Update spaCy pipeline

Browse files

Files changed (11) hide show

README.md +28 -28
accuracy.json +159 -159
ca_core_news_trf-any-py3-none-any.whl +2 -2
config.cfg +51 -24
meta.json +164 -164
morphologizer/model +2 -2
ner/model +2 -2
parser/model +2 -2
transformer/cfg +1 -1
transformer/model +2 -2
vocab/strings.json +2 -2

README.md CHANGED Viewed

@@ -14,72 +14,72 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.9222476315
     - name: NER Recall
       type: recall
-      value: 0.9132966677
     - name: NER F Score
       type: f_score
-      value: 0.9177503251
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9633641507
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9633641507
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9571111935
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.9816802448
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.9484123582
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.930752303
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
-      value: 0.9926750659
 ---
 ### Details: https://spacy.io/models/ca#ca_core_news_trf
-Catalan transformer pipeline (projecte-aina/roberta-base-ca-v2). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer.
 | Feature | Description |
 | --- | --- |
 | **Name** | `ca_core_news_trf` |
-| **Version** | `3.6.1` |
-| **spaCy** | `>=3.6.0,<3.7.0` |
 | **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
 | **Components** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
 | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -109,18 +109,18 @@ Catalan transformer pipeline (projecte-aina/roberta-base-ca-v2). Components: tra
 | `TOKEN_P` | 99.78 |
 | `TOKEN_R` | 99.79 |
 | `TOKEN_F` | 99.79 |
-| `POS_ACC` | 96.34 |
-| `MORPH_ACC` | 95.71 |
-| `MORPH_MICRO_P` | 99.41 |
-| `MORPH_MICRO_R` | 98.46 |
-| `MORPH_MICRO_F` | 98.93 |
-| `SENTS_P` | 99.41 |
-| `SENTS_R` | 99.12 |
-| `SENTS_F` | 99.27 |
-| `DEP_UAS` | 94.84 |
-| `DEP_LAS` | 93.08 |
-| `TAG_ACC` | 96.34 |
-| `LEMMA_ACC` | 98.17 |
-| `ENTS_P` | 92.22 |
-| `ENTS_R` | 91.33 |
-| `ENTS_F` | 91.78 |

     metrics:
     - name: NER Precision
       type: precision
+      value: 0.9225996081
     - name: NER Recall
       type: recall
+      value: 0.9139437075
     - name: NER F Score
       type: f_score
+      value: 0.9182512595
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
+      value: 0.9918845029
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
+      value: 0.9918845029
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
+      value: 0.9900646831
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
+      value: 0.9819043924
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
+      value: 0.9522584579
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
+      value: 0.9367199558
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
+      value: 0.9938506589
 ---
 ### Details: https://spacy.io/models/ca#ca_core_news_trf
+Catalan transformer pipeline (Transformer(name='projecte-aina/roberta-base-ca-v2', piece_encoder='byte-bpe', stride=112, type='roberta', width=768, window=144, vocab_size=50262)). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer.
 | Feature | Description |
 | --- | --- |
 | **Name** | `ca_core_news_trf` |
+| **Version** | `3.7.2` |
+| **spaCy** | `>=3.7.0,<3.8.0` |
 | **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
 | **Components** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
 | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
 | `TOKEN_P` | 99.78 |
 | `TOKEN_R` | 99.79 |
 | `TOKEN_F` | 99.79 |
+| `POS_ACC` | 99.19 |
+| `MORPH_ACC` | 99.01 |
+| `MORPH_MICRO_P` | 99.74 |
+| `MORPH_MICRO_R` | 99.49 |
+| `MORPH_MICRO_F` | 99.62 |
+| `SENTS_P` | 99.47 |
+| `SENTS_R` | 99.30 |
+| `SENTS_F` | 99.39 |
+| `DEP_UAS` | 95.23 |
+| `DEP_LAS` | 93.67 |
+| `TAG_ACC` | 99.19 |
+| `LEMMA_ACC` | 98.19 |
+| `ENTS_P` | 92.26 |
+| `ENTS_R` | 91.39 |
+| `ENTS_F` | 91.83 |

