add type annotations to tok. __init__

src/transformers/models/albert/tokenization_albert.py

@@ -141,7 +141,7 @@ def __init__(
         mask_token="[MASK]",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         # Mask token behave like a normal word, i.e. include the space before it
         mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
 

src/transformers/models/barthez/tokenization_barthez.py

@@ -126,7 +126,7 @@ def __init__(
         mask_token="<mask>",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         # Mask token behave like a normal word, i.e. include the space before it
         mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
 

src/transformers/models/bert_generation/tokenization_bert_generation.py

@@ -90,7 +90,7 @@ def __init__(
         sep_token="<::::>",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
 
         # Add extra_ids to the special token list

src/transformers/models/big_bird/tokenization_big_bird.py

@@ -109,7 +109,7 @@ def __init__(
         cls_token="[CLS]",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
         eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
         unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token

src/transformers/models/camembert/tokenization_camembert.py

@@ -123,7 +123,7 @@ def __init__(
         additional_special_tokens=["<s>NOTUSED", "</s>NOTUSED"],
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         # Mask token behave like a normal word, i.e. include the space before it
         mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
 

src/transformers/models/deberta_v2/tokenization_deberta_v2.py

@@ -108,7 +108,7 @@ def __init__(
         mask_token="[MASK]",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
 
         super().__init__(

src/transformers/models/m2m_100/tokenization_m2m_100.py

@@ -134,7 +134,7 @@ def __init__(
         unk_token="<unk>",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs,
-    ):
+    ) -> None:
         self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
 
         super().__init__(

src/transformers/models/marian/tokenization_marian.py

@@ -131,7 +131,7 @@ def __init__(
         model_max_length=512,
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
 
         super().__init__(

src/transformers/models/mbart/tokenization_mbart50.py

@@ -124,7 +124,7 @@ def __init__(
         mask_token="<mask>",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         # Mask token behave like a normal word, i.e. include the space before it
         mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
 

src/transformers/models/pegasus/tokenization_pegasus.py

@@ -111,7 +111,7 @@ def __init__(
         offset=103,  # entries 2 - 104 are only used for pretraining
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         self.offset = offset
 
         if additional_special_tokens is not None:

src/transformers/models/reformer/tokenization_reformer.py

@@ -97,7 +97,7 @@ def __init__(
         additional_special_tokens=[],
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
 
         super().__init__(

src/transformers/models/speech_to_text/tokenization_speech_to_text.py

@@ -119,7 +119,7 @@ def __init__(
         lang_codes=None,
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs,
-    ):
+    ) -> None:
         self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
 
         super().__init__(

src/transformers/models/t5/tokenization_t5.py

@@ -116,7 +116,7 @@ def __init__(
         additional_special_tokens=None,
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         # Add extra_ids to the special token list
         if extra_ids > 0 and additional_special_tokens is None:
             additional_special_tokens = [f"<extra_id_{i}>" for i in range(extra_ids)]

src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py

@@ -135,7 +135,7 @@ def __init__(
         mask_token="[MASK]",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
 
         super().__init__(

src/transformers/models/xlm_roberta/tokenization_xlm_roberta.py

@@ -131,7 +131,7 @@ def __init__(
         mask_token="<mask>",
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         # Mask token behave like a normal word, i.e. include the space before it
         mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
 

src/transformers/models/xlnet/tokenization_xlnet.py

@@ -140,7 +140,7 @@ def __init__(
         additional_special_tokens=["<eop>", "<eod>"],
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         **kwargs
-    ):
+    ) -> None:
         # Mask token behave like a normal word, i.e. include the space before it
         mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token