diff --git a/setup.py b/setup.py
index aa7be0f6cbf2d5..4541bb0b472a32 100644
--- a/setup.py
+++ b/setup.py
@@ -168,6 +168,7 @@
     "tokenizers>=0.11.1,!=0.11.3,<0.14",
     "torch>=1.7,!=1.12.0",
     "torchaudio",
+    "torchvision",
     "pyctcdecode>=0.4.0",
     "tqdm>=4.27",
     "unidic>=1.0.2",
@@ -285,6 +286,7 @@ def run(self):
 extras["flax-speech"] = extras["audio"]
 extras["vision"] = deps_list("Pillow")
 extras["timm"] = deps_list("timm")
+extras["torchvision"] = deps_list("torchvision")
 extras["natten"] = deps_list("natten")
 extras["codecarbon"] = deps_list("codecarbon")
 extras["video"] = deps_list("decord")
@@ -331,6 +333,7 @@ def run(self):
     + extras["vision"]
     + extras["integrations"]
     + extras["timm"]
+    + extras["torchvision"]
     + extras["codecarbon"]
     + extras["accelerate"]
     + extras["video"]
@@ -351,6 +354,7 @@ def run(self):
     + extras["vision"]
     + extras["integrations"]
     + extras["timm"]
+    + extras["torchvision"]
     + extras["codecarbon"]
     + extras["quality"]
     + extras["ja"]
diff --git a/src/transformers/dependency_versions_table.py b/src/transformers/dependency_versions_table.py
index b81734043fce2a..cb893e92fca133 100644
--- a/src/transformers/dependency_versions_table.py
+++ b/src/transformers/dependency_versions_table.py
@@ -74,6 +74,7 @@
     "tokenizers": "tokenizers>=0.11.1,!=0.11.3,<0.14",
     "torch": "torch>=1.7,!=1.12.0",
     "torchaudio": "torchaudio",
+    "torchvision": "torchvision",
     "pyctcdecode": "pyctcdecode>=0.4.0",
     "tqdm": "tqdm>=4.27",
     "unidic": "unidic>=1.0.2",