accuracy.json CHANGED Viewed

@@ -3,11 +3,11 @@
   "token_p": 0.9978112128,
   "token_r": 0.9979488063,
   "token_f": 0.9978800048,
-  "pos_acc": 0.9633641507,
-  "morph_acc": 0.9571111935,
-  "morph_micro_p": 0.9940523354,
-  "morph_micro_r": 0.9845527244,
-  "morph_micro_f": 0.9892797253,
   "morph_per_feat": {
     "Mood": {
       "p": 0.9982771351,
@@ -15,69 +15,69 @@
       "f": 0.9981543005
     },
     "Number": {
-      "p": 0.9987333068,
-      "r": 0.9904173994,
-      "f": 0.9945579702
     },
     "Person": {
-      "p": 0.9989373007,
       "r": 0.9973474801,
-      "f": 0.9981417574
     },
     "Tense": {
-      "p": 0.9933082392,
-      "r": 0.9960159363,
-      "f": 0.994660245
     },
     "VerbForm": {
-      "p": 0.9972026109,
-      "r": 0.9972026109,
-      "f": 0.9972026109
     },
     "Gender": {
-      "p": 0.9965883614,
-      "r": 0.9846865068,
-      "f": 0.9906016859
     },
     "NumType": {
-      "p": 0.9688385269,
-      "r": 0.9670122526,
-      "f": 0.9679245283
     },
     "Definite": {
-      "p": 0.9969747391,
-      "r": 0.9709781968,
-      "f": 0.9838047615
     },
     "PronType": {
-      "p": 0.9963973237,
-      "r": 0.9810810811,
-      "f": 0.9886798877
     },
     "PunctType": {
-      "p": 0.9537174721,
-      "r": 0.9356309263,
-      "f": 0.9445876289
     },
     "NumForm": {
-      "p": 0.9832167832,
-      "r": 0.9873595506,
-      "f": 0.9852838122
     },
     "Polarity": {
       "p": 1.0,
-      "r": 0.9870550162,
-      "f": 0.993485342
     },
     "Case": {
-      "p": 0.9974958264,
-      "r": 0.9950041632,
-      "f": 0.9962484368
     },
     "PrepCase": {
-      "p": 0.9972413793,
       "r": 0.9986187845,
-      "f": 0.9979296066
     },
     "Reflex": {
       "p": 0.9986052999,
@@ -86,165 +86,165 @@
     },
     "Degree": {
       "p": 1.0,
-      "r": 0.9893992933,
-      "f": 0.9946714032
     },
     "Poss": {
       "p": 1.0,
-      "r": 0.9886039886,
-      "f": 0.994269341
     },
     "AdvType": {
-      "p": 0.9847328244,
-      "r": 0.9416058394,
-      "f": 0.9626865672
     },
     "PunctSide": {
-      "p": 0.8588807786,
-      "r": 0.8526570048,
-      "f": 0.8557575758
     },
     "Number[psor]": {
-      "p": 1.0,
       "r": 1.0,
-      "f": 1.0
     },
     "Polite": {
       "p": 1.0,
-      "r": 0.75,
-      "f": 0.8571428571
     }
   },
-  "sents_p": 0.9941314554,
-  "sents_r": 0.9912229374,
-  "sents_f": 0.9926750659,
-  "dep_uas": 0.9484123582,
-  "dep_las": 0.930752303,
   "dep_las_per_type": {
     "nsubj": {
-      "p": 0.9565067311,
-      "r": 0.9545297968,
-      "f": 0.9555172414
     },
     "flat": {
-      "p": 0.9405940594,
-      "r": 0.9344262295,
-      "f": 0.9375
     },
     "case": {
-      "p": 0.9791868345,
-      "r": 0.9729469761,
-      "f": 0.9760569326
     },
     "aux": {
-      "p": 0.9641519529,
-      "r": 0.9620928991,
-      "f": 0.9631213255
     },
     "root": {
-      "p": 0.9700704225,
-      "r": 0.9672322996,
-      "f": 0.9686492822
     },
     "nummod": {
-      "p": 0.9240282686,
-      "r": 0.9207746479,
-      "f": 0.9223985891
     },
     "obj": {
-      "p": 0.9109390126,
-      "r": 0.9328376704,
-      "f": 0.9217582956
     },
     "det": {
-      "p": 0.9860365199,
-      "r": 0.9856130556,
-      "f": 0.9858247423
     },
     "nmod": {
-      "p": 0.8819821778,
-      "r": 0.8691368601,
-      "f": 0.8755124056
     },
     "amod": {
-      "p": 0.9623210249,
-      "r": 0.9637735849,
-      "f": 0.9630467572
     },
     "obl": {
-      "p": 0.8178421298,
-      "r": 0.7973588342,
-      "f": 0.8074706018
     },
     "cc": {
-      "p": 0.955,
-      "r": 0.9628229364,
-      "f": 0.958895513
     },
     "fixed": {
-      "p": 0.9290640394,
-      "r": 0.9373757455,
-      "f": 0.9332013855
     },
     "conj": {
-      "p": 0.8430821147,
-      "r": 0.8585337915,
-      "f": 0.850737798
     },
     "advmod": {
-      "p": 0.898816568,
-      "r": 0.8841676368,
-      "f": 0.8914319249
     },
     "advcl": {
-      "p": 0.7384987893,
-      "r": 0.7625,
-      "f": 0.7503075031
     },
     "compound": {
-      "p": 0.9074074074,
-      "r": 0.8844765343,
-      "f": 0.8957952468
     },
     "mark": {
-      "p": 0.9359720605,
-      "r": 0.9409011118,
-      "f": 0.9384301138
     },
     "cop": {
-      "p": 0.8928571429,
-      "r": 0.9199134199,
-      "f": 0.9061833689
     },
     "ccomp": {
-      "p": 0.8586956522,
-      "r": 0.8836689038,
-      "f": 0.8710033076
     },
     "acl": {
-      "p": 0.8649951784,
-      "r": 0.8641618497,
-      "f": 0.8645783133
     },
     "expl:pass": {
-      "p": 0.6818181818,
-      "r": 0.652173913,
-      "f": 0.6666666667
     },
     "appos": {
-      "p": 0.8253164557,
-      "r": 0.8295165394,
-      "f": 0.8274111675
     },
     "xcomp": {
-      "p": 0.8886255924,
-      "r": 0.8802816901,
-      "f": 0.8844339623
     },
     "iobj": {
-      "p": 0.8529411765,
-      "r": 0.7754010695,
-      "f": 0.81232493
     },
     "dep": {
       "p": 0.0,
@@ -252,14 +252,14 @@
       "f": 0.0
     },
     "csubj": {
-      "p": 0.8269230769,
-      "r": 0.8113207547,
-      "f": 0.819047619
     },
     "parataxis": {
-      "p": 0.8571428571,
-      "r": 0.5294117647,
-      "f": 0.6545454545
     },
     "nsubj:pass": {
       "p": 0.0,
@@ -272,32 +272,32 @@
       "f": 0.0
     }
   },
-  "tag_acc": 0.9633641507,
-  "lemma_acc": 0.9816802448,
-  "ents_p": 0.9222476315,
-  "ents_r": 0.9132966677,
-  "ents_f": 0.9177503251,
   "ents_per_type": {
     "ORG": {
-      "p": 0.9086799277,
-      "r": 0.9062218215,
-      "f": 0.9074492099
     },
     "LOC": {
-      "p": 0.9441401972,
-      "r": 0.9248927039,
-      "f": 0.9344173442
     },
     "MISC": {
-      "p": 0.837398374,
-      "r": 0.8067885117,
-      "f": 0.8218085106
     },
     "PER": {
-      "p": 0.9613670134,
-      "r": 0.9700149925,
-      "f": 0.9656716418
     }
   },
-  "speed": 2440.4721637988
 }

