Views
No views yet
minn=maxn=5,
hash_count=2, trained on 400,000 Persian documents. Vectors only, no pipeline components.fa_dep_news_md / fa_core_news_md / fa_ent_news_md tier.
Because floret hashes subwords rather than storing whole-word keys, there are no OOV tokens:
every string gets a vector, which is what makes it usable on Persian text where inconsistent
ZWNJ placement otherwise explodes the vocabulary.pip install https://huggingface.co/Phazel/fa_floret_400k/resolve/main/fa_floret_400k-0.1.0-py3-none-any.whl1import spacy
2
3nlp = spacy.load("fa_floret_400k") # vectors only: nlp.pipe_names == []
4print(nlp.vocab.vectors.shape) # (50000, 300)
5print(nlp("کتابهای").vector.shape) # (300,)--paths.vectors and set
components.tok2vec.model.embed.include_static_vectors = true:python -m spacy train config.cfg --paths.vectors fa_floret_400k| Property | Value |
|---|---|
| Rows | 50,000 |
| Dimensions | 300 |
| Mode | floret (subword, Bloom-hashed) |
minn / maxn | 5 / 5 |
hash_count | 2 |
| Training corpus | 400,000 Persian documents |
| Package | Rows | Corpus | Used by |
|---|---|---|---|
fa_floret_400k | 50k | 400k Persian documents | md tier |
fa_floret_full_wiki | 50k | full Persian Wikipedia dump | — |
fa_floret_wiki_200k | 200k | full Persian Wikipedia dump, 5 epochs | lg tier |
spacy-persian (docs/MODELS.md
§6-7).| Source | Author | Licence |
|---|---|---|
fa_floret static vectors, 50k rows x 300d, 400k Persian documents | Kiyarash Fazeli | CC BY-SA 4.0 |
md pipelines that embed this table
carry.