
     "xcomp": {
+      "p": 0.9440993789,
+      "r": 0.95,
+      "f": 0.9470404984
     },
     "ccomp": {
+      "p": 0.9184782609,
+      "r": 0.9184782609,
+      "f": 0.9184782609
+    },
+    "dep": {
+      "p": 0.0465116279,
+      "r": 0.3333333333,
+      "f": 0.0816326531
     },
     "appos": {
+      "p": 0.6258503401,
+      "r": 0.6388888889,
+      "f": 0.6323024055
     },
     "flat": {
+      "p": 0.7647058824,
+      "r": 0.6842105263,
+      "f": 0.7222222222
     },
     "orphan": {
+      "p": 0.6478873239,
+      "r": 0.4791666667,
+      "f": 0.5508982036
     },
     "advcl": {
+      "p": 0.7486910995,
+      "r": 0.680952381,
+      "f": 0.7132169576
     },
     "fixed": {
+      "p": 0.9393939394,
+      "r": 0.9393939394,
+      "f": 0.9393939394
     },
     "list": {
+      "p": 0.7553191489,
       "r": 0.8658536585,
+      "f": 0.8068181818
     },
     "flat:foreign": {
+      "p": 0.6666666667,
+      "r": 0.5,
+      "f": 0.5714285714
     },
     "discourse": {
+      "p": 0.9,
       "r": 0.6428571429,
+      "f": 0.75
     },
     "vocative": {
+      "p": 0.5,
       "r": 0.2,
+      "f": 0.2857142857
     },
     "cc:preconj": {
       "p": 1.0,
       "f": 0.8421052632
     }
   },
+  "lemma_acc": 0.9694198098,
+  "ents_p": 0.9316770186,
+  "ents_r": 0.9493670886,
+  "ents_f": 0.9404388715,
   "ents_per_type": {
     "ORG": {
+      "p": 0.9189189189,
+      "r": 0.85,
+      "f": 0.8831168831
     },
     "PER": {
       "p": 1.0,
+      "r": 1.0,
+      "f": 1.0
     },
     "LOC": {
+      "p": 0.8965517241,
       "r": 0.962962963,
+      "f": 0.9285714286
     },
     "MISC": {
       "p": 0.75,
       "f": 0.6666666667
     }
   },
+  "speed": 1008.1462815944
 }

config.cfg CHANGED Viewed

@@ -17,6 +17,7 @@ after_creation = null
 after_pipeline_creation = null
 batch_size = 64
 tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
 [components]
@@ -39,10 +40,11 @@ nO = null
 normalize = false
 [components.lemmatizer.model.tok2vec]
-@architectures = "spacy-transformers.TransformerListener.v1"
-grad_factor = 1.0
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
 [components.morphologizer]
 factory = "morphologizer"
@@ -57,10 +59,11 @@ nO = null
 normalize = false
 [components.morphologizer.model.tok2vec]
-@architectures = "spacy-transformers.TransformerListener.v1"
-grad_factor = 1.0
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
 [components.ner]
 factory = "ner"
@@ -79,10 +82,11 @@ use_upper = false
 nO = null
 [components.ner.model.tok2vec]
-@architectures = "spacy-transformers.TransformerListener.v1"
-grad_factor = 1.0
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
 [components.parser]
 factory = "parser"
@@ -102,10 +106,11 @@ use_upper = false
 nO = null
 [components.parser.model.tok2vec]
-@architectures = "spacy-transformers.TransformerListener.v1"
-grad_factor = 1.0
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
 [components.tagger]
 factory = "tagger"
@@ -120,32 +125,44 @@ nO = null
 normalize = false
 [components.tagger.model.tok2vec]
-@architectures = "spacy-transformers.TransformerListener.v1"
-grad_factor = 1.0
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
 [components.transformer]
-factory = "transformer"
-max_batch_items = 4096
-set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
 [components.transformer.model]
-name = "EMBEDDIA/sloberta"
-@architectures = "spacy-transformers.TransformerModel.v3"
 mixed_precision = false
-[components.transformer.model.get_spans]
-@span_getters = "spacy-transformers.strided_spans.v1"
-window = 128
-stride = 96
 [components.transformer.model.grad_scaler_config]
-[components.transformer.model.tokenizer_config]
-use_fast = true
-[components.transformer.model.transformer_config]
 [corpora]
@@ -182,11 +199,11 @@ annotating_components = []
 before_update = null
 [training.batcher]
-@batchers = "spacy.batch_by_padded.v1"
-discard_oversize = true
-get_length = null
 size = 2000
-buffer = 256
 [training.logger]
 @loggers = "spacy.ConsoleLogger.v1"
@@ -272,6 +289,18 @@ require = false
 path = "corpus/labels/tagger.json"
 require = false
 [initialize.lookups]
 @misc = "spacy.LookupsDataLoader.v1"
 lang = ${nlp.lang}