   "token_p": 0.9978112128,
   "token_r": 0.9979488063,
   "token_f": 0.9978800048,
+  "pos_acc": 0.9918845029,
+  "morph_acc": 0.9900646831,
+  "morph_micro_p": 0.997430458,
+  "morph_micro_r": 0.9948740873,
+  "morph_micro_f": 0.9961506326,
   "morph_per_feat": {
     "Mood": {
       "p": 0.9982771351,
       "f": 0.9981543005
     },
     "Number": {
+      "p": 0.998884531,
+      "r": 0.9963033413,
+      "f": 0.9975922665
     },
     "Person": {
+      "p": 0.9987604038,
       "r": 0.9973474801,
+      "f": 0.9980534419
     },
     "Tense": {
+      "p": 0.9937251621,
+      "r": 0.9962256238,
+      "f": 0.994973822
     },
     "VerbForm": {
+      "p": 0.9977330311,
+      "r": 0.9966697749,
+      "f": 0.9972011196
     },
     "Gender": {
+      "p": 0.9973378509,
+      "r": 0.9922469421,
+      "f": 0.9947858833
     },
     "NumType": {
+      "p": 0.9706439394,
+      "r": 0.9660697455,
+      "f": 0.9683514407
     },
     "Definite": {
+      "p": 0.9971922565,
+      "r": 0.9941072481,
+      "f": 0.9956473626
     },
     "PronType": {
+      "p": 0.9965301286,
+      "r": 0.9945101351,
+      "f": 0.9955191072
     },
     "PunctType": {
+      "p": 0.9998172181,
+      "r": 0.9974471189,
+      "f": 0.9986307622
     },
     "NumForm": {
+      "p": 0.9819193324,
+      "r": 0.9915730337,
+      "f": 0.9867225716
     },
     "Polarity": {
       "p": 1.0,
+      "r": 0.9902912621,
+      "f": 0.9951219512
     },
     "Case": {
+      "p": 0.9991652755,
+      "r": 0.9966694421,
+      "f": 0.9979157982
     },
     "PrepCase": {
+      "p": 0.9986187845,
       "r": 0.9986187845,
+      "f": 0.9986187845
     },
     "Reflex": {
       "p": 0.9986052999,
     },
     "Degree": {
       "p": 1.0,
+      "r": 0.9929328622,
+      "f": 0.9964539007
     },
     "Poss": {
       "p": 1.0,
+      "r": 0.9914529915,
+      "f": 0.9957081545
     },
     "AdvType": {
+      "p": 0.9921875,
+      "r": 0.9270072993,
+      "f": 0.958490566
     },
     "PunctSide": {
+      "p": 0.9975845411,
+      "r": 0.9975845411,
+      "f": 0.9975845411
     },
     "Number[psor]": {
+      "p": 0.9411764706,
       "r": 1.0,
+      "f": 0.9696969697
     },
     "Polite": {
       "p": 1.0,
+      "r": 1.0,
+      "f": 1.0
     }
   },
+  "sents_p": 0.9947245018,
+  "sents_r": 0.9929783499,
+  "sents_f": 0.9938506589,
+  "dep_uas": 0.9522584579,
+  "dep_las": 0.9367199558,
   "dep_las_per_type": {
     "nsubj": {
+      "p": 0.9610479145,
+      "r": 0.9603858078,
+      "f": 0.9607167471
     },
     "flat": {
+      "p": 0.9334415584,
+      "r": 0.9426229508,
+      "f": 0.9380097879
     },
     "case": {
+      "p": 0.9792044493,
+      "r": 0.9737886257,
+      "f": 0.9764890282
     },
     "aux": {
+      "p": 0.9695512821,
+      "r": 0.9690336359,
+      "f": 0.9692923899
     },
     "root": {
+      "p": 0.9730363423,
+      "r": 0.9713282621,
+      "f": 0.972181552
     },
     "nummod": {
+      "p": 0.9326241135,
+      "r": 0.926056338,
+      "f": 0.9293286219
     },
     "obj": {
+      "p": 0.931773399,
+      "r": 0.9375464684,
+      "f": 0.9346510191
     },
     "det": {
+      "p": 0.9877590465,
+      "r": 0.9876529955,
+      "f": 0.9877060181
     },
     "nmod": {
+      "p": 0.8882657463,
+      "r": 0.8819875776,
+      "f": 0.8851155293
     },
     "amod": {
+      "p": 0.9682539683,
+      "r": 0.9667924528,
+      "f": 0.9675226586
     },
     "obl": {
+      "p": 0.8433286843,
+      "r": 0.8260473588,
+      "f": 0.8345985737
     },
     "cc": {
+      "p": 0.9579145729,
+      "r": 0.9609325772,
+      "f": 0.9594212016
     },
     "fixed": {
+      "p": 0.932938856,
+      "r": 0.9403578529,
+      "f": 0.9366336634
     },
     "conj": {
+      "p": 0.8519153802,
+      "r": 0.8533791523,
+      "f": 0.8526466381
     },
     "advmod": {
+      "p": 0.8939393939,
+      "r": 0.8928987194,
+      "f": 0.8934187536
     },
     "advcl": {
+      "p": 0.7478684531,
+      "r": 0.7675,
+      "f": 0.7575570635
     },
     "compound": {
+      "p": 0.897810219,
+      "r": 0.8880866426,
+      "f": 0.8929219601
     },
     "mark": {
+      "p": 0.9427235535,
+      "r": 0.9438267993,
+      "f": 0.9432748538
     },
     "cop": {
+      "p": 0.9002123142,
+      "r": 0.9177489177,
+      "f": 0.9088960343
     },
     "ccomp": {
+      "p": 0.8777292576,
+      "r": 0.8993288591,
+      "f": 0.8883977901
     },
     "acl": {
+      "p": 0.8672397326,
+      "r": 0.8747591522,
+      "f": 0.8709832134
     },
     "expl:pass": {
+      "p": 0.8611111111,
+      "r": 0.6739130435,
+      "f": 0.756097561
     },
     "appos": {
+      "p": 0.8524590164,
+      "r": 0.8600508906,
+      "f": 0.8562381254
     },
     "xcomp": {
+      "p": 0.9128329298,
+      "r": 0.8849765258,
+      "f": 0.8986889154
     },
     "iobj": {
+      "p": 0.8670520231,
+      "r": 0.8021390374,
+      "f": 0.8333333333
     },
     "dep": {
       "p": 0.0,
       "f": 0.0
     },
     "csubj": {
+      "p": 0.8125,
+      "r": 0.858490566,
+      "f": 0.8348623853
     },
     "parataxis": {
+      "p": 0.8461538462,
+      "r": 0.6470588235,
+      "f": 0.7333333333
     },
     "nsubj:pass": {
       "p": 0.0,
       "f": 0.0
     }
   },
+  "tag_acc": 0.9918845029,
+  "lemma_acc": 0.9819043924,
+  "ents_p": 0.9225996081,
+  "ents_r": 0.9139437075,
+  "ents_f": 0.9182512595,
   "ents_per_type": {
     "ORG": {
+      "p": 0.9112107623,
+      "r": 0.9161406673,
+      "f": 0.9136690647
     },
     "LOC": {
+      "p": 0.9353778751,
+      "r": 0.9163090129,
+      "f": 0.9257452575
     },
     "MISC": {
+      "p": 0.8539944904,
+      "r": 0.8093994778,
+      "f": 0.8310991957
     },
     "PER": {
+      "p": 0.9612518629,
+      "r": 0.9670164918,
+      "f": 0.9641255605
     }
   },
+  "speed": 1944.0672670287
 }

