fr_pipeline

deepin-tech/fr_pipeline

fr_pipeline is a token classification model from deepin-tech. Use it when you need labels on individual words, such as names. It is set up for spacy.

Downloads · 30 days

3% of all-time downloads

All-time downloads

127

Public

Repo size

191 MB

Likes

Public

Repo makeup

Click a slice to open those files.

Other113 MB · 56%

From the Hugging Face model README

Feature	Description
Name	`fr_pipeline`
Version	`0.0.0`
spaCy	`>=3.4.1,<3.5.0`
Default Pipeline	`tok2vec`, `tagger`, `national`, `thematic`, `sentiments`, `ner`
Components	`tok2vec`, `tagger`, `national`, `thematic`, `sentiments`, `ner`
Vectors	-1 keys, 50000 unique vectors (300 dimensions)
Sources	n/a
License	n/a
Author	n/a

<details> <summary>View label scheme (71 labels for 5 components)</summary>

Component	Labels
`tagger`	`1`, `10`, `100`, `125`, `13`, `14`, `15`, `17`, `19`, `190`, `2`, `25`, `3`, `46`, `5`, `50`, `500`, `6`, `7`, `80`, `800`, `ADJ`, `ADP`, `ADV`, `AUX`, `CCONJ`, `CONJ`, `DET`, `INTJ`, `NOUN`, `NUM`, `PRON`, `PROPN`, `PUNCT`, `SCONJ`, `SYM`, `VERB`, `X`
`national`	`International`, `National`
`thematic`	`Coopération/Diplomatie`, `Culture`, `Economie`, `Education`, `Election`, `Environnement`, `Gouvernement`, `Insolite`, `Justice`, `Nécrologie`, `People`, `Politique`, `Réligion`, `Santé`, `Sexualité/Vie couple`, `Société`, `Sport`, `Sécurité`, `Sécurité routière`, `Technologie`
`sentiments`	`Negatif`, `Neutre`, `Positif`
`ner`	`DATE`, `EVENT`, `LOC`, `MISC`, `MONEY`, `ORG`, `PER`, `PER-T`

</details>