 after_pipeline_creation = null
 batch_size = 64
 tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
 [components]
 normalize = false
 [components.lemmatizer.model.tok2vec]
+@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
+width = ${components.transformer.model.hidden_width}
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
+grad_factor = 1.0
 [components.morphologizer]
 factory = "morphologizer"
 normalize = false
 [components.morphologizer.model.tok2vec]
+@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
+width = ${components.transformer.model.hidden_width}
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
+grad_factor = 1.0
 [components.ner]
 factory = "ner"
 nO = null
 [components.ner.model.tok2vec]
+@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
+width = ${components.transformer.model.hidden_width}
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
+grad_factor = 1.0
 [components.parser]
 factory = "parser"
 nO = null
 [components.parser.model.tok2vec]
+@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
+width = ${components.transformer.model.hidden_width}
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
+grad_factor = 1.0
 [components.tagger]
 factory = "tagger"
 normalize = false
 [components.tagger.model.tok2vec]
+@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
+width = ${components.transformer.model.hidden_width}
 upstream = "transformer"
 pooling = {"@layers":"reduce_mean.v1"}
+grad_factor = 1.0
 [components.transformer]
+factory = "curated_transformer"
+all_layer_outputs = false
+frozen = false
 [components.transformer.model]
+@architectures = "spacy-curated-transformers.CamembertTransformer.v1"
+vocab_size = 32005
+hidden_width = 768
+piece_encoder = {"@architectures":"spacy-curated-transformers.CamembertSentencepieceEncoder.v1"}
+attention_probs_dropout_prob = 0.1
+hidden_act = "gelu"
+hidden_dropout_prob = 0.1
+intermediate_width = 3072
+layer_norm_eps = 0.00001
+max_position_embeddings = 514
+model_max_length = 512
+num_attention_heads = 12
+num_hidden_layers = 12
+padding_idx = 1
+type_vocab_size = 1
 mixed_precision = false
+torchscript = false
+wrapped_listener = null
 [components.transformer.model.grad_scaler_config]
+[components.transformer.model.with_spans]
+@architectures = "spacy-curated-transformers.WithStridedSpans.v1"
+stride = 128
+window = 168
+batch_size = 384
 [corpora]
 before_update = null
 [training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
 size = 2000
+tolerance = 0.2
+get_length = null
 [training.logger]
 @loggers = "spacy.ConsoleLogger.v1"
 path = "corpus/labels/tagger.json"
 require = false
+[initialize.components.transformer]
+[initialize.components.transformer.encoder_loader]
+@model_loaders = "spacy-curated-transformers.HFTransformerEncoderLoader.v1"
+name = "EMBEDDIA/sloberta"
+revision = "main"
+[initialize.components.transformer.piecer_loader]
+@model_loaders = "spacy-curated-transformers.HFPieceEncoderLoader.v1"
+name = "EMBEDDIA/sloberta"
+revision = "main"
 [initialize.lookups]
 @misc = "spacy.LookupsDataLoader.v1"
 lang = ${nlp.lang}

