diff --git a/bindings/python/Makefile b/bindings/python/Makefile
index eb5d2c57c..f07cff584 100644
--- a/bindings/python/Makefile
+++ b/bindings/python/Makefile
@@ -9,13 +9,13 @@ check_dirs := examples py_src/tokenizers tests
 style:
 	python stub.py
 	ruff check  $(check_dirs) --fix 
-	ruff format --line-length 119 --target-version py35 $(check_dirs)
+	ruff format $(check_dirs)
 
 # Check the source code is formatted correctly
 check-style:
 	python stub.py --check
 	ruff check examples py_src/tokenizers tests 
-	ruff format --check --line-length 119 --target-version py35 examples py_src/tokenizers tests 
+	ruff format --check examples py_src/tokenizers tests 
 
 TESTS_RESOURCES = $(DATA_DIR)/small.txt $(DATA_DIR)/roberta.json
 
diff --git a/bindings/python/examples/example.py b/bindings/python/examples/example.py
index c09d4c128..d62390644 100644
--- a/bindings/python/examples/example.py
+++ b/bindings/python/examples/example.py
@@ -14,7 +14,6 @@
 logging.getLogger("transformers.tokenization_utils").disabled = True
 
 
-
 parser = argparse.ArgumentParser()
 parser.add_argument("--type", default="gpt2", type=str, help="The type of tokenizer (bert|gpt2)")
 parser.add_argument("--file", default=None, type=str, help="The file to encode")
@@ -51,9 +50,7 @@
 If the implementation is hard to explain, it's a bad idea.
 If the implementation is easy to explain, it may be a good idea.
 Namespaces are one honking great idea -- let's do more of those!
-""".split(
-        "\n"
-    )
+""".split("\n")
 
 if args.type == "gpt2":
     print("Running GPT-2 tokenizer")
diff --git a/bindings/python/py_src/tokenizers/__init__.pyi b/bindings/python/py_src/tokenizers/__init__.pyi
index 9a8c500ce..5dbc665dc 100644
--- a/bindings/python/py_src/tokenizers/__init__.pyi
+++ b/bindings/python/py_src/tokenizers/__init__.pyi
@@ -34,16 +34,7 @@ class AddedToken:
             Defines whether this token should be skipped when decoding.
 
     """
-
-    def __init__(
-        self,
-        content,
-        single_word=False,
-        lstrip=False,
-        rstrip=False,
-        normalized=True,
-        special=False,
-    ):
+    def __init__(self, content, single_word=False, lstrip=False, rstrip=False, normalized=True, special=False):
         pass
 
     @property
@@ -88,12 +79,10 @@ class AddedToken:
         """
         pass
 
-
 class Encoding:
     """
     The :class:`~tokenizers.Encoding` represents the output of a :class:`~tokenizers.Tokenizer`.
     """
-
     @property
     def attention_mask(self):
         """
@@ -206,9 +195,7 @@ class Encoding:
         """
         pass
 
-    def pad(
-        self, length, direction="right", pad_id=0, pad_type_id=0, pad_token="[PAD]"
-    ):
+    def pad(self, length, direction="right", pad_id=0, pad_type_id=0, pad_token="[PAD]"):
         """
         Pad the :class:`~tokenizers.Encoding` at the given length
 
@@ -430,7 +417,6 @@ class Encoding:
         """
         pass
 
-
 class NormalizedString:
     """
     NormalizedString
@@ -443,7 +429,6 @@ class NormalizedString:
         sequence: str:
             The string sequence used to initialize this NormalizedString
     """
-
     def append(self, s):
         """
         Append the given sequence to the string
@@ -581,7 +566,6 @@ class NormalizedString:
         """
         pass
 
-
 class PreTokenizedString:
     """
     PreTokenizedString
@@ -600,7 +584,6 @@ class PreTokenizedString:
         sequence: str:
             The string sequence used to initialize this PreTokenizedString
     """
-
     def __init__(self, sequence):
         pass
 
@@ -681,20 +664,16 @@ class PreTokenizedString:
         """
         pass
 
-
 class Regex:
     """
     Instantiate a new Regex with the given pattern
     """
-
     def __init__(self, pattern):
         pass
 
-
 class Token:
     pass
 
-
 class Tokenizer:
     """
     A :obj:`Tokenizer` works as a pipeline. It processes some raw text as input
@@ -705,7 +684,6 @@ class Tokenizer:
             The core algorithm that this :obj:`Tokenizer` should be using.
 
     """
-
     def __init__(self, model):
         pass
 
@@ -789,13 +767,7 @@ class Tokenizer:
         pass
 
     def enable_padding(
-        self,
-        direction="right",
-        pad_id=0,
-        pad_type_id=0,
-        pad_token="[PAD]",
-        length=None,
-        pad_to_multiple_of=None,
+        self, direction="right", pad_id=0, pad_type_id=0, pad_token="[PAD]", length=None, pad_to_multiple_of=None
     ):
         """
         Enable the padding
@@ -824,9 +796,7 @@ class Tokenizer:
         """
         pass
 
-    def enable_truncation(
-        self, max_length, stride=0, strategy="longest_first", direction="right"
-    ):
+    def enable_truncation(self, max_length, stride=0, strategy="longest_first", direction="right"):
         """
         Enable truncation
 
@@ -847,9 +817,7 @@ class Tokenizer:
         """
         pass
 
-    def encode(
-        self, sequence, pair=None, is_pretokenized=False, add_special_tokens=True
-    ):
+    def encode(self, sequence, pair=None, is_pretokenized=False, add_special_tokens=True):
         """
         Encode the given sequence and pair. This method can process raw text sequences
         as well as already pre-tokenized sequences.
diff --git a/bindings/python/py_src/tokenizers/decoders/__init__.pyi b/bindings/python/py_src/tokenizers/decoders/__init__.pyi
index 2a8692f82..94dda2354 100644
--- a/bindings/python/py_src/tokenizers/decoders/__init__.pyi
+++ b/bindings/python/py_src/tokenizers/decoders/__init__.pyi
@@ -6,7 +6,6 @@ class Decoder:
     This class is not supposed to be instantiated directly. Instead, any implementation of
     a Decoder will return an instance of this class when instantiated.
     """
-
     def decode(self, tokens):
         """
         Decode the given list of tokens to a final string
@@ -20,7 +19,6 @@ class Decoder:
         """
         pass
 
