Instructions to use jdoerfler/SpaCy-fa_dep_web_sm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use jdoerfler/SpaCy-fa_dep_web_sm with spaCy:
!pip install https://huggingface.co/jdoerfler/SpaCy-fa_dep_web_sm/resolve/main/SpaCy-fa_dep_web_sm-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("SpaCy-fa_dep_web_sm") # Importing as module. import SpaCy-fa_dep_web_sm nlp = SpaCy-fa_dep_web_sm.load() - Notebooks
- Google Colab
- Kaggle
metadata
license: apache-2.0
datasets:
- universal-dependencies/universal_dependencies
language:
- fa
pipeline_tag: token-classification
library_name: spacy
tags:
- part-of-speech
- nlp
- spacy
- tagger
https://github.com/jdoerfler/ar-fa-id-tl-SpaCy-Training
SpaCy morphologizer (universal POS tagger) and dependency labeler. Trained on ~30k samples from Universal Dependencies' fa_perdt-ud-train.conllu and fa_seraji-ud-train.conllu, tested on ~2k samples Universal Dependencies' fa_perdt-ud-test.conllu and fa_seraji-ud-test.conllu.
- uPOS accuracy: 0.9216
- Dep head accuracy: 0.7858
- Dep label accuracy: 0.6666