Downloads · 30 days
5
1% of all-time downloads
de_fnhd_nerdh
easyh/de_fnhd_nerdh
de_fnhd_nerdh is a token classification model from easyh. Use it when you need labels on individual words, such as names. It is set up for spacy.
Deutsche NER-Pipeline für frühneuhochdeutsche Texte (2.Version)
All-time downloads
472
Public
Repo size
1.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other642 MB · 51%
At a glance
- Task
- Token Classification
- Library
- spacy
- Access
- Public
- Created
- Nov 19, 2022
- Updated
- Nov 19, 2022
- SHA
- 29d5e7b0
Model card
From the Hugging Face model README
Deutsche NER-Pipeline für frühneuhochdeutsche Texte (2.Version)
| Feature | Description |
|---|---|
| Name | de_fnhd_nerdh |
| Version | 0.0.2 |
| spaCy | >=3.4.1,<3.5.0 |
| Default Pipeline | tok2vec, ner |
| Components | tok2vec, ner |
| Vectors | 500000 keys, 500000 unique vectors (300 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | ih |
Label Scheme
<details> <summary>View label scheme (5 labels for 1 components)</summary>| Component | Labels |
|---|---|
ner | OBJEKT, ORGANISATION, ORT, PERSON, ZEIT |
Accuracy
| Type | Score |
|---|---|
ENTS_F | 95.66 |
ENTS_P | 96.29 |
ENTS_R | 95.04 |
TOK2VEC_LOSS | 25311.59 |
NER_LOSS | 15478.32 |
- Task
- Token Classification
- Library
- spacy
- Languages
- de
- Created
- Nov 19, 2022
- Updated
- Nov 19, 2022