Update README.md

README.md

@@ -14,29 +14,41 @@ model-index:
       name: NER
       type: token-classification
     metrics:
-    - name: NER Precision (micro avg)
+    - name: NER Precision
       type: precision
-      value: 0.963
-    - name: NER Recall (micro avg)
+      value: 0.9648998822
+    - name: NER Recall
       type: recall
-      value: 0.958
-    - name: NER F Score (micro avg)
+      value: 0.9603751465
+    - name: NER F Score
       type: f_score
-      value: 0.961
+      value: 0.9626321974
 ---
 
 # Introduction
 
-spaCy NER model for Spanish trained in the domain of tourism related to the Way of Saint Jacques. It recognizes four types of entities: location (LOC), organizations (ORG), person (PER) and miscellaneous (MISC).
+spaCy NER model for Spanish trained with interviews in the domain of tourism related to the Way of Saint Jacques. It recognizes four types of entities: location (LOC), organizations (ORG), person (PER) and miscellaneous (MISC).
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `es_spacy_ner_cds` |
 | **Version** | `0.0.1a` |
 | **spaCy** | `>=3.4.3,<3.5.0` |
-| **Pipeline** | `tok2vec`, `ner` |
+| **Default Pipeline** | `tok2vec`, `ner` |
 | **Components** | `tok2vec`, `ner` |
 
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (4 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`ner`** | `LOC`, `MISC`, `ORG`, `PER` |
+
+</details>
+
 ## Usage
 
 You can use this model with the spaCy *pipeline* for NER.
@@ -61,13 +73,12 @@ for token in merge_entities(ner_pipe):
 
 ToDo
 
-## Model performance
+### Accuracy
 
-entity|precision|recall|f1
--|-|-|-
-PER|0.942|0.890|0.915
-ORG|0.869|0.688|0.768
-LOC|0.975|0.987|0.981
-MISC|0.854|0.757|0.803
-micro avg|0.963|0.958|0.961
-macro avg|0.910|0.831|0.867
+| Type | Score |
+| --- | --- |
+| `ENTS_F` | 96.26 |
+| `ENTS_P` | 96.49 |
+| `ENTS_R` | 96.04 |
+| `TOK2VEC_LOSS` | 62780.17 |
+| `NER_LOSS` | 34006.41 |