| Feature | Description |
|---|---|
| Name | es_roberta_base_bne_leetspeak_ner |
| Version | 0.0.0 |
| spaCy | >=3.2.1,<3.3.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | PlanTL-GOB-ES/roberta-base-bne model a transformer-based masked language model for the Spanish language pre-trained with a total of 570GB of clean and deduplicated text compiled from the web crawlings performed by the National Library of Spain (Biblioteca Nacional de España) LeetSpeak-NER app where this model is in production for countering information disorders |
| License | Apache 2.0 |
| Author | Álvaro Huertas García at AI+DA |
Label Scheme
View label scheme (4 labels for 1 components)
| Component | Labels |
|---|---|
ner |
INV_CAMO, LEETSPEAK, MIX, PUNCT_CAMO |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
91.82 |
ENTS_P |
89.79 |
ENTS_R |
93.94 |
TRANSFORMER_LOSS |
166484.92 |
NER_LOSS |
318457.35 |
- Downloads last month
- 8
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.
Evaluation results
- NER Precisionself-reported0.898
- NER Recallself-reported0.939
- NER F Scoreself-reported0.918