-
 class BPEDecoder(Decoder):
     """
     BPEDecoder Decoder
@@ -30,7 +28,6 @@ class BPEDecoder(Decoder):
             The suffix that was used to caracterize an end-of-word. This suffix will
             be replaced by whitespaces during the decoding
     """
-
     def __init__(self, suffix="</w>"):
         pass
 
@@ -47,7 +44,6 @@ class BPEDecoder(Decoder):
         """
         pass
 
-
 class ByteFallback(Decoder):
     """
     ByteFallback Decoder
@@ -56,7 +52,6 @@ class ByteFallback(Decoder):
     cannot be decoded you will get � instead for each inconvertable byte token
 
     """
-
     def __init__(self):
         pass
 
@@ -73,7 +68,6 @@ class ByteFallback(Decoder):
         """
         pass
 
-
 class ByteLevel(Decoder):
     """
     ByteLevel Decoder
@@ -81,7 +75,6 @@ class ByteLevel(Decoder):
     This decoder is to be used in tandem with the :class:`~tokenizers.pre_tokenizers.ByteLevel`
     :class:`~tokenizers.pre_tokenizers.PreTokenizer`.
     """
-
     def __init__(self):
         pass
 
@@ -98,7 +91,6 @@ class ByteLevel(Decoder):
         """
         pass
 
-
 class CTC(Decoder):
     """
     CTC Decoder
@@ -112,7 +104,6 @@ class CTC(Decoder):
             Whether to cleanup some tokenization artifacts.
             Mainly spaces before punctuation, and some abbreviated english forms.
     """
-
     def __init__(self, pad_token="<pad>", word_delimiter_token="|", cleanup=True):
         pass
 
@@ -129,7 +120,6 @@ class CTC(Decoder):
         """
         pass
 
-
 class Fuse(Decoder):
     """
     Fuse Decoder
@@ -137,7 +127,6 @@ class Fuse(Decoder):
     This is the last step of decoding, this decoder exists only if
     there is need to add other decoders *after* the fusion
     """
-
     def __init__(self):
         pass
 
@@ -154,7 +143,6 @@ class Fuse(Decoder):
         """
         pass
 
-
 class Metaspace(Decoder):
     """
     Metaspace Decoder
@@ -168,7 +156,6 @@ class Metaspace(Decoder):
             Whether to add a space to the first word if there isn't already one. This
             lets us treat `hello` exactly like `say hello`.
     """
-
     def __init__(self, replacement="▁", add_prefix_space=True):
         pass
 
@@ -185,7 +172,6 @@ class Metaspace(Decoder):
         """
         pass
 
-
 class Replace(Decoder):
     """
     Replace Decoder
@@ -193,7 +179,6 @@ class Replace(Decoder):
     This decoder is to be used in tandem with the :class:`~tokenizers.pre_tokenizers.Replace`
     :class:`~tokenizers.pre_tokenizers.PreTokenizer`.
     """
-
     def __init__(self, pattern, content):
         pass
 
@@ -210,7 +195,6 @@ class Replace(Decoder):
         """
         pass
 
-
 class Sequence(Decoder):
     """
     Sequence Decoder
@@ -219,7 +203,6 @@ class Sequence(Decoder):
         decoders (:obj:`List[Decoder]`)
             The decoders that need to be chained
     """
-
     def __init__(self, decoders):
         pass
 
@@ -236,13 +219,11 @@ class Sequence(Decoder):
         """
         pass
 
-
 class Strip(Decoder):
     """
     Strip normalizer
     Strips n left characters of each token, or n right characters of each token
     """
-
     def __init__(self, content, left=0, right=0):
         pass
 
@@ -259,7 +240,6 @@ class Strip(Decoder):
         """
         pass
 
-
 class WordPiece(Decoder):
     """
     WordPiece Decoder
@@ -272,7 +252,6 @@ class WordPiece(Decoder):
             Whether to cleanup some tokenization artifacts. Mainly spaces before punctuation,
             and some abbreviated english forms.
     """
-
     def __init__(self, prefix="##", cleanup=True):
         pass
 
diff --git a/bindings/python/py_src/tokenizers/models/__init__.py b/bindings/python/py_src/tokenizers/models/__init__.py
index 68ac211aa..e69de29bb 100644
--- a/bindings/python/py_src/tokenizers/models/__init__.py
+++ b/bindings/python/py_src/tokenizers/models/__init__.py
@@ -1,8 +0,0 @@
-# Generated content DO NOT EDIT
-from .. import models
-
-Model = models.Model
-BPE = models.BPE
-Unigram = models.Unigram
-WordLevel = models.WordLevel
-WordPiece = models.WordPiece
diff --git a/bindings/python/py_src/tokenizers/models/__init__.pyi b/bindings/python/py_src/tokenizers/models/__init__.pyi
index 9c747e611..b46f32f25 100644
--- a/bindings/python/py_src/tokenizers/models/__init__.pyi
+++ b/bindings/python/py_src/tokenizers/models/__init__.pyi
@@ -8,7 +8,6 @@ class Model:
 
     This class cannot be constructed directly. Please use one of the concrete models.
     """
-
     def get_trainer(self):
         """
         Get the associated :class:`~tokenizers.trainers.Trainer`
@@ -80,7 +79,6 @@ class Model:
         """
         pass
 
-
 class BPE(Model):
     """
     An implementation of the BPE (Byte-Pair Encoding) algorithm
@@ -115,7 +113,6 @@ class BPE(Model):
         byte_fallback (:obj:`bool`, `optional`):
             Whether to use spm byte-fallback trick (defaults to False)
     """
-
     def __init__(
         self,
         vocab=None,
@@ -249,7 +246,6 @@ class BPE(Model):
         """
         pass
 
