diff --git a/model_cards/allenai/wmt19-de-en-6-6-base/README.md b/model_cards/allenai/wmt19-de-en-6-6-base/README.md
index 303a11cb6590..c946ad9f2f1d 100644
--- a/model_cards/allenai/wmt19-de-en-6-6-base/README.md
+++ b/model_cards/allenai/wmt19-de-en-6-6-base/README.md
@@ -61,7 +61,7 @@ Pretrained weights were left identical to the original model released by allenai
 Here are the BLEU scores:
 
 model   |  transformers
--------|---------|----------
+-------|---------
 wmt19-de-en-6-6-base  |  38.37
 
 The score was calculated using this code:
diff --git a/model_cards/allenai/wmt19-de-en-6-6-big/README.md b/model_cards/allenai/wmt19-de-en-6-6-big/README.md
index 515e1d6744d8..f675f899a16d 100644
--- a/model_cards/allenai/wmt19-de-en-6-6-big/README.md
+++ b/model_cards/allenai/wmt19-de-en-6-6-big/README.md
@@ -61,7 +61,7 @@ Pretrained weights were left identical to the original model released by allenai
 Here are the BLEU scores:
 
 model   |  transformers
--------|---------|----------
+-------|---------
 wmt19-de-en-6-6-big  |  39.9
 
 The score was calculated using this code:
diff --git a/scripts/fsmt/gen-card-allenai-wmt19.py b/scripts/fsmt/gen-card-allenai-wmt19.py
index b6bb97d6ac52..4df5ca0542e3 100755
--- a/scripts/fsmt/gen-card-allenai-wmt19.py
+++ b/scripts/fsmt/gen-card-allenai-wmt19.py
@@ -85,7 +85,7 @@ def write_model_card(model_card_dir, src_lang, tgt_lang, model_name):
 Here are the BLEU scores:
 
 model   |  transformers
--------|---------|----------
+-------|---------
 {model_name}  |  {scores[model_name][1]}
 
 The score was calculated using this code: