de-hdt-wikiner
Collection
German spaCy models trained on German UD-HDT and the WikiNER corpus
•
4 items
•
Updated
| Feature | Description |
|---|---|
| Name | de_wikiner_lg |
| Version | 1.0.0 |
| spaCy | >=3.7.5,<3.8.0 |
| Default Pipeline | tok2vec, ner |
| Components | tok2vec, ner |
| Vectors | 500000 keys, 500000 unique vectors (300 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | n/a |
Label Scheme
View label scheme (4 labels for 1 components)
| Component | Labels |
|---|---|
ner |
LOC, MISC, ORG, PER |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
83.26 |
ENTS_P |
84.71 |
ENTS_R |
81.86 |
TOK2VEC_LOSS |
401121.28 |
NER_LOSS |
924927.46 |
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Collection including zentrum-lexikographie/de_wikiner_lg
Evaluation results
- NER Precisionself-reported0.847
- NER Recallself-reported0.819
- NER F Scoreself-reported0.833