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334c4784bfa81b8608901ca77618b322ff24118a4350131a5009f6dcb593d32d
-size 459879407

 version https://git-lfs.github.com/spec/v1
+oid sha256:4bbc29626e73283096a70097b307e9c898878c6b005648f0bfa89b736345c672
+size 457100783

config.cfg CHANGED Viewed

@@ -17,6 +17,7 @@ after_creation = null
 after_pipeline_creation = null
 batch_size = 64
 tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
 [components]
@@ -45,10 +46,11 @@ 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"
@@ -67,10 +69,11 @@ 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"
@@ -90,32 +93,44 @@ 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.transformer]
-factory = "transformer"
-max_batch_items = 4096
-set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
 [components.transformer.model]
-name = "projecte-aina/roberta-base-ca-v2"
-@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]
@@ -152,11 +167,11 @@ 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"
@@ -227,6 +242,18 @@ require = false
 path = "corpus/labels/parser.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.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.transformer]
+factory = "curated_transformer"
+all_layer_outputs = false
+frozen = false
 [components.transformer.model]
+@architectures = "spacy-curated-transformers.RobertaTransformer.v1"
+vocab_size = 50262
+hidden_width = 768
+piece_encoder = {"@architectures":"spacy-curated-transformers.ByteBpeEncoder.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
+torchscript = false
 mixed_precision = false
+wrapped_listener = null
 [components.transformer.model.grad_scaler_config]
+[components.transformer.model.with_spans]
+@architectures = "spacy-curated-transformers.WithStridedSpans.v1"
+stride = 112
+window = 144
+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/parser.json"
 require = false
+[initialize.components.transformer]
+[initialize.components.transformer.encoder_loader]
+@model_loaders = "spacy-curated-transformers.HFTransformerEncoderLoader.v1"
+name = "projecte-aina/roberta-base-ca-v2"
+revision = "main"
+[initialize.components.transformer.piecer_loader]
+@model_loaders = "spacy-curated-transformers.HFPieceEncoderLoader.v1"
+name = "projecte-aina/roberta-base-ca-v2"
+revision = "main"
 [initialize.lookups]
 @misc = "spacy.LookupsDataLoader.v1"
 lang = ${nlp.lang}