-
 class Unigram(Model):
     """
     An implementation of the Unigram algorithm
@@ -258,7 +254,6 @@ class Unigram(Model):
         vocab (:obj:`List[Tuple[str, float]]`, `optional`, `optional`):
             A list of vocabulary items and their relative score [("am", -0.2442),...]
     """
-
     def __init__(self, vocab, unk_id, byte_fallback):
         pass
 
@@ -333,7 +328,6 @@ class Unigram(Model):
         """
         pass
 
-
 class WordLevel(Model):
     """
     An implementation of the WordLevel algorithm
@@ -347,7 +341,6 @@ class WordLevel(Model):
         unk_token (:obj:`str`, `optional`):
             The unknown token to be used by the model.
     """
-
     def __init__(self, vocab, unk_token):
         pass
 
@@ -463,7 +456,6 @@ class WordLevel(Model):
         """
         pass
 
-
 class WordPiece(Model):
     """
     An implementation of the WordPiece algorithm
@@ -478,7 +470,6 @@ class WordPiece(Model):
         max_input_chars_per_word (:obj:`int`, `optional`):
             The maximum number of characters to authorize in a single word.
     """
-
     def __init__(self, vocab, unk_token, max_input_chars_per_word):
         pass
 
diff --git a/bindings/python/py_src/tokenizers/normalizers/__init__.pyi b/bindings/python/py_src/tokenizers/normalizers/__init__.pyi
index 996c255ca..507d44731 100644
--- a/bindings/python/py_src/tokenizers/normalizers/__init__.pyi
+++ b/bindings/python/py_src/tokenizers/normalizers/__init__.pyi
@@ -6,7 +6,6 @@ class Normalizer:
     This class is not supposed to be instantiated directly. Instead, any implementation of a
     Normalizer will return an instance of this class when instantiated.
     """
-
     def normalize(self, normalized):
         """
         Normalize a :class:`~tokenizers.NormalizedString` in-place
@@ -41,7 +40,6 @@ class Normalizer:
         """
         pass
 
-
 class BertNormalizer(Normalizer):
     """
     BertNormalizer
@@ -64,14 +62,7 @@ class BertNormalizer(Normalizer):
         lowercase (:obj:`bool`, `optional`, defaults to :obj:`True`):
             Whether to lowercase.
     """
-
-    def __init__(
-        self,
-        clean_text=True,
-        handle_chinese_chars=True,
-        strip_accents=None,
-        lowercase=True,
-    ):
+    def __init__(self, clean_text=True, handle_chinese_chars=True, strip_accents=None, lowercase=True):
         pass
 
     def normalize(self, normalized):
@@ -108,12 +99,10 @@ class BertNormalizer(Normalizer):
         """
         pass
 
-
 class Lowercase(Normalizer):
     """
     Lowercase Normalizer
     """
-
     def __init__(self):
         pass
 
@@ -151,12 +140,10 @@ class Lowercase(Normalizer):
         """
         pass
 
-
 class NFC(Normalizer):
     """
     NFC Unicode Normalizer
     """
-
     def __init__(self):
         pass
 
@@ -194,12 +181,10 @@ class NFC(Normalizer):
         """
         pass
 
-
 class NFD(Normalizer):
     """
     NFD Unicode Normalizer
     """
-
     def __init__(self):
         pass
 
@@ -237,12 +222,10 @@ class NFD(Normalizer):
         """
         pass
 
-
 class NFKC(Normalizer):
     """
     NFKC Unicode Normalizer
     """
-
     def __init__(self):
         pass
 
@@ -280,12 +263,10 @@ class NFKC(Normalizer):
         """
         pass
 
-
 class NFKD(Normalizer):
     """
     NFKD Unicode Normalizer
     """
-
     def __init__(self):
         pass
 
@@ -323,12 +304,10 @@ class NFKD(Normalizer):
         """
         pass
 
-
 class Nmt(Normalizer):
     """
     Nmt normalizer
     """
-
     def __init__(self):
         pass
 
@@ -366,13 +345,11 @@ class Nmt(Normalizer):
         """
         pass
 
-
 class Precompiled(Normalizer):
     """
     Precompiled normalizer
     Don't use manually it is used for compatiblity for SentencePiece.
     """
-
     def __init__(self, precompiled_charsmap):
         pass
 
@@ -410,12 +387,10 @@ class Precompiled(Normalizer):
         """
         pass
 
-
 class Prepend(Normalizer):
     """
     Prepend normalizer
     """
-
     def __init__(self, prepend):
         pass
 
@@ -453,12 +428,10 @@ class Prepend(Normalizer):
         """
         pass
 
-
 class Replace(Normalizer):
     """
     Replace normalizer
     """
-
     def __init__(self, pattern, content):
         pass
 
@@ -496,7 +469,6 @@ class Replace(Normalizer):
         """
         pass
 
-
 class Sequence(Normalizer):
     """
     Allows concatenating multiple other Normalizer as a Sequence.
@@ -506,7 +478,6 @@ class Sequence(Normalizer):
         normalizers (:obj:`List[Normalizer]`):
             A list of Normalizer to be run as a sequence
     """
-
     def normalize(self, normalized):
         """
         Normalize a :class:`~tokenizers.NormalizedString` in-place
@@ -541,12 +512,10 @@ class Sequence(Normalizer):
         """
         pass
 
-
 class Strip(Normalizer):
     """
     Strip normalizer
     """
-
     def __init__(self, left=True, right=True):
         pass
 