lemmatizer/cfg CHANGED Viewed

@@ -102,31 +102,31 @@
     202,
     204,
     206,
-    208,
-    210,
-    212,
-    215,
-    217,
-    222,
-    224,
-    226,
     227,
     230,
-    232,
-    234,
-    237,
     238,
-    239,
     241,
-    243,
     244,
     246,
-    248,
-    252,
-    253,
-    254,
     256,
-    258,
     259,
     261,
     262,
@@ -135,418 +135,422 @@
     267,
     268,
     270,
-    272,
     275,
-    276,
-    277,
     279,
-    281,
-    283,
-    285,
     289,
-    292,
-    295,
     297,
     301,
-    302,
     303,
     304,
-    306,
     307,
     308,
-    310,
-    311,
     313,
-    316,
     317,
     319,
-    321,
     323,
-    324,
     326,
     327,
-    330,
     331,
     333,
-    335,
     337,
     338,
-    340,
     341,
-    342,
     343,
-    345,
-    347,
-    350,
     353,
     355,
-    356,
     357,
-    359,
     361,
     364,
-    365,
-    366,
     368,
-    372,
-    374,
-    379,
     380,
-    381,
-    384,
     386,
-    389,
     390,
     392,
     394,
-    396,
     397,
-    398,
-    400,
     401,
     403,
     405,
-    407,
-    408,
     409,
     412,
     413,
-    414,
-    415,
-    417,
     418,
-    421,
-    423,
     424,
     425,
-    427,
     429,
-    430,
     433,
     434,
-    436,
     438,
-    439,
-    441,
     442,
-    446,
     447,
-    448,
-    451,
     453,
     454,
-    457,
     458,
     460,
-    462,
-    463,
     464,
-    465,
-    467,
     469,
     472,
-    473,
-    475,
     476,
     478,
     480,
-    481,
     483,
     485,
     487,
-    488,
     489,
-    490,
     492,
     494,
     497,
-    498,
     499,
     501,
-    502,
     503,
-    504,
     506,
-    508,
     510,
-    512,
-    513,
     514,
-    516,
     518,
-    519,
     520,
     523,
     527,
-    529,
     532,
     533,
     535,
     536,
     537,
     539,
     541,
     542,
     543,
     544,
-    545,
     546,
     548,
-    549,
     550,
     551,
-    552,
-    554,
     555,
-    556,
     558,
-    560,
     562,
     563,
     565,
     567,
-    570,
     571,
     573,
     574,
-    575,
     577,
-    579,
     581,
     583,
-    584,
     585,
     586,
-    587,
     589,
-    590,
-    591,
     593,
     594,
     595,
     597,
     598,
-    600,
     601,
     605,
-    606,
     607,
     609,
     610,
     613,
-    617,
     619,
-    620,
     621,
     622,
     624,
-    625,
     628,
     631,
-    633,
     634,
     636,
     638,
-    639,
     640,
     641,
-    642,
     643,
-    644,
     646,
     648,
     650,
     652,
-    653,
-    655,
     657,
-    658,
     660,
-    662,
-    664,
     666,
     668,
     669,
-    671,
     672,
-    673,
-    675,
-    678,
-    680,
     681,
-    682,
     685,
     687,
-    690,
     692,
-    693,
     695,
-    697,
     698,
-    700,
     702,
-    703,
     706,
     709,
     710,
     712,
-    713,
     715,
     716,
     718,
-    107,
     720,
-    722,
     723,
-    724,
     726,
-    728,
     729,
-    730,
-    731,
     732,
-    733,
-    735,
     736,
     738,
-    741,
     744,
-    747,
     749,
     751,
-    753,
     755,
     757,
-    758,
     759,
-    760,
     761,
     763,
     764,
     766,
     767,
     769,
-    770,
     771,
     773,
-    775,
     776,
     777,
     778,
-    779,
     780,
     781,
-    783,
     785,
     786,
     787,
-    790,
-    791,
     792,
     794,
-    795,
-    796,
-    799,
     800,
     801,
-    803,
     806,
     808,
     811,
-    813,
     814,
-    815,
-    817,
     818,
-    484,
-    820,
-    822,
-    824,
     825,
-    827,
-    829,
-    831,
     834,
-    836,
     838,
     839,
-    841,
     843,
-    845,
     846,
     847,
-    848,
     851,
-    852,
     853,
     855,
-    856,
     857,
     859,
     860,
-    862,
     864,
-    866,
     868,
     870,
-    872,
     873,
-    874,
     876,
-    879,
     881,
-    884,
-    886,
     887,
-    888,
-    892,
     893,
     894,
     896,
     898,
     900,
-    901,
-    166,
     903,
     904,
-    906,
-    907,
-    908,
     909,
-    912,
     913,
     918,
     922,
     925,
-    927,
     930,
-    932,
     935,
-    936,
     937,
     939,
-    941,
-    943,
     945,
     948,
-    949,
     950,
     952,
-    954,
     956,
     958,
-    961,
     963,
     965,
     967,
     968,
     970,
     971,
-    973,
     974,
     975,
     977,
     978,
     980,
     982,
     983,
@@ -557,42 +561,38 @@
     989,
     990,
     992,
-    993,
     994,
-    995,
-    997,
     998,
-    999,
     1000,
-    1001,
     1002,
-    1004,
     1005,
-    1007,
-    1009,
     1011,
     1013,
-    1015,
-    1017,
     1018,
     1020,
     1023,
-    1024,
-    1026,
-    1028,
     1029,
-    1031,
-    1033,