meta.json CHANGED Viewed

@@ -1,14 +1,14 @@
 {
   "lang":"ca",
   "name":"core_news_trf",
-  "version":"3.6.1",
-  "description":"Catalan transformer pipeline (projecte-aina/roberta-base-ca-v2). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer.",
   "author":"Explosion",
   "email":"contact@explosion.ai",
   "url":"https://explosion.ai",
   "license":"GNU GPL 3.0",
-  "spacy_version":">=3.6.0,<3.7.0",
-  "spacy_git_version":"c067b5264",
   "vectors":{
     "width":0,
     "vectors":0,
@@ -372,11 +372,11 @@
     "token_p":0.9978112128,
     "token_r":0.9979488063,
     "token_f":0.9978800048,
-    "pos_acc":0.9633641507,
-    "morph_acc":0.9571111935,
-    "morph_micro_p":0.9940523354,
-    "morph_micro_r":0.9845527244,
-    "morph_micro_f":0.9892797253,
     "morph_per_feat":{
       "Mood":{
         "p":0.9982771351,
@@ -384,69 +384,69 @@
         "f":0.9981543005
       },
       "Number":{
-        "p":0.9987333068,
-        "r":0.9904173994,
-        "f":0.9945579702
       },
       "Person":{
-        "p":0.9989373007,
         "r":0.9973474801,
-        "f":0.9981417574
       },
       "Tense":{
-        "p":0.9933082392,
-        "r":0.9960159363,
-        "f":0.994660245
       },
       "VerbForm":{
-        "p":0.9972026109,
-        "r":0.9972026109,
-        "f":0.9972026109
       },
       "Gender":{
-        "p":0.9965883614,
-        "r":0.9846865068,
-        "f":0.9906016859
       },
       "NumType":{
-        "p":0.9688385269,
-        "r":0.9670122526,
-        "f":0.9679245283
       },
       "Definite":{
-        "p":0.9969747391,
-        "r":0.9709781968,
-        "f":0.9838047615
       },
       "PronType":{
-        "p":0.9963973237,
-        "r":0.9810810811,
-        "f":0.9886798877
       },
       "PunctType":{
-        "p":0.9537174721,
-        "r":0.9356309263,
-        "f":0.9445876289
       },
       "NumForm":{
-        "p":0.9832167832,
-        "r":0.9873595506,
-        "f":0.9852838122
       },
       "Polarity":{
         "p":1.0,
-        "r":0.9870550162,
-        "f":0.993485342
       },
       "Case":{
-        "p":0.9974958264,
-        "r":0.9950041632,
-        "f":0.9962484368
       },
       "PrepCase":{
-        "p":0.9972413793,
         "r":0.9986187845,
-        "f":0.9979296066
       },
       "Reflex":{
         "p":0.9986052999,
@@ -455,165 +455,165 @@
       },
       "Degree":{
         "p":1.0,
-        "r":0.9893992933,
-        "f":0.9946714032
       },
       "Poss":{
         "p":1.0,
-        "r":0.9886039886,
-        "f":0.994269341
       },
       "AdvType":{
-        "p":0.9847328244,
-        "r":0.9416058394,
-        "f":0.9626865672
       },
       "PunctSide":{
-        "p":0.8588807786,
-        "r":0.8526570048,
-        "f":0.8557575758
       },
       "Number[psor]":{
-        "p":1.0,
         "r":1.0,
-        "f":1.0
       },
       "Polite":{
         "p":1.0,
-        "r":0.75,
-        "f":0.8571428571
       }
     },
-    "sents_p":0.9941314554,
-    "sents_r":0.9912229374,
-    "sents_f":0.9926750659,
-    "dep_uas":0.9484123582,
-    "dep_las":0.930752303,
     "dep_las_per_type":{
       "nsubj":{
-        "p":0.9565067311,
-        "r":0.9545297968,
-        "f":0.9555172414
       },
       "flat":{
-        "p":0.9405940594,
-        "r":0.9344262295,
-        "f":0.9375
       },
       "case":{
-        "p":0.9791868345,
-        "r":0.9729469761,
-        "f":0.9760569326
       },