@@ -584,12 +553,10 @@ class Strip(Normalizer):
         """
         pass
 
-
 class StripAccents(Normalizer):
     """
     StripAccents normalizer
     """
-
     def __init__(self):
         pass
 
diff --git a/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.py b/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.py
index 48277f0d2..e69de29bb 100644
--- a/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.py
+++ b/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.py
@@ -1,15 +0,0 @@
-# Generated content DO NOT EDIT
-from .. import pre_tokenizers
-
-PreTokenizer = pre_tokenizers.PreTokenizer
-BertPreTokenizer = pre_tokenizers.BertPreTokenizer
-ByteLevel = pre_tokenizers.ByteLevel
-CharDelimiterSplit = pre_tokenizers.CharDelimiterSplit
-Digits = pre_tokenizers.Digits
-Metaspace = pre_tokenizers.Metaspace
-Punctuation = pre_tokenizers.Punctuation
-Sequence = pre_tokenizers.Sequence
-Split = pre_tokenizers.Split
-UnicodeScripts = pre_tokenizers.UnicodeScripts
-Whitespace = pre_tokenizers.Whitespace
-WhitespaceSplit = pre_tokenizers.WhitespaceSplit
diff --git a/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.pyi b/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.pyi
index 852a52e19..9e975326f 100644
--- a/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.pyi
+++ b/bindings/python/py_src/tokenizers/pre_tokenizers/__init__.pyi
@@ -6,7 +6,6 @@ class PreTokenizer:
     This class is not supposed to be instantiated directly. Instead, any implementation of a
     PreTokenizer will return an instance of this class when instantiated.
     """
-
     def pre_tokenize(self, pretok):
         """
         Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
@@ -44,7 +43,6 @@ class PreTokenizer:
         """
         pass
 
-
 class BertPreTokenizer(PreTokenizer):
     """
     BertPreTokenizer
@@ -52,7 +50,6 @@ class BertPreTokenizer(PreTokenizer):
     This pre-tokenizer splits tokens on spaces, and also on punctuation.
     Each occurence of a punctuation character will be treated separately.
     """
-
     def __init__(self):
         pass
 
@@ -93,7 +90,6 @@ class BertPreTokenizer(PreTokenizer):
         """
         pass
 
-
 class ByteLevel(PreTokenizer):
     """
     ByteLevel PreTokenizer
@@ -109,7 +105,6 @@ class ByteLevel(PreTokenizer):
             Set this to :obj:`False` to prevent this `pre_tokenizer` from using
             the GPT2 specific regexp for spliting on whitespace.
     """
-
     def __init__(self, add_prefix_space=True, use_regex=True):
         pass
 
@@ -164,7 +159,6 @@ class ByteLevel(PreTokenizer):
         """
         pass
 
-
 class CharDelimiterSplit(PreTokenizer):
     """
     This pre-tokenizer simply splits on the provided char. Works like `.split(delimiter)`
@@ -173,7 +167,6 @@ class CharDelimiterSplit(PreTokenizer):
         delimiter: str:
             The delimiter char that will be used to split input
     """
-
     def pre_tokenize(self, pretok):
         """
         Pre-tokenize a :class:`~tokenizers.PyPreTokenizedString` in-place
@@ -211,7 +204,6 @@ class CharDelimiterSplit(PreTokenizer):
         """
         pass
 
-
 class Digits(PreTokenizer):
     """
     This pre-tokenizer simply splits using the digits in separate tokens
@@ -226,7 +218,6 @@ class Digits(PreTokenizer):
 
                 "Call 123 please" -> "Call ", "123", " please"
     """
-
     def __init__(self, individual_digits=False):
         pass
 
@@ -267,7 +258,6 @@ class Digits(PreTokenizer):
         """
         pass
 
-
 class Metaspace(PreTokenizer):
     """
     Metaspace pre-tokenizer
@@ -284,7 +274,6 @@ class Metaspace(PreTokenizer):
             Whether to add a space to the first word if there isn't already one. This
             lets us treat `hello` exactly like `say hello`.
     """
-
     def __init__(self, replacement="_", add_prefix_space=True):
         pass
 
@@ -325,7 +314,6 @@ class Metaspace(PreTokenizer):
         """
         pass
 
-
 class Punctuation(PreTokenizer):
     """
     This pre-tokenizer simply splits on punctuation as individual characters.
@@ -336,7 +324,6 @@ class Punctuation(PreTokenizer):
             Choices: "removed", "isolated" (default), "merged_with_previous", "merged_with_next",
             "contiguous"
     """
-
     def __init__(self, behavior="isolated"):
         pass
 
@@ -377,12 +364,10 @@ class Punctuation(PreTokenizer):
         """
         pass
 
-
 class Sequence(PreTokenizer):
     """
     This pre-tokenizer composes other pre_tokenizers and applies them in sequence
     """
-
     def __init__(self, pretokenizers):
         pass
 
@@ -423,7 +408,6 @@ class Sequence(PreTokenizer):
         """
         pass
 
-
 class Split(PreTokenizer):
     """
     Split PreTokenizer
@@ -444,7 +428,6 @@ class Split(PreTokenizer):
         invert (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether to invert the pattern.
     """
-
     def __init__(self, pattern, behavior, invert=False):
         pass
 
@@ -485,7 +468,6 @@ class Split(PreTokenizer):
         """
         pass
 
-
 class UnicodeScripts(PreTokenizer):
     """
     This pre-tokenizer splits on characters that belong to different language family
@@ -493,7 +475,6 @@ class UnicodeScripts(PreTokenizer):
     Actually Hiragana and Katakana are fused with Han, and 0x30FC is Han too.
     This mimicks SentencePiece Unigram implementation.
     """
-
     def __init__(self):
         pass
 
@@ -534,12 +515,10 @@ class UnicodeScripts(PreTokenizer):
         """
         pass
 
-
 class Whitespace(PreTokenizer):
     """
     This pre-tokenizer simply splits using the following regex: `\w+|[^\w\s]+`
     """
-
     def __init__(self):
         pass
 
