explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Sort and add vectors for langs without transformers

Browse Source
This commit is contained in:
Adriane Boyd 2020-10-16 08:25:16 +02:00
parent 2fbd43c603
commit c8d04b79e2
1 changed files with 75 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

132
spacy/cli/templates/quickstart_training_recommendations.yml
View File

@ -1,15 +1,18 @@
# Recommended settings and available resources for each language, if available. # Recommended settings and available resources for each language, if available.
# Not all languages have recommended word vectors or transformers and for some, # Not all languages have recommended word vectors or transformers and for some,
# the recommended transformer for efficiency and accuracy may be the same. # the recommended transformer for efficiency and accuracy may be the same.
en: ar:
word_vectors: en_core_web_lg word_vectors: null
transformer: transformer:
efficiency: efficiency:
name: roberta-base name: asafaya/bert-base-arabic
size_factor: 3 size_factor: 3
accuracy: accuracy:
name: roberta-base name: asafaya/bert-base-arabic
size_factor: 3 size_factor: 3
da:
word_vectors: da_core_news_lg
transformer: null
de: de:
word_vectors: de_core_news_lg word_vectors: de_core_news_lg
transformer: transformer:
@ -19,14 +22,23 @@ de:
accuracy: accuracy:
name: bert-base-german-cased name: bert-base-german-cased
size_factor: 3 size_factor: 3
fr: el:
word_vectors: fr_core_news_lg word_vectors: el_core_news_lg
transformer: transformer:
efficiency: efficiency:
name: camembert-base name: nlpaueb/bert-base-greek-uncased-v1
size_factor: 3 size_factor: 3
accuracy: accuracy:
name: camembert-base 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 size_factor: 3
es: es:
word_vectors: es_core_news_lg word_vectors: es_core_news_lg
@ -37,15 +49,6 @@ es:
accuracy: accuracy:
name: dccuchile/bert-base-spanish-wwm-cased name: dccuchile/bert-base-spanish-wwm-cased
size_factor: 3 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: fi:
word_vectors: null word_vectors: null
transformer: transformer:
@ -55,14 +58,65 @@ fi:
accuracy: accuracy:
name: TurkuNLP/bert-base-finnish-cased-v1 name: TurkuNLP/bert-base-finnish-cased-v1
size_factor: 3 size_factor: 3
el: fr:
word_vectors: el_core_news_lg word_vectors: fr_core_news_lg
transformer: transformer:
efficiency: efficiency:
name: nlpaueb/bert-base-greek-uncased-v1 name: camembert-base
size_factor: 3 size_factor: 3
accuracy: accuracy:
name: nlpaueb/bert-base-greek-uncased-v1 name: camembert-base
size_factor: 3
it:
word_vectors: it_core_news_lg
transformers: null
ja:
word_vectors: ja_core_news_lg
transformers: null
lt:
word_vectors: lt_core_news_lg
transformers: null
nb:
word_vectors: nb_core_news_lg
transformers: null
nl:
word_vectors: nl_core_news_lg
transformer:
efficiency:
name: pdelobelle/robbert-v2-dutch-base
size_factor: 3
accuracy:
name: pdelobelle/robbert-v2-dutch-base
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
transformers: null
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 size_factor: 3
tr: tr:
word_vectors: null word_vectors: null
@ -83,39 +137,3 @@ zh:
name: bert-base-chinese name: bert-base-chinese
size_factor: 3 size_factor: 3
has_letters: false 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: 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
nl:
word_vectors: nl_core_news_lg
transformer:
efficiency:
name: pdelobelle/robbert-v2-dutch-base
size_factor: 3
accuracy:
name: pdelobelle/robbert-v2-dutch-base
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