mirror of
https://github.com/explosion/spaCy.git
synced 2025-02-24 23:50:45 +03:00
e2f2ef3a5a
- As much as I dislike YAML, it seemed like a better format here because it allows us to add comments if we want to explain the different recommendations - Don't include the generated JS in the repo by default and build it on the fly when running or deploying the site. This ensures it's always up to date. - Simplify jinja_to_js script and use fewer dependencies
104 lines
2.3 KiB
YAML
104 lines
2.3 KiB
YAML
# Recommended settings and available resources for each language, if available.
|
|
# Not all languages have recommended word vecotrs or transformers and for some,
|
|
# the recommended transformer for efficiency and accuracy may be the same.
|
|
en:
|
|
word_vectors: en_vectors_web_lg
|
|
transformer:
|
|
efficiency:
|
|
name: roberta-base
|
|
size_factor: 3
|
|
accuracy:
|
|
name: roberta-base
|
|
size_factor: 3
|
|
de:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: bert-base-german-cased
|
|
size_factor: 3
|
|
accuracy:
|
|
name: bert-base-german-cased
|
|
size_factor: 3
|
|
fr:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: camembert-base
|
|
size_factor: 3
|
|
accuracy:
|
|
name: camembert-base
|
|
size_factor: 3
|
|
es:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: mrm8488/RuPERTa-base
|
|
size_factor: 3
|
|
accuracy:
|
|
name: mrm8488/RuPERTa-base
|
|
size_factor: 3
|
|
sv:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: KB/bert-base-swedish-cased
|
|
size_factor: 3
|
|
accuracy:
|
|
name: KB/bert-base-swedish-cased
|
|
size_factor: 3
|
|
fi:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: TurkuNLP/bert-base-finnish-cased-v1
|
|
size_factor: 3
|
|
accuracy:
|
|
name: TurkuNLP/bert-base-finnish-cased-v1
|
|
size_factor: 3
|
|
el:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: nlpaueb/bert-base-greek-uncased-v1
|
|
size_factor: 3
|
|
accuracy:
|
|
name: nlpaueb/bert-base-greek-uncased-v1
|
|
size_factor: 3
|
|
tr:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: dbmdz/bert-base-turkish-cased
|
|
size_factor: 3
|
|
accuracy:
|
|
name: dbmdz/bert-base-turkish-cased
|
|
size_factor: 3
|
|
zh:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: bert-base-chinese
|
|
size_factor: 3
|
|
accuracy:
|
|
name: bert-base-chinese
|
|
size_factor: 3
|
|
has_letters: false
|
|
ar:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: asafaya/bert-base-arabic
|
|
size_factor: 3
|
|
accuracy:
|
|
name: asafaya/bert-base-arabic
|
|
size_factor: 3
|
|
pl:
|
|
word_vectors: null
|
|
transformer:
|
|
efficiency:
|
|
name: dkleczek/bert-base-polish-cased-v1
|
|
size_factor: 3
|
|
accuracy:
|
|
name: dkleczek/bert-base-polish-cased-v1
|
|
size_factor: 3
|