@@ -580,12 +559,10 @@ class Whitespace(PreTokenizer):
         """
         pass
 
-
 class WhitespaceSplit(PreTokenizer):
     """
     This pre-tokenizer simply splits on the whitespace. Works like `.split()`
     """
-
     def __init__(self):
         pass
 
diff --git a/bindings/python/py_src/tokenizers/processors/__init__.py b/bindings/python/py_src/tokenizers/processors/__init__.py
index 06d124037..e69de29bb 100644
--- a/bindings/python/py_src/tokenizers/processors/__init__.py
+++ b/bindings/python/py_src/tokenizers/processors/__init__.py
@@ -1,9 +0,0 @@
-# Generated content DO NOT EDIT
-from .. import processors
-
-PostProcessor = processors.PostProcessor
-BertProcessing = processors.BertProcessing
-ByteLevel = processors.ByteLevel
-RobertaProcessing = processors.RobertaProcessing
-Sequence = processors.Sequence
-TemplateProcessing = processors.TemplateProcessing
diff --git a/bindings/python/py_src/tokenizers/processors/__init__.pyi b/bindings/python/py_src/tokenizers/processors/__init__.pyi
index 0b1652ca6..5136d02bb 100644
--- a/bindings/python/py_src/tokenizers/processors/__init__.pyi
+++ b/bindings/python/py_src/tokenizers/processors/__init__.pyi
@@ -6,7 +6,6 @@ class PostProcessor:
     This class is not supposed to be instantiated directly. Instead, any implementation of
     a PostProcessor will return an instance of this class when instantiated.
     """
-
     def num_special_tokens_to_add(self, is_pair):
         """
         Return the number of special tokens that would be added for single/pair sentences.
@@ -39,7 +38,6 @@ class PostProcessor:
         """
         pass
 
-
 class BertProcessing(PostProcessor):
     """
     This post-processor takes care of adding the special tokens needed by
@@ -55,7 +53,6 @@ class BertProcessing(PostProcessor):
         cls (:obj:`Tuple[str, int]`):
             A tuple with the string representation of the CLS token, and its id
     """
-
     def __init__(self, sep, cls):
         pass
 
@@ -91,7 +88,6 @@ class BertProcessing(PostProcessor):
         """
         pass
 
-
 class ByteLevel(PostProcessor):
     """
     This post-processor takes care of trimming the offsets.
@@ -103,7 +99,6 @@ class ByteLevel(PostProcessor):
         trim_offsets (:obj:`bool`):
             Whether to trim the whitespaces from the produced offsets.
     """
-
     def __init__(self, trim_offsets=True):
         pass
 
@@ -139,7 +134,6 @@ class ByteLevel(PostProcessor):
         """
         pass
 
-
 class RobertaProcessing(PostProcessor):
     """
     This post-processor takes care of adding the special tokens needed by
@@ -167,7 +161,6 @@ class RobertaProcessing(PostProcessor):
             Whether the add_prefix_space option was enabled during pre-tokenization. This
             is relevant because it defines the way the offsets are trimmed out.
     """
-
     def __init__(self, sep, cls, trim_offsets=True, add_prefix_space=True):
         pass
 
@@ -203,7 +196,6 @@ class RobertaProcessing(PostProcessor):
         """
         pass
 
-
 class Sequence(PostProcessor):
     """
     Sequence Processor
@@ -212,7 +204,6 @@ class Sequence(PostProcessor):
         processors (:obj:`List[PostProcessor]`)
             The processors that need to be chained
     """
-
     def __init__(self, processors):
         pass
 
@@ -248,7 +239,6 @@ class Sequence(PostProcessor):
         """
         pass
 
-
 class TemplateProcessing(PostProcessor):
     """
     Provides a way to specify templates in order to add the special tokens to each
@@ -316,7 +306,6 @@ class TemplateProcessing(PostProcessor):
              The given dict expects the provided :obj:`ids` and :obj:`tokens` lists to have
              the same length.
     """
-
     def __init__(self, single, pair, special_tokens):
         pass
 
diff --git a/bindings/python/py_src/tokenizers/trainers/__init__.py b/bindings/python/py_src/tokenizers/trainers/__init__.py
index 22f94c50b..e69de29bb 100644
--- a/bindings/python/py_src/tokenizers/trainers/__init__.py
+++ b/bindings/python/py_src/tokenizers/trainers/__init__.py
@@ -1,8 +0,0 @@
-# Generated content DO NOT EDIT
-from .. import trainers
-
-Trainer = trainers.Trainer
-BpeTrainer = trainers.BpeTrainer
-UnigramTrainer = trainers.UnigramTrainer
-WordLevelTrainer = trainers.WordLevelTrainer
-WordPieceTrainer = trainers.WordPieceTrainer
diff --git a/bindings/python/py_src/tokenizers/trainers/__init__.pyi b/bindings/python/py_src/tokenizers/trainers/__init__.pyi
index 399340cc7..d6c525718 100644
--- a/bindings/python/py_src/tokenizers/trainers/__init__.pyi
+++ b/bindings/python/py_src/tokenizers/trainers/__init__.pyi
@@ -7,7 +7,6 @@ class Trainer:
     Trainer will return an instance of this class when instantiated.
     """
 
-
 class BpeTrainer(Trainer):
     """
     Trainer capable of training a BPE model
@@ -47,7 +46,6 @@ class BpeTrainer(Trainer):
 
     """
 
-
 class UnigramTrainer(Trainer):
     """
     Trainer capable of training a Unigram model
@@ -82,7 +80,6 @@ class UnigramTrainer(Trainer):
             The number of iterations of the EM algorithm to perform before
             pruning the vocabulary.
     """
-
     def __init__(
         self,
         vocab_size=8000,
@@ -95,7 +92,6 @@ class UnigramTrainer(Trainer):
     ):
         pass
 
-
 class WordLevelTrainer(Trainer):
     """
     Trainer capable of training a WorldLevel model
@@ -114,7 +110,6 @@ class WordLevelTrainer(Trainer):
             A list of special tokens the model should know of.
     """
 
-
 class WordPieceTrainer(Trainer):
     """
     Trainer capable of training a WordPiece model
@@ -147,7 +142,6 @@ class WordPieceTrainer(Trainer):
         end_of_word_suffix (:obj:`str`, `optional`):
             A suffix to be used for every subword that is a end-of-word.
     """
-
     def __init__(
         self,
         vocab_size=30000,
diff --git a/bindings/python/pyproject.toml b/bindings/python/pyproject.toml
index cbe463370..8702fc37b 100644
--- a/bindings/python/pyproject.toml
+++ b/bindings/python/pyproject.toml
@@ -54,6 +54,8 @@ line-length = 119
 target-version = ['py35']
 
