Merge pull request #6262 from adrianeboyd/bugfix/template-en-vectors

spacy/cli/templates/quickstart_training_recommendations.yml

@@ -1,17 +1,20 @@
 # 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.
-en:
+ar:
-  word_vectors: en_vectors_web_lg
+  word_vectors: null
   transformer:
     efficiency:
-      name: roberta-base
+      name: asafaya/bert-base-arabic
       size_factor: 3
     accuracy:
-      name: roberta-base
+      name: asafaya/bert-base-arabic
       size_factor: 3
+da:
+  word_vectors: da_core_news_lg
+  transformer: null
 de:
-  word_vectors: null
+  word_vectors: de_core_news_lg
   transformer:
     efficiency:
       name: bert-base-german-cased
@@ -19,17 +22,26 @@ de:
     accuracy:
       name: bert-base-german-cased
       size_factor: 3
-fr:
+el:
-  word_vectors: null
+  word_vectors: el_core_news_lg
   transformer:
     efficiency:
-      name: camembert-base
+      name: nlpaueb/bert-base-greek-uncased-v1
       size_factor: 3
     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
 es:
-  word_vectors: null
+  word_vectors: es_core_news_lg
   transformer:
     efficiency:
       name: dccuchile/bert-base-spanish-wwm-cased
@@ -37,15 +49,6 @@ es:
     accuracy:
       name: dccuchile/bert-base-spanish-wwm-cased
       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:
@@ -55,14 +58,65 @@ fi:
     accuracy:
       name: TurkuNLP/bert-base-finnish-cased-v1
       size_factor: 3
-el:
+fr:
+  word_vectors: fr_core_news_lg
+  transformer:
+    efficiency:
+      name: camembert-base
+      size_factor: 3
+    accuracy:
+      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: nlpaueb/bert-base-greek-uncased-v1
+      name: KB/bert-base-swedish-cased
       size_factor: 3
     accuracy:
-      name: nlpaueb/bert-base-greek-uncased-v1
+      name: KB/bert-base-swedish-cased
       size_factor: 3
 tr:
   word_vectors: null
@@ -74,7 +128,7 @@ tr:
       name: dbmdz/bert-base-turkish-cased
       size_factor: 3
 zh:
-  word_vectors: null
+  word_vectors: zh_core_web_lg
   transformer:
     efficiency:
       name: bert-base-chinese
@@ -83,39 +137,3 @@ zh:
       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
-nl:
-  word_vectors: null
-  transformer:
-    efficiency:
-      name: pdelobelle/robbert-v2-dutch-base
-      size_factor: 3
-    accuracy:
-      name: pdelobelle/robbert-v2-dutch-base
-      size_factor: 3
-pt:
-  word_vectors: null
-  transformer:
-    efficiency:
-      name: neuralmind/bert-base-portuguese-cased
-      size_factor: 3
-    accuracy:
-      name: neuralmind/bert-base-portuguese-cased
-      size_factor: 3