-    1035,
     1036,
-    1038,
-    1040,
-    1042,
     1043,
     1044,
     1045,
-    48,
     1046,
     1047,
     1048,
     1049,
@@ -618,7 +618,6 @@
     1069,
     1070,
     1071,
-    1072,
     1073,
     1074,
     1075,
@@ -647,313 +646,312 @@
     1098,
     1099,
     1100,
-    1101,
     1102,
-    1103,
-    1104,
     1105,
-    1106,
     1107,
-    1108,
     1109,
-    1110,
     1111,
-    1112,
     1113,
     1114,
     1115,
     1116,
     1117,
-    1118,
     1119,
-    1120,
     1121,
     1123,
     1124,
-    1127,
     1129,
-    1131,
-    1133,
     1135,
-    1137,
-    1139,
     1140,
-    1141,
     1143,
-    1145,
     1146,
     1147,
-    1148,
-    1150,
-    1152,
     1153,
-    1156,
     1158,
-    1159,
     1160,
     1162,
     1164,
-    1167,
     1168,
     1169,
-    1171,
     1172,
     1174,
-    1176,
-    1178,
     1179,
     1180,
-    1181,
     1183,
-    1184,
     1186,
     1187,
-    1188,
-    1190,
-    1191,
-    1193,
     1194,
     1195,
     1197,
     1198,
     1202,
     1203,
-    1205,
     1206,
     1209,
     1210,
     1212,
     1215,
     1217,
-    1218,
     1220,
     1221,
-    140,
     1222,
-    1223,
     1226,
     1227,
     1230,
     1231,
     1232,
     1233,
     1235,
-    1236,
     1238,
     1240,
-    1242,
     1243,
     1244,
     1245,
     1246,
     1248,
     1249,
-    1250,
-    1251,
     1252,
-    1253,
-    1254,
     1255,
     1257,
-    1258,
     1259,
-    1262,
-    746,
     1263,
-    1264,
     1266,
     1267,
     1268,
-    1269,
     1271,
     1272,
     1275,
-    1278,
     1279,
     1280,
-    1281,
     1283,
-    1285,
     1287,
     1289,
     1290,
-    1291,
     1292,
     1294,
-    1295,
-    1297,
     1298,
     1300,
-    1302,
     1303,
-    1305,
     1306,
     1307,
     1309,
-    1310,
     1312,
-    1313,
     1315,
-    1316,
     1318,
-    1319,
-    1321,
     1322,
     1323,
-    1324,
     1326,
     1327,
-    1330,
-    1333,
     1334,
-    445,
     1336,
-    1338,
     1339,
     1341,
     1343,
     1344,
     1345,
     1346,
     1349,
     1350,
     1351,
     1352,
     1353,
     1355,
     1356,
     1357,
     1359,
     1360,
     1361,
     1362,
     1363,
     1364,
-    1365,
-    1366,
     1367,
     1368,
     1369,
-    1370,
     1371,
-    1372,
     1373,
-    1374,
-    1375,
     1376,
     1377,
     1380,
     1381,
     1382,
-    1383,
     1385,
     1387,
     1390,
-    1391,
     1392,
-    1393,
-    1394,
     1395,
-    1396,
     1397,
     1400,
-    1401,
     1402,
     1404,
     1407,
-    1409,
     1410,
     1411,
     1412,
-    1413,
     1415,
     1416,
     1418,
     1420,
-    1421,
     1422,
     1423,
     1424,
     1425,
-    1427,
-    1429,
     1430,
-    1431,
     1432,
     1433,
-    1435,
-    1437,
     1438,
     1439,
     1442,
     1444,
-    1445,
     1446,
-    1447,
-    1449,
     1450,
     1452,
     1453,
     1455,
     1457,
-    1459,
-    1461,
     1462,
     1463,
     1465,
-    1467,
     1468,
     1470,
     1472,
     1473,
-    1475,
     1477,
     1479,
     1481,
     1482,
     1483,
     1486,
-    1487,
     1488,
     1489,
     1490,
     1491,
     1492,
-    1493,
     1494,
-    1496,
     1497,
-    1498,
-    1499,
     1501,
     1502,
-    1504,
     1505,
     1508,
     1509,
-    1510,
     1511,
-    1513,
     1515,
     1516,
     1517,
-    1519,
-    1520,
     1522,
     1523,
-    1524,
     1528,
     1529,
     1531,
     1534,
     1535,
-    1537,
     1538,
-    1540,
     1541,
     1543,
     1544,
     1545,
     1547,
     1548,
     1549,
@@ -1006,7 +1004,7 @@
     1596,
     1597,
     1598,
-    1599,
     1601,
     1602,
     1603,
@@ -1025,98 +1023,89 @@
     1617,
     1618,
     1619,
-    1620,
-    1622,
     1625,
     1626,
-    1627,
     1628,
     1629,
     1631,
     1632,
     1633,
-    1634,
     1636,
-    1637,
     1638,
     1640,
     1641,
-    1642,
     1643,
     1645,
-    1646,
-    1647,
     1650,
-    1652,
     1653,
     1655,
-    1656,
     1657,
-    1658,
-    1659,
     1660,
     1662,
     1665,
     1666,
     1667,
-    1668,
     1669,
     1670,
     1671,
     1672,
-    1674,
     1675,
     1676,
-    1677,
     1678,
     1679,
     1681,
-    1682,
     1683,
-    1685,
     1686,
     1687,
     1689,
     1690,
-    1692,
-    1694,
-    1695,
     1696,
     1697,
     1699,
-    1702,
-    1703,
     1704,
     1705,
-    1707,
     1708,
-    1709,
     1710,
     1711,
-    1712,
     1713,
-    1716,
     1717,
-    1718,
-    1720,
     1722,
     1724,
     1726,
     1728,
     1732,
-    1733,
-    1735,
-    1737,
-    1739,
     1741,
     1742,
     1743,
-    1745,
-    1747,
-    1749,
-    1751,
-    1752,
-    1753,
-    1754
   ]
 }