 [tool.ruff]
+line-length = 119
+target-version = "py311"
 lint.ignore = [
     # a == None in tests vs is None.
     "E711",
diff --git a/bindings/python/scripts/convert.py b/bindings/python/scripts/convert.py
index 6c812f8c7..e6df5ad8a 100644
--- a/bindings/python/scripts/convert.py
+++ b/bindings/python/scripts/convert.py
@@ -80,9 +80,7 @@ def tokenizer(self, proto):
             tokenizer = Tokenizer(Unigram(vocab, unk_id))
         elif model_type == 2:
             vocab, merges = SentencePieceExtractor(self.original_tokenizer.vocab_file).extract()
-            tokenizer = Tokenizer(
-                BPE(vocab, merges, unk_token=proto.trainer_spec.unk_piece, fuse_unk=True)
-            )
+            tokenizer = Tokenizer(BPE(vocab, merges, unk_token=proto.trainer_spec.unk_piece, fuse_unk=True))
         else:
             raise Exception(
                 "You're trying to run a `Unigram` model but you're file was trained with a different algorithm"
@@ -105,12 +103,8 @@ def converted(self):
 
         replacement = "▁"
         add_prefix_space = True
-        tokenizer.pre_tokenizer = Metaspace(
-            replacement=replacement, add_prefix_space=add_prefix_space
-        )
-        tokenizer.decoder = decoders.Metaspace(
-            replacement=replacement, add_prefix_space=add_prefix_space
-        )
+        tokenizer.pre_tokenizer = Metaspace(replacement=replacement, add_prefix_space=add_prefix_space)
+        tokenizer.decoder = decoders.Metaspace(replacement=replacement, add_prefix_space=add_prefix_space)
         post_processor = self.post_processor(tokenizer)
         if post_processor:
             tokenizer.post_processor = post_processor
@@ -124,9 +118,7 @@ def converted(self):
 class AlbertConverter(SpmConverter):
     def vocab(self, proto):
         return [
-            (piece.piece, piece.score)
-            if check_number_comma(piece.piece)
-            else (piece.piece, piece.score - 100)
+            (piece.piece, piece.score) if check_number_comma(piece.piece) else (piece.piece, piece.score - 100)
             for piece in proto.pieces
         ]
 
@@ -261,9 +253,7 @@ def post_processor(self, tokenizer):
 class XLNetConverter(SpmConverter):
     def vocab(self, proto):
         return [
-            (piece.piece, piece.score)
-            if check_number_comma(piece.piece)
-            else (piece.piece, piece.score - 100)
+            (piece.piece, piece.score) if check_number_comma(piece.piece) else (piece.piece, piece.score - 100)
             for piece in proto.pieces
         ]
 
@@ -420,9 +410,7 @@ def main():
     print(f"|{'-'*model_len}|{'-'*status_len}|{'-'*speedup_len}|")
     for pretrained in args.models:
         status, speedup = check(pretrained, args.filename)
-        print(
-            f"|{pretrained:<{model_len}}|{status:^{status_len}}|{speedup:^{speedup_len - 1}.2f}x|"
-        )
+        print(f"|{pretrained:<{model_len}}|{status:^{status_len}}|{speedup:^{speedup_len - 1}.2f}x|")
 
 
 if __name__ == "__main__":
diff --git a/bindings/python/scripts/sentencepiece_extractor.py b/bindings/python/scripts/sentencepiece_extractor.py
index fba05d8f4..a7bce9b49 100644
--- a/bindings/python/scripts/sentencepiece_extractor.py
+++ b/bindings/python/scripts/sentencepiece_extractor.py
@@ -59,7 +59,6 @@ def __init__(self, model: str):
 
     def extract(self) -> Tuple[Dict[str, int], List[Tuple]]:
         with open(self._model, "r") as model_f:
-
             # Retrieve information
             nb_pieces, nb_merges = map(int, model_f.readline().split())
             vocab, merges = {}, []
@@ -97,9 +96,7 @@ def extract(self) -> Tuple[Dict[str, int], List[Tuple]]:
         choices=["sentencepiece", "youtokentome"],
         help="Indicate the format of the file.",
     )
-    parser.add_argument(
-        "--model", type=str, required=True, help="SentencePiece model to extract vocab from."
-    )
+    parser.add_argument("--model", type=str, required=True, help="SentencePiece model to extract vocab from.")
     parser.add_argument(
         "--vocab-output-path",
         type=str,
@@ -128,9 +125,7 @@ def extract(self) -> Tuple[Dict[str, int], List[Tuple]]:
                 args.model = f.name
 
         # Allocate extractor
-        extractor = (
-            SentencePieceExtractor if args.provider == "sentencepiece" else YouTokenToMeExtractor
-        )
+        extractor = SentencePieceExtractor if args.provider == "sentencepiece" else YouTokenToMeExtractor
         extractor = extractor(args.model)
 
         logger.info(f"Using {type(extractor).__name__}")
diff --git a/bindings/python/scripts/spm_parity_check.py b/bindings/python/scripts/spm_parity_check.py
index 09e5b9475..33cfff4fa 100644
--- a/bindings/python/scripts/spm_parity_check.py
+++ b/bindings/python/scripts/spm_parity_check.py
@@ -121,9 +121,7 @@ def check_train(args):
             break
 
     print(f"Tokenizer used {tokenizer_tokens}, where spm used {spm_tokens}")
-    assert (
-        tokenizer_tokens < spm_tokens
-    ), "Our trainer should be at least more efficient than the SPM one"
+    assert tokenizer_tokens < spm_tokens, "Our trainer should be at least more efficient than the SPM one"
     print("Ok our trainer is at least more efficient than the SPM one")
 
