diff --git a/spacy/cli/evaluate.py b/spacy/cli/evaluate.py
index 83281543a..ee1be57a3 100644
--- a/spacy/cli/evaluate.py
+++ b/spacy/cli/evaluate.py
@@ -67,10 +67,7 @@ def evaluate(
     corpus = Corpus(data_path, data_path)
     nlp = util.load_model(model)
     dev_dataset = list(corpus.dev_dataset(nlp, gold_preproc=gold_preproc))
-    begin = timer()
     scores = nlp.evaluate(dev_dataset, verbose=False)
-    end = timer()
-    nwords = sum(len(ex.predicted) for ex in dev_dataset)
     metrics = {
         "TOK": "token_acc",
         "TAG": "tag_acc",
@@ -82,17 +79,21 @@ def evaluate(
         "NER P": "ents_p",
         "NER R": "ents_r",
         "NER F": "ents_f",
-        "Textcat": "cats_score",
-        "Sent P": "sents_p",
-        "Sent R": "sents_r",
-        "Sent F": "sents_f",
+        "TEXTCAT": "cats_score",
+        "SENT P": "sents_p",
+        "SENT R": "sents_r",
+        "SENT F": "sents_f",
+        "SPEED": "speed",
     }
     results = {}
     for metric, key in metrics.items():
         if key in scores:
             if key == "cats_score":
                 metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")"
-            results[metric] = f"{scores[key]*100:.2f}"
+            if key == "speed":
+                results[metric] = f"{scores[key]:.0f}"
+            else:
+                results[metric] = f"{scores[key]*100:.2f}"
     data = {re.sub(r"[\s/]", "_", k.lower()): v for k, v in results.items()}
 
     msg.table(results, title="Results")
diff --git a/spacy/cli/train.py b/spacy/cli/train.py
index 44597c73e..25eb4a3c0 100644
--- a/spacy/cli/train.py
+++ b/spacy/cli/train.py
@@ -1,5 +1,4 @@
 from typing import Optional, Dict, Any, Tuple, Union, Callable, List
-from timeit import default_timer as timer
 import srsly
 import tqdm
 from pathlib import Path
@@ -248,14 +247,11 @@ def create_evaluation_callback(
         dev_examples = list(dev_examples)
         n_words = sum(len(ex.predicted) for ex in dev_examples)
         batch_size = cfg["eval_batch_size"]
-        start_time = timer()
         if optimizer.averages:
             with nlp.use_params(optimizer.averages):
                 scores = nlp.evaluate(dev_examples, batch_size=batch_size)
         else:
             scores = nlp.evaluate(dev_examples, batch_size=batch_size)
-        end_time = timer()
-        wps = n_words / (end_time - start_time)
         # Calculate a weighted sum based on score_weights for the main score
         weights = cfg["score_weights"]
         try:
@@ -264,7 +260,6 @@ def create_evaluation_callback(
             keys = list(scores.keys())
             err = Errors.E983.format(dict="score_weights", key=str(e), keys=keys)
             raise KeyError(err)
-        scores["speed"] = wps
         return weighted_score, scores
 
     return evaluate
diff --git a/spacy/language.py b/spacy/language.py
index 79fceec95..fe0a86ed1 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -14,6 +14,7 @@ from thinc.api import get_current_ops, Config, require_gpu, Optimizer
 import srsly
 import multiprocessing as mp
 from itertools import chain, cycle
+from timeit import default_timer as timer
 
 from .tokens.underscore import Underscore
 from .vocab import Vocab, create_vocab
@@ -1088,7 +1089,14 @@ class Language:
             kwargs.setdefault("verbose", verbose)
             kwargs.setdefault("nlp", self)
             scorer = Scorer(**kwargs)
-        docs = list(eg.predicted for eg in examples)
+        texts = [eg.reference.text for eg in examples]
+        docs = [eg.predicted for eg in examples]
+        start_time = timer()
+        # tokenize the texts only for timing purposes
+        if not hasattr(self.tokenizer, "pipe"):
+            _ = [self.tokenizer(text) for text in texts]
+        else:
+            _ = list(self.tokenizer.pipe(texts))
         for name, pipe in self.pipeline:
             kwargs = component_cfg.get(name, {})
             kwargs.setdefault("batch_size", batch_size)
@@ -1096,11 +1104,18 @@ class Language:
                 docs = _pipe(docs, pipe, kwargs)
             else:
                 docs = pipe.pipe(docs, **kwargs)
+        # iterate over the final generator
+        if len(self.pipeline):
+            docs = list(docs)
+        end_time = timer()
         for i, (doc, eg) in enumerate(zip(docs, examples)):
             if verbose:
                 print(doc)
             eg.predicted = doc
-        return scorer.score(examples)
+        results = scorer.score(examples)
+        n_words = sum(len(eg.predicted) for eg in examples)
+        results["speed"] = n_words / (end_time - start_time)
+        return results
 
     @contextmanager
     def use_params(self, params: dict):