       "aux":{
-        "p":0.9641519529,
-        "r":0.9620928991,
-        "f":0.9631213255
       },
       "root":{
-        "p":0.9700704225,
-        "r":0.9672322996,
-        "f":0.9686492822
       },
       "nummod":{
-        "p":0.9240282686,
-        "r":0.9207746479,
-        "f":0.9223985891
       },
       "obj":{
-        "p":0.9109390126,
-        "r":0.9328376704,
-        "f":0.9217582956
       },
       "det":{
-        "p":0.9860365199,
-        "r":0.9856130556,
-        "f":0.9858247423
       },
       "nmod":{
-        "p":0.8819821778,
-        "r":0.8691368601,
-        "f":0.8755124056
       },
       "amod":{
-        "p":0.9623210249,
-        "r":0.9637735849,
-        "f":0.9630467572
       },
       "obl":{
-        "p":0.8178421298,
-        "r":0.7973588342,
-        "f":0.8074706018
       },
       "cc":{
-        "p":0.955,
-        "r":0.9628229364,
-        "f":0.958895513
       },
       "fixed":{
-        "p":0.9290640394,
-        "r":0.9373757455,
-        "f":0.9332013855
       },
       "conj":{
-        "p":0.8430821147,
-        "r":0.8585337915,
-        "f":0.850737798
       },
       "advmod":{
-        "p":0.898816568,
-        "r":0.8841676368,
-        "f":0.8914319249
       },
       "advcl":{
-        "p":0.7384987893,
-        "r":0.7625,
-        "f":0.7503075031
       },
       "compound":{
-        "p":0.9074074074,
-        "r":0.8844765343,
-        "f":0.8957952468
       },
       "mark":{
-        "p":0.9359720605,
-        "r":0.9409011118,
-        "f":0.9384301138
       },
       "cop":{
-        "p":0.8928571429,
-        "r":0.9199134199,
-        "f":0.9061833689
       },
       "ccomp":{
-        "p":0.8586956522,
-        "r":0.8836689038,
-        "f":0.8710033076
       },
       "acl":{
-        "p":0.8649951784,
-        "r":0.8641618497,
-        "f":0.8645783133
       },
       "expl:pass":{
-        "p":0.6818181818,
-        "r":0.652173913,
-        "f":0.6666666667
       },
       "appos":{
-        "p":0.8253164557,
-        "r":0.8295165394,
-        "f":0.8274111675
       },
       "xcomp":{
-        "p":0.8886255924,
-        "r":0.8802816901,
-        "f":0.8844339623
       },
       "iobj":{
-        "p":0.8529411765,
-        "r":0.7754010695,
-        "f":0.81232493
       },
       "dep":{
         "p":0.0,
@@ -621,14 +621,14 @@
         "f":0.0
       },
       "csubj":{
-        "p":0.8269230769,
-        "r":0.8113207547,
-        "f":0.819047619
       },
       "parataxis":{
-        "p":0.8571428571,
-        "r":0.5294117647,
-        "f":0.6545454545
       },
       "nsubj:pass":{
         "p":0.0,
@@ -641,34 +641,34 @@
         "f":0.0
       }
     },
-    "tag_acc":0.9633641507,
-    "lemma_acc":0.9816802448,
-    "ents_p":0.9222476315,
-    "ents_r":0.9132966677,
-    "ents_f":0.9177503251,
     "ents_per_type":{
       "ORG":{
-        "p":0.9086799277,
-        "r":0.9062218215,
-        "f":0.9074492099
       },
       "LOC":{
-        "p":0.9441401972,
-        "r":0.9248927039,
-        "f":0.9344173442
       },
       "MISC":{
-        "p":0.837398374,
-        "r":0.8067885117,
-        "f":0.8218085106
       },
       "PER":{
-        "p":0.9613670134,
-        "r":0.9700149925,
-        "f":0.9656716418
       }
     },
-    "speed":2440.4721637988
   },
   "sources":[
     {
@@ -697,6 +697,6 @@
     }
   ],
   "requirements":[
-    "spacy-transformers>=1.2.2,<1.3.0"
   ]
 }

