spaCy/spacy/cli/templates/quickstart_training_recommendations.yml
Adriane Boyd 8448c7dbc5
Update da trf recommendation (#8921)
Update the da trf recommendation to the same model used in the
pretrained pipelines.
2021-08-12 13:54:02 +02:00

275 lines
6.0 KiB
YAML

# Recommended settings and available resources for each language, if available.
# Not all languages have recommended word vectors or transformers and for some,
# the recommended transformer for efficiency and accuracy may be the same.
__default__:
word_vectors: null
transformer:
efficiency:
name: bert-base-multilingual-uncased
size_factor: 3
accuracy:
name: bert-base-multilingual-uncased
size_factor: 3
ar:
word_vectors: null
transformer:
efficiency:
name: asafaya/bert-base-arabic
size_factor: 3
accuracy:
name: asafaya/bert-base-arabic
size_factor: 3
bg:
word_vectors: null
transformer:
efficiency:
name: iarfmoose/roberta-base-bulgarian
size_factor: 3
accuracy:
name: iarfmoose/roberta-base-bulgarian
size_factor: 3
bn:
word_vectors: null
transformer:
efficiency:
name: sagorsarker/bangla-bert-base
size_factor: 3
accuracy:
name: sagorsarker/bangla-bert-base
size_factor: 3
da:
word_vectors: da_core_news_lg
transformer:
efficiency:
name: Maltehb/danish-bert-botxo
size_factor: 3
accuracy:
name: Maltehb/danish-bert-botxo
size_factor: 3
de:
word_vectors: de_core_news_lg
transformer:
efficiency:
name: bert-base-german-cased
size_factor: 3
accuracy:
name: bert-base-german-cased
size_factor: 3
el:
word_vectors: el_core_news_lg
transformer:
efficiency:
name: nlpaueb/bert-base-greek-uncased-v1
size_factor: 3
accuracy:
name: nlpaueb/bert-base-greek-uncased-v1
size_factor: 3
en:
word_vectors: en_core_web_lg
transformer:
efficiency:
name: roberta-base
size_factor: 3
accuracy:
name: roberta-base
size_factor: 3
es:
word_vectors: es_core_news_lg
transformer:
efficiency:
name: dccuchile/bert-base-spanish-wwm-cased
size_factor: 3
accuracy:
name: dccuchile/bert-base-spanish-wwm-cased
size_factor: 3
eu:
word_vectors: null
transformer:
efficiency:
name: mrm8488/RoBasquERTa
size_factor: 3
accuracy:
name: mrm8488/RoBasquERTa
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
fr:
word_vectors: fr_core_news_lg
transformer:
efficiency:
name: camembert-base
size_factor: 3
accuracy:
name: camembert-base
size_factor: 3
hi:
word_vectors: null
transformer:
efficiency:
name: ai4bharat/indic-bert
size_factor: 3
accuracy:
name: ai4bharat/indic-bert
size_factor: 3
id:
word_vectors: null
transformer:
efficiency:
name: indolem/indobert-base-uncased
size_factor: 3
accuracy:
name: indolem/indobert-base-uncased
size_factor: 3
it:
word_vectors: it_core_news_lg
transformer: null
ja:
word_vectors: ja_core_news_lg
transformer: null
lt:
word_vectors: lt_core_news_lg
transformer: null
mk:
word_vectors: null
transformer:
efficiency:
name: anon-submission-mk/bert-base-macedonian-cased
size_factor: 3
accuracy:
name: anon-submission-mk/bert-base-macedonian-cased
size_factor: 3
nb:
word_vectors: nb_core_news_lg
transformer:
efficiency:
name: NbAiLab/nb-bert-base
size_factor: 3
accuracy:
name: NbAiLab/nb-bert-base
size_factor: 3
nl:
word_vectors: nl_core_news_lg
transformer:
efficiency:
name: GroNLP/bert-base-dutch-cased
size_factor: 3
accuracy:
name: GroNLP/bert-base-dutch-cased
size_factor: 3
pl:
word_vectors: pl_core_news_lg
transformer:
efficiency:
name: dkleczek/bert-base-polish-cased-v1
size_factor: 3
accuracy:
name: dkleczek/bert-base-polish-cased-v1
size_factor: 3
pt:
word_vectors: pt_core_news_lg
transformer:
efficiency:
name: neuralmind/bert-base-portuguese-cased
size_factor: 3
accuracy:
name: neuralmind/bert-base-portuguese-cased
size_factor: 3
ro:
word_vectors: ro_core_news_lg
transformer:
efficiency:
name: dumitrescustefan/bert-base-romanian-cased-v1
size_factor: 3
accuracy:
name: dumitrescustefan/bert-base-romanian-cased-v1
size_factor: 3
si:
word_vectors: null
transformer:
efficiency:
name: setu4993/LaBSE
size_factor: 3
accuracy:
name: setu4993/LaBSE
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
ta:
word_vectors: null
transformer:
efficiency:
name: ai4bharat/indic-bert
size_factor: 3
accuracy:
name: ai4bharat/indic-bert
size_factor: 3
te:
word_vectors: null
transformer:
efficiency:
name: kuppuluri/telugu_bertu
size_factor: 3
accuracy:
name: kuppuluri/telugu_bertu
size_factor: 3
th:
word_vectors: null
transformer:
efficiency:
name: monsoon-nlp/bert-base-thai
size_factor: 3
accuracy:
name: monsoon-nlp/bert-base-thai
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
uk:
word_vectors: null
transformer:
efficiency:
name: youscan/ukr-roberta-base
size_factor: 3
accuracy:
name: youscan/ukr-roberta-base
size_factor: 3
ur:
word_vectors: null
transformer:
efficiency:
name: urduhack/roberta-urdu-small
size_factor: 3
accuracy:
name: urduhack/roberta-urdu-small
size_factor: 3
zh:
word_vectors: zh_core_web_lg
transformer:
efficiency:
name: bert-base-chinese
size_factor: 3
accuracy:
name: bert-base-chinese
size_factor: 3
has_letters: false