     202,
     204,
     206,
+    207,
+    209,
+    211,
+    213,
+    216,
+    218,
+    223,
+    225,
     227,
+    229,
     230,
+    233,
+    235,
+    236,
     238,
     241,
+    242,
     244,
     246,
+    247,
+    249,
+    251,
+    255,
     256,
+    257,
     259,
     261,
     262,
     267,
     268,
     270,
+    271,
+    273,
     275,
+    278,
     279,
+    280,
+    282,
+    286,
     289,
+    290,
+    293,
     297,
+    298,
+    299,
+    300,
     301,
     303,
     304,
+    305,
     307,
     308,
+    309,
+    312,
     313,
+    315,
     317,
     319,
+    320,
+    322,
     323,
     326,
     327,
+    329,
     331,
     333,
+    334,
+    336,
     337,
     338,
+    339,
     341,
     343,
+    346,
+    349,
+    351,
+    352,
     353,
     355,
     357,
+    360,
     361,
+    362,
     364,
     368,
+    370,
+    375,
+    376,
+    377,
     380,
+    382,
+    385,
     386,
+    388,
     390,
     392,
     394,
+    395,
     397,
+    399,
     401,
     403,
     405,
+    406,
     409,
+    410,
     412,
     413,
+    416,
     418,
+    419,
+    420,
+    422,
     424,
     425,
+    428,
     429,
+    431,
     433,
     434,
+    435,
+    437,
     438,
     442,
+    443,
+    444,
     447,
+    449,
+    450,
     453,
     454,
+    456,
     458,
+    459,
     460,
+    461,
     464,
+    466,
+    468,
     469,
+    471,
     472,
+    474,
     476,
     478,
     480,
+    482,
     483,
+    484,
     485,
     487,
     489,
     492,
     494,
+    495,
+    496,
     497,
     499,
     501,
     503,
+    505,
     506,
+    507,
+    509,
     510,
+    511,
     514,
     518,
     520,
     523,
+    524,
+    526,
     527,
+    528,
+    530,
     532,
     533,
+    534,
     535,
     536,
     537,
     539,
+    540,
     541,
     542,
     543,
     544,
     546,
     548,
     550,
     551,
+    553,
     555,
     558,
+    559,
+    561,
     562,
     563,
     565,
     567,
+    569,
     571,
+    572,
     573,
     574,
+    576,
     577,
+    578,
+    580,
     581,
+    582,
     583,
     585,
     586,
+    588,
     589,
     593,
     594,
     595,
     597,
     598,
     601,
     605,
     607,
+    608,
     609,
     610,
+    612,
     613,
+    616,
     619,
     621,
     622,
     624,
+    626,
+    627,
     628,
+    629,
+    630,
     631,
+    632,
     634,
     636,
     638,
     640,
     641,
     643,
+    645,
     646,
     648,
     650,
     652,
+    654,
+    656,
     657,
+    659,
     660,
+    661,
+    663,
     666,
     668,
     669,
     672,
+    674,
+    677,
+    679,
     681,
+    683,
     685,
     687,
+    689,
     692,
     695,
+    696,
     698,
+    699,
+    701,
     702,
+    704,
+    107,
     706,
+    708,
     709,
     710,
     712,
+    714,
     715,
     716,
+    717,
     718,
     720,
+    721,
     723,
     726,
     729,
     732,
+    734,
     736,
     738,
+    740,
+    742,
+    743,
     744,
+    745,
+    746,
+    748,
     749,
     751,
+    752,
+    754,
     755,
+    756,
     757,
     759,
     761,
+    762,
     763,
     764,
+    765,
     766,
     767,
     769,
     771,
+    772,
     773,
     776,
     777,
     778,
     780,
     781,
+    782,
     785,
     786,
     787,
+    789,
     792,
     794,
+    797,
+    798,
     800,
     801,
+    802,
+    804,
+    805,
     806,
     808,
+    809,
     811,
+    812,
     814,
+    816,
     818,
+    821,
+    823,
     825,
+    826,
+    828,
+    830,
+    832,
+    833,
     834,
+    835,
     838,
     839,
+    840,
+    842,
     843,
+    844,
     846,
     847,
+    849,
     851,
     853,
     855,
     857,
     859,
     860,
+    861,
+    863,
     864,
+    865,
     868,
     870,
     873,
+    875,
     876,
+    877,
     881,
+    882,
+    883,
+    885,
     887,
+    889,
+    890,
+    891,
+    166,
     893,
     894,
     896,
+    897,
     898,
+    899,
     900,
     903,
     904,
     909,
     913,
+    916,
     918,
+    919,
     922,
+    923,
     925,
+    928,
+    929,
     930,
+    931,
+    933,
     935,
     937,
     939,
+    942,
     945,
+    947,
     948,
     950,
     952,
+    953,
+    955,
     956,
     958,
+    959,
+    960,
+    962,
     963,
     965,
     967,
     968,
+    969,
     970,
     971,
+    972,
     974,
     975,
     977,
     978,
+    979,
     980,
     982,
     983,
     989,
     990,
     992,
     994,
+    996,
     998,
     1000,
     1002,
+    1003,
     1005,
+    1008,
+    1010,
     1011,
     1013,
+    1014,
+    1016,
     1018,
     1020,
+    1021,
     1023,
+    1025,
+    1027,
     1029,
+    1030,
+    1032,
+    1034,
     1036,
+    1037,
+    1039,
+    1041,
     1043,
     1044,
     1045,
     1046,
+    48,
     1047,
     1048,
     1049,
     1069,
     1070,
     1071,
     1073,
     1074,
     1075,
     1098,
     1099,
     1100,
     1102,
     1105,
     1107,
     1109,
     1111,
     1113,
     1114,
     1115,
     1116,
     1117,
     1119,
     1121,
+    1122,
     1123,
     1124,
+    1126,
+    1128,
     1129,
+    1132,
+    1134,
     1135,
+    1136,
+    1138,
     1140,
     1143,
+    1144,
     1146,
     1147,
+    1149,
+    1151,
     1153,
+    1154,
+    1155,
+    1157,
     1158,
     1160,
     1162,
+    1163,
     1164,
+    1165,
+    1166,
     1168,
     1169,
+    1170,
     1172,
+    1173,
     1174,
+    1175,
     1179,
     1180,
+    1182,
     1183,
     1186,
     1187,
+    1189,
+    1192,
     1194,
     1195,
     1197,
     1198,
+    140,
+    1199,
     1202,
     1203,
     1206,
+    1207,
+    1208,
     1209,
     1210,
     1212,
+    1213,
     1215,
     1217,
+    1219,
     1220,
     1221,
     1222,
+    1224,
+    1225,
     1226,
     1227,
+    1228,
+    1229,
     1230,
     1231,
     1232,
     1233,
+    1234,
     1235,
     1238,
+    1239,
+    731,
     1240,
+    1241,
     1243,
     1244,
     1245,
     1246,
     1248,
     1249,
     1252,
     1255,
+    1256,
     1257,
     1259,
+    1261,
     1263,
+    1265,
     1266,
     1267,
     1268,
+    1270,
     1271,
     1272,
+    1274,
     1275,
+    1277,
     1279,
     1280,
+    1282,
     1283,
+    1284,
+    1286,
     1287,
     1289,
     1290,
     1292,
+    1293,
     1294,
+    1296,
     1298,
     1300,
+    1301,
     1303,
+    1304,
     1306,
     1307,
+    1308,
     1309,
+    1311,
     1312,
     1315,
     1318,
+    441,
+    1320,
     1322,
     1323,
+    1325,
     1326,
     1327,
+    1328,
+    1331,
+    1332,
     1334,
+    1335,
     1336,
+    1337,
     1339,
+    1340,
     1341,
+    1342,
     1343,
     1344,
     1345,
     1346,
+    1348,
     1349,
     1350,
     1351,
     1352,
     1353,
+    1354,
     1355,
     1356,
     1357,
+    1358,
     1359,
     1360,
     1361,
     1362,
     1363,
     1364,
     1367,
     1368,
     1369,
     1371,
     1373,
     1376,
     1377,
+    1378,
+    1379,
     1380,
     1381,
     1382,
     1385,
+    1386,
     1387,
+    1388,
     1390,
     1392,
     1395,
     1397,
+    1398,
+    1399,
     1400,
     1402,
+    1403,
     1404,
+    1406,
     1407,
+    1408,
     1410,
     1411,
     1412,
+    1414,
     1415,
     1416,
+    1417,
     1418,
     1420,
     1422,
     1423,
     1424,
     1425,
+    1426,
+    1428,
     1430,
     1432,
     1433,
+    1436,
     1438,
     1439,
+    1440,
     1442,
+    1443,
     1444,
     1446,
+    1448,
     1450,
+    1451,
     1452,
     1453,
     1455,
     1457,
+    1458,
+    1460,
     1462,
     1463,
     1465,
+    1466,
     1468,
     1470,
     1472,
     1473,
+    1474,
     1477,
+    1478,
     1479,
+    1480,
     1481,
     1482,
     1483,
+    1484,
+    1485,
     1486,
     1488,
     1489,
     1490,
     1491,
     1492,
     1494,
+    1495,
     1497,
+    1500,
     1501,
     1502,
+    1503,
     1505,
+    1507,
     1508,
     1509,
     1511,
+    1512,
+    1514,
     1515,
     1516,
     1517,
+    1521,
     1522,
     1523,
+    1525,
     1528,
     1529,
     1531,
+    1532,
     1534,
     1535,
+    1536,
     1538,
+    1539,
     1541,
+    1542,
     1543,
     1544,
     1545,
+    1546,
     1547,
     1548,
     1549,
     1596,
     1597,
     1598,
+    1600,
     1601,
     1602,
     1603,
     1617,
     1618,
     1619,
+    1621,
+    1624,
     1625,
     1626,
     1628,
     1629,
+    1630,
     1631,
     1632,
     1633,
+    1635,
     1636,
     1638,
+    1639,
     1640,
     1641,
     1643,
+    1644,
     1645,
+    1648,
     1650,
+    1651,
     1653,
+    1654,
     1655,
     1657,
     1660,
+    1661,
     1662,
+    1663,
+    1664,
     1665,
     1666,
     1667,
     1669,
     1670,
     1671,
     1672,
+    1673,
     1675,
     1676,
     1678,
     1679,
+    1680,
     1681,
     1683,
+    1684,
     1686,
     1687,
     1689,
     1690,
+    1691,
+    1693,
     1696,
     1697,
+    1698,
     1699,
+    1700,
+    1701,
     1704,
     1705,
+    1706,
     1708,
     1710,
     1711,
     1713,
+    1715,
     1717,
+    1721,
     1722,
     1724,
     1726,
     1728,
+    1730,
+    1731,
     1732,
+    1734,
+    1736,
+    1738,
+    1740,
     1741,
     1742,
     1743,
+    1744
   ]
 }