 {
   "lang":"ca",
   "name":"core_news_trf",
+  "version":"3.7.2",
+  "description":"Catalan transformer pipeline (Transformer(name='projecte-aina/roberta-base-ca-v2', piece_encoder='byte-bpe', stride=112, type='roberta', width=768, window=144, vocab_size=50262)). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer.",
   "author":"Explosion",
   "email":"contact@explosion.ai",
   "url":"https://explosion.ai",
   "license":"GNU GPL 3.0",
+  "spacy_version":">=3.7.0,<3.8.0",
+  "spacy_git_version":"6b4f77441",
   "vectors":{
     "width":0,
     "vectors":0,
     "token_p":0.9978112128,
     "token_r":0.9979488063,
     "token_f":0.9978800048,
+    "pos_acc":0.9918845029,
+    "morph_acc":0.9900646831,
+    "morph_micro_p":0.997430458,
+    "morph_micro_r":0.9948740873,
+    "morph_micro_f":0.9961506326,
     "morph_per_feat":{
       "Mood":{
         "p":0.9982771351,
         "f":0.9981543005
       },
       "Number":{
+        "p":0.998884531,
+        "r":0.9963033413,
+        "f":0.9975922665
       },
       "Person":{
+        "p":0.9987604038,
         "r":0.9973474801,
+        "f":0.9980534419
       },
       "Tense":{
+        "p":0.9937251621,
+        "r":0.9962256238,
+        "f":0.994973822
       },
       "VerbForm":{
+        "p":0.9977330311,
+        "r":0.9966697749,
+        "f":0.9972011196
       },
       "Gender":{
+        "p":0.9973378509,
+        "r":0.9922469421,
+        "f":0.9947858833
       },
       "NumType":{
+        "p":0.9706439394,
+        "r":0.9660697455,
+        "f":0.9683514407
       },
       "Definite":{
+        "p":0.9971922565,
+        "r":0.9941072481,
+        "f":0.9956473626
       },
       "PronType":{
+        "p":0.9965301286,
+        "r":0.9945101351,
+        "f":0.9955191072
       },
       "PunctType":{
+        "p":0.9998172181,
+        "r":0.9974471189,
+        "f":0.9986307622
       },
       "NumForm":{
+        "p":0.9819193324,
+        "r":0.9915730337,
+        "f":0.9867225716
       },
       "Polarity":{
         "p":1.0,
+        "r":0.9902912621,
+        "f":0.9951219512
       },
       "Case":{
+        "p":0.9991652755,
+        "r":0.9966694421,
+        "f":0.9979157982
       },
       "PrepCase":{
+        "p":0.9986187845,
         "r":0.9986187845,
+        "f":0.9986187845
       },
       "Reflex":{
         "p":0.9986052999,
       },
       "Degree":{
         "p":1.0,
+        "r":0.9929328622,
+        "f":0.9964539007
       },
       "Poss":{
         "p":1.0,
+        "r":0.9914529915,
+        "f":0.9957081545
       },
       "AdvType":{
+        "p":0.9921875,
+        "r":0.9270072993,
+        "f":0.958490566
       },
       "PunctSide":{
+        "p":0.9975845411,
+        "r":0.9975845411,
+        "f":0.9975845411
       },
       "Number[psor]":{
+        "p":0.9411764706,
         "r":1.0,
+        "f":0.9696969697
       },
       "Polite":{
         "p":1.0,
+        "r":1.0,
+        "f":1.0
       }
     },
+    "sents_p":0.9947245018,
+    "sents_r":0.9929783499,
+    "sents_f":0.9938506589,
+    "dep_uas":0.9522584579,
+    "dep_las":0.9367199558,
     "dep_las_per_type":{
       "nsubj":{
+        "p":0.9610479145,
+        "r":0.9603858078,
+        "f":0.9607167471
       },
       "flat":{
+        "p":0.9334415584,
+        "r":0.9426229508,
+        "f":0.9380097879
       },
       "case":{
+        "p":0.9792044493,
+        "r":0.9737886257,
+        "f":0.9764890282
       },
       "aux":{
+        "p":0.9695512821,
+        "r":0.9690336359,
+        "f":0.9692923899
       },
       "root":{
+        "p":0.9730363423,
+        "r":0.9713282621,
+        "f":0.972181552
       },
       "nummod":{
+        "p":0.9326241135,
+        "r":0.926056338,
+        "f":0.9293286219
       },
       "obj":{
+        "p":0.931773399,
+        "r":0.9375464684,
+        "f":0.9346510191
       },
       "det":{
+        "p":0.9877590465,
+        "r":0.9876529955,
+        "f":0.9877060181
       },
       "nmod":{
+        "p":0.8882657463,
+        "r":0.8819875776,
+        "f":0.8851155293
       },
       "amod":{
+        "p":0.9682539683,
+        "r":0.9667924528,
+        "f":0.9675226586
       },
       "obl":{
+        "p":0.8433286843,
+        "r":0.8260473588,
+        "f":0.8345985737
       },
       "cc":{
+        "p":0.9579145729,
+        "r":0.9609325772,
+        "f":0.9594212016
       },
       "fixed":{
+        "p":0.932938856,
+        "r":0.9403578529,
+        "f":0.9366336634
       },
       "conj":{
+        "p":0.8519153802,
+        "r":0.8533791523,
+        "f":0.8526466381
       },
       "advmod":{
+        "p":0.8939393939,
+        "r":0.8928987194,
+        "f":0.8934187536
       },
       "advcl":{
+        "p":0.7478684531,
+        "r":0.7675,
+        "f":0.7575570635
       },
       "compound":{
+        "p":0.897810219,
+        "r":0.8880866426,
+        "f":0.8929219601
       },
       "mark":{
+        "p":0.9427235535,
+        "r":0.9438267993,
+        "f":0.9432748538
       },
       "cop":{
+        "p":0.9002123142,
+        "r":0.9177489177,
+        "f":0.9088960343
       },
       "ccomp":{
+        "p":0.8777292576,
+        "r":0.8993288591,
+        "f":0.8883977901
       },
       "acl":{
+        "p":0.8672397326,
+        "r":0.8747591522,
+        "f":0.8709832134
       },
       "expl:pass":{
+        "p":0.8611111111,
+        "r":0.6739130435,
+        "f":0.756097561
       },
       "appos":{
+        "p":0.8524590164,
+        "r":0.8600508906,
+        "f":0.8562381254
       },
       "xcomp":{
+        "p":0.9128329298,
+        "r":0.8849765258,
+        "f":0.8986889154
       },
       "iobj":{
+        "p":0.8670520231,
+        "r":0.8021390374,
+        "f":0.8333333333
       },
       "dep":{
         "p":0.0,
         "f":0.0
       },
       "csubj":{
+        "p":0.8125,
+        "r":0.858490566,
+        "f":0.8348623853
       },
       "parataxis":{
+        "p":0.8461538462,
+        "r":0.6470588235,
+        "f":0.7333333333
       },
       "nsubj:pass":{
         "p":0.0,
         "f":0.0
       }
     },
+    "tag_acc":0.9918845029,
+    "lemma_acc":0.9819043924,
+    "ents_p":0.9225996081,
+    "ents_r":0.9139437075,
+    "ents_f":0.9182512595,
     "ents_per_type":{
       "ORG":{
+        "p":0.9112107623,
+        "r":0.9161406673,
+        "f":0.9136690647
       },
       "LOC":{
+        "p":0.9353778751,
+        "r":0.9163090129,
+        "f":0.9257452575
       },
       "MISC":{
+        "p":0.8539944904,
+        "r":0.8093994778,
+        "f":0.8310991957
       },
       "PER":{
+        "p":0.9612518629,
+        "r":0.9670164918,
+        "f":0.9641255605
       }
     },
+    "speed":1944.0672670287
   },
   "sources":[
     {
     }
   ],
   "requirements":[
+    "spacy-curated-transformers>=0.2.0,<0.3.0"
   ]
 }