 
@@ -131,9 +129,7 @@ def check_diff(spm_diff, tok_diff, sp, tok):
     if spm_diff == list(reversed(tok_diff)):
         # AAA -> AA+A vs A+AA case.
         return True
-    elif len(spm_diff) == len(tok_diff) and tok.decode(spm_diff) == tok.decode(
-        tok_diff
-    ):
+    elif len(spm_diff) == len(tok_diff) and tok.decode(spm_diff) == tok.decode(tok_diff):
         # Second order OK
         # Barrich -> Barr + ich vs Bar + rich
         return True
@@ -173,24 +169,17 @@ def check_details(line, spm_ids, tok_ids, sp, tok):
         spms = Counter(spm_ids[first:last])
         toks = Counter(tok_ids[first:last])
 
-        removable_tokens = {
-            spm_ for (spm_, si) in spms.items() if toks.get(spm_, 0) == si
-        }
+        removable_tokens = {spm_ for (spm_, si) in spms.items() if toks.get(spm_, 0) == si}
         min_width = 3
         for i in range(last - first - min_width):
-            if all(
-                spm_ids[first + i + j] in removable_tokens for j in range(min_width)
-            ):
+            if all(spm_ids[first + i + j] in removable_tokens for j in range(min_width)):
                 possible_matches = [
                     k
                     for k in range(last - first - min_width)
-                    if tok_ids[first + k : first + k + min_width]
-                    == spm_ids[first + i : first + i + min_width]
+                    if tok_ids[first + k : first + k + min_width] == spm_ids[first + i : first + i + min_width]
                 ]
                 for j in possible_matches:
-                    if check_diff(
-                        spm_ids[first : first + i], tok_ids[first : first + j], sp, tok
-                    ) and check_details(
+                    if check_diff(spm_ids[first : first + i], tok_ids[first : first + j], sp, tok) and check_details(
                         line,
                         spm_ids[first + i : last],
                         tok_ids[first + j : last],
@@ -210,9 +199,7 @@ def check_details(line, spm_ids, tok_ids, sp, tok):
     wrong = tok.decode(spm_ids[first:last])
     print()
     if has_color:
-        print(
-            f"{colored(ok_start, 'grey')}{colored(wrong, 'red')}{colored(ok_end, 'grey')}"
-        )
+        print(f"{colored(ok_start, 'grey')}{colored(wrong, 'red')}{colored(ok_end, 'grey')}")
     else:
         print(wrong)
     return False
@@ -251,9 +238,7 @@ def check_encode(args):
 
             if args.verbose:
                 if i % 10000 == 0:
-                    print(
-                        f"({perfect} / {imperfect} / {wrong} ----- {perfect + imperfect + wrong})"
-                    )
+                    print(f"({perfect} / {imperfect} / {wrong} ----- {perfect + imperfect + wrong})")
                     print(f"SPM: {spm_total_time} - TOK: {tok_total_time}")
 
             if ids != encoded.ids:
@@ -265,13 +250,13 @@ def check_encode(args):
             else:
                 perfect += 1
 
-            assert ids == encoded.ids, f"line {i}: {line} : \n\n{ids}\n{encoded.ids}\n{list(zip(encoded.ids, encoded.tokens))}"
+            assert (
+                ids == encoded.ids
+            ), f"line {i}: {line} : \n\n{ids}\n{encoded.ids}\n{list(zip(encoded.ids, encoded.tokens))}"
 
     print(f"({perfect} / {imperfect} / {wrong} ----- {perfect + imperfect + wrong})")
     total = perfect + imperfect + wrong
-    print(
-        f"Accuracy {perfect * 100 / total:.2f} Slowdown : {tok_total_time/ spm_total_time:.2f}"
-    )
+    print(f"Accuracy {perfect * 100 / total:.2f} Slowdown : {tok_total_time/ spm_total_time:.2f}")
 
 
 if __name__ == "__main__":
diff --git a/bindings/python/stub.py b/bindings/python/stub.py
index 672eb803f..41ef2d6ec 100644
--- a/bindings/python/stub.py
+++ b/bindings/python/stub.py
@@ -83,7 +83,7 @@ def pyi_file(obj, indent=""):
             body += f"{indent+INDENT}pass\n"
             body += "\n"
 
-        for (name, fn) in fns:
+        for name, fn in fns:
             body += pyi_file(fn, indent=indent)
 
         if not body:
@@ -119,28 +119,18 @@ def py_file(module, origin):
         string += f"{name} = {origin}.{name}\n"
     return string
 
+
 import subprocess
 from typing import List, Optional, Tuple
 
+
 def do_ruff(code, is_pyi: bool):
-    command = ["ruff", "format", "-", "--config", "pyproject.toml", "--silent"]
+    command = ["ruff", "format", "--config", "pyproject.toml", "--silent", "-"]
+    if is_pyi:
+        command.extend(["--stdin-filename", "test.pyi"])
     process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
-    stdout, _ = process.communicate(input=code.encode())
-    return stdout.decode()
-
-
-def do_black(content, is_pyi):
-    mode = black.Mode(
-        target_versions={black.TargetVersion.PY35},
-        line_length=119,
-        is_pyi=is_pyi,
-        string_normalization=True,
-        experimental_string_processing=False,
-    )
-    try:
-        return black.format_file_contents(content, fast=True, mode=mode)
-    except black.NothingChanged:
-        return content
+    stdout, _ = process.communicate(input=code.encode("utf-8"))
+    return stdout.decode("utf-8")
 
 
 def write(module, directory, origin, check=False):
diff --git a/bindings/python/tests/bindings/test_encoding.py b/bindings/python/tests/bindings/test_encoding.py
index 189da4fee..e82fc6dda 100644
--- a/bindings/python/tests/bindings/test_encoding.py
+++ b/bindings/python/tests/bindings/test_encoding.py
@@ -3,7 +3,6 @@
 from tokenizers import BertWordPieceTokenizer
 
 
-
 class TestEncoding:
     @pytest.fixture(scope="class")
     def encodings(self, bert_files):
diff --git a/bindings/python/tests/bindings/test_models.py b/bindings/python/tests/bindings/test_models.py
index cae7f2e6e..919b5043b 100644
--- a/bindings/python/tests/bindings/test_models.py
+++ b/bindings/python/tests/bindings/test_models.py
@@ -5,7 +5,6 @@
 from tokenizers.models import BPE, Model, WordLevel, WordPiece
 