lemmatizer/model CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1127147ab65ad6929e0f4685f452de94c481da040eb40213d48f37da216d810
-size 3439621

 version https://git-lfs.github.com/spec/v1
+oid sha256:aa40645b19dddf7b29ed1769770b9676aa676751efc953ff281f0441cfe97b8e
+size 3405869

lemmatizer/trees CHANGED Viewed

Binary files a/lemmatizer/trees and b/lemmatizer/trees differ

meta.json CHANGED Viewed

@@ -1,14 +1,14 @@
 {
   "lang":"sl",
   "name":"core_news_trf",
-  "version":"3.6.1",
-  "description":"Slovenian transformer pipeline (EMBEDDIA/sloberta). Components: transformer, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner.",
   "author":"Explosion",
   "email":"contact@explosion.ai",
   "url":"https://explosion.ai",
   "license":"CC BY-SA 4.0",
-  "spacy_version":">=3.6.0,<3.7.0",
-  "spacy_git_version":"c067b5264",
   "vectors":{
     "width":0,
     "vectors":0,
@@ -2419,57 +2419,57 @@
     "token_p":0.9980762654,
     "token_r":0.9956925964,
     "token_f":0.996883006,
-    "tag_acc":0.9770274602,
-    "pos_acc":0.9899348221,
-    "morph_acc":0.9788652634,
-    "morph_micro_p":0.9900582551,
-    "morph_micro_r":0.9888854047,
-    "morph_micro_f":0.9894714824,
     "morph_per_feat":{
       "Case":{
-        "p":0.9839550079,
-        "r":0.9840363937,
-        "f":0.9839956991
       },
       "Gender":{
-        "p":0.9841089671,
-        "r":0.9844814534,
-        "f":0.984295175
       },
       "Number":{
-        "p":0.9930539296,
-        "r":0.9932864949,
-        "f":0.9931701986
       },
       "Aspect":{
-        "p":0.9868204283,
-        "r":0.9933665008,
-        "f":0.9900826446
       },
       "Mood":{
-        "p":0.9951520494,
-        "r":0.9947136564,
-        "f":0.9949328046
       },
       "Person":{
-        "p":0.9972166998,
-        "r":0.9964243147,
-        "f":0.9968203498
       },
       "Tense":{
-        "p":0.9980582524,
-        "r":0.9951597289,
-        "f":0.9966068832
       },
       "VerbForm":{
-        "p":0.997615894,
-        "r":0.9949801849,
-        "f":0.9962962963
       },
       "PronType":{
-        "p":0.9929214929,
         "r":0.995483871,
-        "f":0.9942010309
       },
       "Variant":{
         "p":0.9981412639,
@@ -2478,18 +2478,18 @@
       },
       "NumForm":{
         "p":1.0,
-        "r":0.9617834395,
-        "f":0.9805194805
       },
       "NumType":{
         "p":1.0,
-        "r":0.9653179191,
-        "f":0.9823529412
       },
       "Degree":{
-        "p":0.9925989183,
-        "r":0.9923164485,
-        "f":0.9924576633
       },
       "Polarity":{
         "p":1.0,
@@ -2497,14 +2497,14 @@
         "f":0.9992902768
       },
       "Number[psor]":{
-        "p":0.9375,
-        "r":0.9375,
-        "f":0.9375
       },
       "Poss":{
-        "p":1.0,
-        "r":0.995,
-        "f":0.9974937343
       },
       "Reflex":{
         "p":0.9975,
@@ -2517,9 +2517,9 @@
         "f":0.9896551724
       },
       "Animacy":{
-        "p":0.9634831461,
-        "r":0.9346049046,
-        "f":0.948824343
       },
       "Abbr":{
         "p":1.0,
@@ -2527,186 +2527,186 @@
         "f":1.0
       },
       "Foreign":{
-        "p":0.8947368421,
-        "r":0.4473684211,
-        "f":0.5964912281
       },
       "Gender[psor]":{
-        "p":0.9090909091,
         "r":0.9090909091,
-        "f":0.9090909091
       }
     },
-    "sents_p":0.9320113314,
-    "sents_r":0.9426934097,
-    "sents_f":0.9373219373,
-    "dep_uas":0.93363503,
-    "dep_las":0.9170251386,
     "dep_las_per_type":{
       "nsubj":{
-        "p":0.942804428,
-        "r":0.9560336763,
-        "f":0.949372968
       },
       "nmod":{
-        "p":0.8998951782,
-        "r":0.8850515464,
-        "f":0.8924116424
       },
       "root":{
-        "p":0.9437022901,
-        "r":0.9446036294,
-        "f":0.9441527446
       },
       "obj":{
-        "p":0.9335899904,
-        "r":0.9371980676,
-        "f":0.9353905497
       },
       "iobj":{
-        "p":0.8732394366,
-        "r":0.7209302326,
-        "f":0.7898089172
       },
       "case":{
-        "p":0.9897260274,
-        "r":0.9863481229,
-        "f":0.988034188
       },
       "cc":{
-        "p":0.9503546099,
-        "r":0.9447708578,
-        "f":0.947554508
       },
       "conj":{
-        "p":0.8023483366,
-        "r":0.8,
-        "f":0.8011724475
       },
       "mark":{
-        "p":0.9721115538,
-        "r":0.9721115538,
-        "f":0.9721115538
       },
       "obl":{
-        "p":0.9013806706,
-        "r":0.8984272608,
-        "f":0.8999015425
       },
       "nummod":{
-        "p":0.9423076923,
-        "r":0.9171122995,
-        "f":0.9295392954
       },
       "acl":{
-        "p":0.8353221957,
-        "r":0.8177570093,
-        "f":0.826446281
       },
       "amod":{
-        "p":0.9797830375,
-        "r":0.9895418327,
-        "f":0.9846382557
       },
       "aux":{
-        "p":0.9900552486,
-        "r":0.9900552486,
-        "f":0.9900552486
       },
       "det":{
-        "p":0.9719222462,
-        "r":0.9846827133,
-        "f":0.9782608696
       },
       "advmod":{
-        "p":0.8700209644,
-        "r":0.8718487395,
-        "f":0.870933893
       },
       "parataxis":{
-        "p":0.7,
         "r":0.6549707602,
-        "f":0.6767371601
       },
       "flat:name":{
-        "p":0.9681528662,
-        "r":0.987012987,
-        "f":0.9774919614
       },
       "cop":{
-        "p":0.9393939394,
-        "r":0.9482352941,
-        "f":0.943793911
       },
       "csubj":{
-        "p":0.8863636364,
-        "r":0.8764044944,
-        "f":0.8813559322
       },
       "expl":{
-        "p":0.9272151899,
-        "r":0.9391025641,
-        "f":0.9331210191
       },
       "xcomp":{
-        "p":0.9496855346,
-        "r":0.94375,
-        "f":0.9467084639
       },
       "ccomp":{
-        "p":0.9438202247,
-        "r":0.9130434783,
-        "f":0.9281767956
       },
       "appos":{
-        "p":0.5921052632,
-        "r":0.625,
-        "f":0.6081081081
       },
       "flat":{
-        "p":0.6086956522,
-        "r":0.7368421053,
-        "f":0.6666666667
       },
       "orphan":{
-        "p":0.6470588235,
-        "r":0.4583333333,
-        "f":0.5365853659
       },
       "advcl":{
-        "p":0.75,
-        "r":0.7285714286,
-        "f":0.7391304348
       },
       "fixed":{
-        "p":0.9090909091,
-        "r":0.9090909091,
-        "f":0.9090909091
       },
       "list":{
-        "p":0.7717391304,
         "r":0.8658536585,
-        "f":0.816091954
       },
       "flat:foreign":{
-        "p":0.625,
-        "r":0.625,
-        "f":0.625
-      },
-      "dep":{
-        "p":0.0344827586,
-        "r":0.1666666667,
-        "f":0.0571428571
       },
       "discourse":{
-        "p":0.6,
         "r":0.6428571429,
-        "f":0.6206896552
       },
       "vocative":{
-        "p":1.0,
         "r":0.2,
-        "f":0.3333333333
       },
       "cc:preconj":{
         "p":1.0,
@@ -2714,25 +2714,25 @@
         "f":0.8421052632
       }
     },
-    "lemma_acc":0.9679666631,
-    "ents_p":0.8841463415,
-    "ents_r":0.917721519,
-    "ents_f":0.900621118,
     "ents_per_type":{
       "ORG":{
-        "p":0.7692307692,
-        "r":0.75,
-        "f":0.7594936709
       },
       "PER":{
         "p":1.0,
-        "r":0.9833333333,
-        "f":0.9915966387
       },
       "LOC":{
-        "p":0.8666666667,
         "r":0.962962963,
-        "f":0.9122807018
       },
       "MISC":{
         "p":0.75,
@@ -2745,7 +2745,7 @@
         "f":0.6666666667
       }
     },
-    "speed":1211.6699495749
   },
   "sources":[
     {
@@ -2762,6 +2762,8 @@
     }
   ],
   "requirements":[
-    "spacy-transformers>=1.2.2,<1.3.0"
   ]
 }

