Downloads · 30 days
14
5% of all-time downloads
fr_ner4archives_default_test
ner4archives/fr_ner4archives_default_test
fr_ner4archives_default_test is a token classification model from ner4archives. Use it when you need labels on individual words, such as names. It is set up for spacy.
NER4Archives pipeline optimized for CPU and specialized on French National Archives findings aids (XML-EAD) - Corpus V2. Components: tok2vec, ner. Base default CNN architecture.
All-time downloads
299
Public
Repo size
8.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other6.1 MB · 58%
At a glance
- Task
- Token Classification
- Library
- spacy
- Access
- Public
- Created
- Jul 28, 2022
- Updated
- Sep 30, 2022
- SHA
- 287f6586
Try a prompt
Model card
From the Hugging Face model README
NER4Archives pipeline optimized for CPU and specialized on French National Archives findings aids (XML-EAD) - Corpus V2. Components: tok2vec, ner. Base default CNN architecture.
| Feature | Description |
|---|---|
| Name | fr_ner4archives_default_test |
| Version | 0.0.0 |
| spaCy | >=3.3.1,<3.4.0 |
| Default Pipeline | tok2vec, ner |
| Components | tok2vec, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | French corpus for the NER task composed of finding aids in XML-EAD from the National Archives of France (v. 2.0) - Check corpus version on GitHub |
| License | CC-BY-4.0 license |
| Author | Archives nationales / Inria-Almanach |
Label Scheme
<details> <summary>View label scheme (5 labels for 1 components)</summary>| Component | Labels |
|---|---|
ner | EVENT, LOCATION, ORGANISATION, PERSON, TITLE |
Accuracy
| Type | Score |
|---|---|
ENTS_F | 76.95 |
ENTS_P | 80.00 |
ENTS_R | 74.13 |
TOK2VEC_LOSS | 76044.50 |
NER_LOSS | 75529.77 |
- Task
- Token Classification
- Library
- spacy
- Languages
- fr
- Created
- Jul 28, 2022
- Updated
- Sep 30, 2022