diff --git a/spacy/tests/doc/test_doc_spilt.py b/spacy/tests/doc/test_doc_spilt.py
index bcadf4eb4..9bd1721e2 100644
--- a/spacy/tests/doc/test_doc_spilt.py
+++ b/spacy/tests/doc/test_doc_spilt.py
@@ -8,60 +8,43 @@ from spacy.tokens import Doc
 from ..util import get_doc
 
 
-def test_doc_split(en_tokenizer):
-    text = "LosAngeles start."
+def test_doc_split(en_vocab):
+    words = ["LosAngeles", "start", "."]
     heads = [1, 1, 0]
-    tokens = en_tokenizer(text)
-    doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads)
-
+    doc = get_doc(en_vocab, words=words, heads=heads)
     assert len(doc) == 3
     assert len(str(doc)) == 19
     assert doc[0].head.text == "start"
     assert doc[1].head.text == "."
-
     with doc.retokenize() as retokenizer:
-        retokenizer.split(
-            doc[0],
-            ["Los", "Angeles"],
-            [1, 0],
-            attrs={"tag": "NNP", "lemma": "Los Angeles", "ent_type": "GPE"},
-        )
-
+        attrs = {"tag": "NNP", "lemma": "Los Angeles", "ent_type": "GPE"}
+        retokenizer.split(doc[0], ["Los", "Angeles"], [1, 0], attrs=attrs)
     assert len(doc) == 4
     assert doc[0].text == "Los"
     assert doc[0].head.text == "Angeles"
     assert doc[0].idx == 0
     assert doc[1].idx == 3
-
     assert doc[1].text == "Angeles"
     assert doc[1].head.text == "start"
-
     assert doc[2].text == "start"
     assert doc[2].head.text == "."
-
     assert doc[3].text == "."
     assert doc[3].head.text == "."
-
     assert len(str(doc)) == 19
 
 
-def test_split_dependencies(en_tokenizer):
-    text = "LosAngeles start."
-    tokens = en_tokenizer(text)
-    doc = get_doc(tokens.vocab, [t.text for t in tokens])
+def test_split_dependencies(en_vocab):
+    doc = Doc(en_vocab, words=["LosAngeles", "start", "."])
     dep1 = doc.vocab.strings.add("amod")
     dep2 = doc.vocab.strings.add("subject")
     with doc.retokenize() as retokenizer:
         retokenizer.split(doc[0], ["Los", "Angeles"], [1, 0], [dep1, dep2])
-
     assert doc[0].dep == dep1
     assert doc[1].dep == dep2
 
 
-def test_split_heads_error(en_tokenizer):
-    text = "LosAngeles start."
-    tokens = en_tokenizer(text)
-    doc = get_doc(tokens.vocab, [t.text for t in tokens])
+def test_split_heads_error(en_vocab):
+    doc = Doc(en_vocab, words=["LosAngeles", "start", "."])
     # Not enough heads
     with pytest.raises(ValueError):
         with doc.retokenize() as retokenizer:
@@ -90,7 +73,6 @@ def test_spans_entity_merge_iob():
     doc.ents = [(doc.vocab.strings.add("ent-abcd"), 0, 2)]
     assert doc[0].ent_iob_ == "B"
     assert doc[1].ent_iob_ == "I"
-
     with doc.retokenize() as retokenizer:
         retokenizer.split(doc[0], ["a", "b", "c"], [1, 1, 0])
     assert doc[0].ent_iob_ == "B"
@@ -99,16 +81,15 @@ def test_spans_entity_merge_iob():
     assert doc[3].ent_iob_ == "I"
 
 
-def test_spans_sentence_update_after_merge(en_tokenizer):
+def test_spans_sentence_update_after_merge(en_vocab):
     # fmt: off
-    text = "StewartLee is a stand up comedian. He lives in England and loves JoePasquale."
+    words = ["StewartLee", "is", "a", "stand", "up", "comedian", ".", "He",
+             "lives", "in", "England", "and", "loves", "JoePasquale", "."]
     heads = [1, 0, 1, 2, -1, -4, -5, 1, 0, -1, -1, -3, -4, 1, -2]
     deps = ["nsubj", "ROOT", "det", "amod", "prt", "attr", "punct", "nsubj",
             "ROOT", "prep", "pobj", "cc", "conj", "compound", "punct"]
     # fmt: on
-
-    tokens = en_tokenizer(text)
-    doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps)
+    doc = get_doc(en_vocab, words=words, heads=heads, deps=deps)
     sent1, sent2 = list(doc.sents)
     init_len = len(sent1)
     init_len2 = len(sent2)