 {
   "lang":"sl",
   "name":"core_news_trf",
+  "version":"3.7.2",
+  "description":"Slovenian transformer pipeline (Transformer(name='EMBEDDIA/sloberta', piece_encoder='camembert-sentencepiece', stride=128, type='camembert', width=768, window=168, vocab_size=32005)). Components: transformer, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner.",
   "author":"Explosion",
   "email":"contact@explosion.ai",
   "url":"https://explosion.ai",
   "license":"CC BY-SA 4.0",
+  "spacy_version":">=3.7.0,<3.8.0",
+  "spacy_git_version":"6b4f77441",
   "vectors":{
     "width":0,
     "vectors":0,
     "token_p":0.9980762654,
     "token_r":0.9956925964,
     "token_f":0.996883006,
+    "tag_acc":0.9802329309,
+    "pos_acc":0.9908323539,
+    "morph_acc":0.981857036,
+    "morph_micro_p":0.9914889164,
+    "morph_micro_r":0.9903661893,
+    "morph_micro_f":0.9909272349,
     "morph_per_feat":{
       "Case":{
+        "p":0.9859446052,
+        "r":0.9863523573,
+        "f":0.9861484391
       },
       "Gender":{
+        "p":0.986196464,
+        "r":0.9870363361,
+        "f":0.9866162213
       },
       "Number":{
+        "p":0.9937587767,
+        "r":0.9943793911,
+        "f":0.994068987
       },
       "Aspect":{
+        "p":0.9906439185,
+        "r":0.9950248756,
+        "f":0.9928295643
       },
       "Mood":{
+        "p":0.9955927721,
+        "r":0.995154185,
+        "f":0.9953734303
       },
       "Person":{
+        "p":0.9984095427,
+        "r":0.9976162098,
+        "f":0.9980127186
       },
       "Tense":{
+        "p":0.9985436893,
+        "r":0.9956437561,
+        "f":0.9970916142
       },
       "VerbForm":{
+        "p":0.9986772487,
+        "r":0.9973579921,
+        "f":0.9980171844
       },
       "PronType":{
+        "p":0.9948420374,
         "r":0.995483871,
+        "f":0.9951628507
       },
       "Variant":{
         "p":0.9981412639,
       },
       "NumForm":{
         "p":1.0,
+        "r":0.9681528662,
+        "f":0.9838187702
       },
       "NumType":{
         "p":1.0,
+        "r":0.9710982659,
+        "f":0.9853372434
       },
       "Degree":{
+        "p":0.9937268321,
+        "r":0.9917472965,
+        "f":0.9927360775
       },
       "Polarity":{
         "p":1.0,
         "f":0.9992902768
       },
       "Number[psor]":{
+        "p":0.9583333333,
+        "r":0.9583333333,
+        "f":0.9583333333
       },
       "Poss":{
+        "p":0.9949748744,
+        "r":0.99,
+        "f":0.992481203
       },
       "Reflex":{
         "p":0.9975,
         "f":0.9896551724
       },
       "Animacy":{
+        "p":0.9630681818,
+        "r":0.9237057221,
+        "f":0.9429763561
       },
       "Abbr":{
         "p":1.0,
         "f":1.0
       },
       "Foreign":{
+        "p":1.0,
+        "r":0.3947368421,
+        "f":0.5660377358
       },
       "Gender[psor]":{
+        "p":0.9375,
         "r":0.9090909091,
+        "f":0.9230769231
       }
     },
+    "sents_p":0.9208566108,
+    "sents_r":0.9446036294,
+    "sents_f":0.9325789722,
+    "dep_uas":0.9361807921,
+    "dep_las":0.9223081322,
     "dep_las_per_type":{
       "nsubj":{
+        "p":0.9579831933,
+        "r":0.9597754911,
+        "f":0.9588785047
       },
       "nmod":{
+        "p":0.8976744186,
+        "r":0.8953608247,
+        "f":0.896516129
       },
       "root":{
+        "p":0.9408960915,
+        "r":0.9426934097,
+        "f":0.9417938931
       },
       "obj":{
+        "p":0.9537126326,
+        "r":0.9555555556,
+        "f":0.9546332046
       },
       "iobj":{
+        "p":0.8441558442,
+        "r":0.7558139535,
+        "f":0.7975460123
       },
       "case":{
+        "p":0.9897128161,
+        "r":0.9850682594,
+        "f":0.9873850759
       },
       "cc":{
+        "p":0.9610849057,
+        "r":0.9576968273,
+        "f":0.9593878752
       },
       "conj":{
+        "p":0.820909971,
+        "r":0.8273170732,
+        "f":0.824101069
       },
       "mark":{
+        "p":0.9654255319,
+        "r":0.9641434263,
+        "f":0.9647840532
       },
       "obl":{
+        "p":0.923128793,
+        "r":0.8971166448,
+        "f":0.9099368561
       },
       "nummod":{
+        "p":0.9453551913,
+        "r":0.9251336898,
+        "f":0.9351351351
       },
       "acl":{
+        "p":0.8486997636,
+        "r":0.8387850467,
+        "f":0.8437132785
       },
       "amod":{
+        "p":0.9846000994,
+        "r":0.9870517928,
+        "f":0.9858244218
       },
       "aux":{
+        "p":0.9911406423,
+        "r":0.9889502762,
+        "f":0.9900442478
       },
       "det":{
+        "p":0.9739696312,
+        "r":0.9824945295,
+        "f":0.9782135076
       },
       "advmod":{
+        "p":0.8706004141,
+        "r":0.8834033613,
+        "f":0.8769551616
       },
       "parataxis":{
+        "p":0.6892307692,
         "r":0.6549707602,
+        "f":0.6716641679
       },
       "flat:name":{
+        "p":0.9741935484,
+        "r":0.9805194805,
+        "f":0.9773462783
       },
       "cop":{
+        "p":0.9443155452,
+        "r":0.9576470588,
+        "f":0.9509345794
       },
       "csubj":{
+        "p":0.9101123596,
+        "r":0.9101123596,
+        "f":0.9101123596
       },
       "expl":{
+        "p":0.961414791,
+        "r":0.9583333333,
+        "f":0.9598715891
       },
       "xcomp":{
+        "p":0.9440993789,
+        "r":0.95,
+        "f":0.9470404984
       },
       "ccomp":{
+        "p":0.9184782609,
+        "r":0.9184782609,
+        "f":0.9184782609
+      },
+      "dep":{
+        "p":0.0465116279,
+        "r":0.3333333333,
+        "f":0.0816326531
       },
       "appos":{
+        "p":0.6258503401,
+        "r":0.6388888889,
+        "f":0.6323024055
       },
       "flat":{
+        "p":0.7647058824,
+        "r":0.6842105263,
+        "f":0.7222222222
       },
       "orphan":{
+        "p":0.6478873239,
+        "r":0.4791666667,
+        "f":0.5508982036
       },
       "advcl":{
+        "p":0.7486910995,
+        "r":0.680952381,
+        "f":0.7132169576
       },
       "fixed":{
+        "p":0.9393939394,
+        "r":0.9393939394,
+        "f":0.9393939394
       },
       "list":{
+        "p":0.7553191489,
         "r":0.8658536585,
+        "f":0.8068181818
       },
       "flat:foreign":{
+        "p":0.6666666667,
+        "r":0.5,
+        "f":0.5714285714
       },
       "discourse":{
+        "p":0.9,
         "r":0.6428571429,
+        "f":0.75
       },
       "vocative":{
+        "p":0.5,
         "r":0.2,
+        "f":0.2857142857
       },
       "cc:preconj":{
         "p":1.0,
         "f":0.8421052632
       }
     },
+    "lemma_acc":0.9694198098,
+    "ents_p":0.9316770186,
+    "ents_r":0.9493670886,
+    "ents_f":0.9404388715,
     "ents_per_type":{
       "ORG":{
+        "p":0.9189189189,
+        "r":0.85,
+        "f":0.8831168831
       },
       "PER":{
         "p":1.0,
+        "r":1.0,
+        "f":1.0
       },
       "LOC":{
+        "p":0.8965517241,
         "r":0.962962963,
+        "f":0.9285714286
       },
       "MISC":{
         "p":0.75,
         "f":0.6666666667
       }
     },
+    "speed":1008.1462815944
   },
   "sources":[
     {
     }
   ],
   "requirements":[
+    "spacy-curated-transformers>=0.2.0,<0.3.0",
+    "sentencepiece>=0.1.91,!=0.1.92",
+    "protobuf<3.21.0"
   ]
 }