 
-
 class TestBPE:
     def test_instantiate(self, roberta_files):
         assert isinstance(BPE(), Model)
diff --git a/bindings/python/tests/bindings/test_processors.py b/bindings/python/tests/bindings/test_processors.py
index 4522977f8..f30c93d2f 100644
--- a/bindings/python/tests/bindings/test_processors.py
+++ b/bindings/python/tests/bindings/test_processors.py
@@ -16,7 +16,6 @@
 )
 
 
-
 class TestBertProcessing:
     def test_instantiate(self):
         processor = BertProcessing(("[SEP]", 0), ("[CLS]", 1))
diff --git a/bindings/python/tests/bindings/test_trainers.py b/bindings/python/tests/bindings/test_trainers.py
index 3a799ab45..0f406c288 100644
--- a/bindings/python/tests/bindings/test_trainers.py
+++ b/bindings/python/tests/bindings/test_trainers.py
@@ -15,7 +15,6 @@
 )
 
 
-
 class TestBpeTrainer:
     def test_can_modify(self):
         trainer = trainers.BpeTrainer(
diff --git a/bindings/python/tests/documentation/test_pipeline.py b/bindings/python/tests/documentation/test_pipeline.py
index 0a8c02530..ae8127be6 100644
--- a/bindings/python/tests/documentation/test_pipeline.py
+++ b/bindings/python/tests/documentation/test_pipeline.py
@@ -1,7 +1,6 @@
 from tokenizers import Tokenizer
 
 
-
 disable_printing = True
 original_print = print
 
diff --git a/bindings/python/tests/documentation/test_quicktour.py b/bindings/python/tests/documentation/test_quicktour.py
index e81c642b4..8bca8d680 100644
--- a/bindings/python/tests/documentation/test_quicktour.py
+++ b/bindings/python/tests/documentation/test_quicktour.py
@@ -1,7 +1,6 @@
 from tokenizers import Tokenizer
 
 
-
 disable_printing = True
 original_print = print
 
diff --git a/bindings/python/tests/documentation/test_tutorial_train_from_iterators.py b/bindings/python/tests/documentation/test_tutorial_train_from_iterators.py
index f0934cf11..2ba51c4be 100644
--- a/bindings/python/tests/documentation/test_tutorial_train_from_iterators.py
+++ b/bindings/python/tests/documentation/test_tutorial_train_from_iterators.py
@@ -6,7 +6,6 @@
 import pytest
 
 
-
 class TestTrainFromIterators:
     @staticmethod
     def get_tokenizer_trainer():
diff --git a/bindings/python/tests/implementations/test_base_tokenizer.py b/bindings/python/tests/implementations/test_base_tokenizer.py
index d42c40c4e..535964656 100644
--- a/bindings/python/tests/implementations/test_base_tokenizer.py
+++ b/bindings/python/tests/implementations/test_base_tokenizer.py
@@ -1,4 +1,3 @@
-
 from tokenizers import Tokenizer, decoders, models, normalizers, pre_tokenizers, processors
 from tokenizers.implementations import BaseTokenizer
 
diff --git a/bindings/python/tests/implementations/test_bert_wordpiece.py b/bindings/python/tests/implementations/test_bert_wordpiece.py
index 4333bc87d..2c47beb68 100644
--- a/bindings/python/tests/implementations/test_bert_wordpiece.py
+++ b/bindings/python/tests/implementations/test_bert_wordpiece.py
@@ -1,4 +1,3 @@
-
 from tokenizers import BertWordPieceTokenizer
 
 from ..utils import multiprocessing_with_parallelism
diff --git a/bindings/python/tests/implementations/test_byte_level_bpe.py b/bindings/python/tests/implementations/test_byte_level_bpe.py
index 3f063a24c..d6af6e31e 100644
--- a/bindings/python/tests/implementations/test_byte_level_bpe.py
+++ b/bindings/python/tests/implementations/test_byte_level_bpe.py
@@ -1,4 +1,3 @@
-
 from tokenizers import ByteLevelBPETokenizer
 
 from ..utils import multiprocessing_with_parallelism
diff --git a/bindings/python/tests/implementations/test_char_bpe.py b/bindings/python/tests/implementations/test_char_bpe.py
index de7db1c8c..b786ca850 100644
--- a/bindings/python/tests/implementations/test_char_bpe.py
+++ b/bindings/python/tests/implementations/test_char_bpe.py
@@ -1,4 +1,3 @@
-
 from tokenizers import CharBPETokenizer
 
 from ..utils import multiprocessing_with_parallelism
diff --git a/bindings/python/tests/implementations/test_sentencepiece.py b/bindings/python/tests/implementations/test_sentencepiece.py
index a7f7208a2..1da41fec0 100644
--- a/bindings/python/tests/implementations/test_sentencepiece.py
+++ b/bindings/python/tests/implementations/test_sentencepiece.py
@@ -1,4 +1,3 @@
-
 import pytest
 
 from tokenizers import SentencePieceBPETokenizer, SentencePieceUnigramTokenizer
diff --git a/bindings/python/tests/test_serialization.py b/bindings/python/tests/test_serialization.py
index 22ed21e90..d0111a88e 100644
--- a/bindings/python/tests/test_serialization.py
+++ b/bindings/python/tests/test_serialization.py
@@ -8,7 +8,6 @@
 from tokenizers import Tokenizer
 
 
-
 class TestSerialization:
     def test_full_serialization_albert(self, albert_base):
         # Check we can read this file.
@@ -74,7 +73,7 @@ def test_full_deserialization_hub(self):
             except Exception as e:
                 print(f"{model_id} is not loadable: {e}")
                 not_loadable.append(model_id)
-            except: # noqa: E722
+            except:  # noqa: E722
                 print(f"{model_id} is not loadable: Rust error")
                 not_loadable.append(model_id)