morphologizer/model CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4c677b72c8e1cf128058b042bba6f392ef97aa5c508e066b9c8d275c1b6e46
-size 871161

 version https://git-lfs.github.com/spec/v1
+oid sha256:16b0e7dc5ca70f1dabbc604c2f8aa790fa883a13d636a670b110f4a4a677e484
+size 871245

ner/model CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c5724cc10367a4af366b99ea2033c4d1c5ae9e3da40b0139631040e0f79906
-size 225962

 version https://git-lfs.github.com/spec/v1
+oid sha256:f25e4338cd60f3d30b4801a8cd26ab2a684ae70be4620d616ddd6dd22d3b392e
+size 226046

parser/model CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996d6350c1b4f12065344c8cc1c8279d7440f521570b7bc41fb06be1cc1aa4e9
-size 460325

 version https://git-lfs.github.com/spec/v1
+oid sha256:636b1a25fb2efdbdb8f3716d9a3c3f0a6e1494938d51df9300e8e85b198868b8
+size 460409

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:ef7515cc05db5dac9bd310f575fffd807088cce8171bfa3734b7fc63cdb318a3
-size 502217324

 version https://git-lfs.github.com/spec/v1
+oid sha256:cb98b432634b701ebfa18a7a3e3b84860e58f29b07d88842f51febea4de0394f
+size 497432290

vocab/strings.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab64b6938e21e30cb640708036808b618c41f0e295a633deb9767b53f3dfd2ad
-size 733905

 version https://git-lfs.github.com/spec/v1
+oid sha256:33111f72872b678ee90b376a310c25a9762839a9d8a68ef47c723418c0812a76
+size 733932