morphologizer/model CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f127e8db060afb095771948c1f1169cdd75ad5cc151cbe45eef8108fee2d6c64
-size 3685701

 version https://git-lfs.github.com/spec/v1
+oid sha256:9fd5c4e3dfa2bf6ac7368e61cc7e7f34c447fe5af9972651441bc88cf783d0c4
+size 3685785

ner/model CHANGED Viewed

Binary files a/ner/model and b/ner/model differ

parser/model CHANGED Viewed

Binary files a/parser/model and b/parser/model differ

sl_core_news_trf-any-py3-none-any.whl CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8094b2c2b4d2024a05f1795e2a63606e8bb221b4c7bb6e44ee45745553beb622
-size 419759778

 version https://git-lfs.github.com/spec/v1
+oid sha256:bcfce7fb9b5f08c87011d7ff65856a1ce19a53a75f5ac7570d0394037d1b4324
+size 416542321

tagger/model CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9025c664e957b190cd343d24b394f2116951af02d47114ac192841ca6bf08fa1
-size 3458077

 version https://git-lfs.github.com/spec/v1
+oid sha256:2916216093dd41cd67a8cbebb98b4c38fed6b3705bc36bd039f7c62ce82524b7
+size 3458161

transformer/cfg CHANGED Viewed

@@ -1,3 +1,3 @@
 {
-  "max_batch_items":4096
 }


1	{
2	+
3	}

transformer/model CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87995fccfad76c91bee71fe2efd21082db30dfbc59ce9dbe5bfc80b4d99972b1
-size 445707181

 version https://git-lfs.github.com/spec/v1
+oid sha256:72f89ebe7ab0349486b2a256def9def699e785b561ea1058882674d230ecffc0
+size 440984165

vocab/strings.json CHANGED Viewed

The diff for this file is too large to render. See raw diff