diff --git a/bindings/python/src/encoding.rs b/bindings/python/src/encoding.rs
index a93d29e7..ac0be33d 100644
--- a/bindings/python/src/encoding.rs
+++ b/bindings/python/src/encoding.rs
@@ -109,7 +109,7 @@ impl Encoding {
 impl PyObjectProtocol for Encoding {
     fn __repr__(&self) -> PyResult<String> {
         Ok(format!(
-            "Encoding(num_tokens={}, attributs=[ids, type_ids, tokens, offsets, \
+            "Encoding(num_tokens={}, attributes=[ids, type_ids, tokens, offsets, \
              attention_mask, special_tokens_mask, overflowing, original_str, normalized_str])",
             self.encoding.get_ids().len()
         ))
diff --git a/bindings/python/tokenizers/implementations/base_tokenizer.py b/bindings/python/tokenizers/implementations/base_tokenizer.py
index e8ac08c1..2c3d9432 100644
--- a/bindings/python/tokenizers/implementations/base_tokenizer.py
+++ b/bindings/python/tokenizers/implementations/base_tokenizer.py
@@ -12,7 +12,7 @@ class BaseTokenizer:
     def __repr__(self):
         return "Tokenizer(vocabulary_size={}, {})".format(
             self._tokenizer.get_vocab_size(),
-            ', '.join(k + ': ' + str(v) for k, v in self._parameters.items()))
+            ', '.join(k + '=' + str(v) for k, v in self._parameters.items()))
 
     def enable_padding(self,
                        direction: Optional[str] = "right",
diff --git a/bindings/python/tokenizers/implementations/bert_wordpiece.py b/bindings/python/tokenizers/implementations/bert_wordpiece.py
index c3564c21..a7d89f04 100644
--- a/bindings/python/tokenizers/implementations/bert_wordpiece.py
+++ b/bindings/python/tokenizers/implementations/bert_wordpiece.py
@@ -33,14 +33,14 @@ class BertWordPieceTokenizer(BaseTokenizer):
                                                   lowercase=lowercase)
         tokenizer.pre_tokenizer = BertPreTokenizer.new()
 
-        sep_token_id = tokenizer.token_to_id(sep_token)
-        if sep_token_id is None:
-            raise TypeError("sep_token not found in the vocabulary")
-        cls_token_id = tokenizer.token_to_id(cls_token)
-        if cls_token_id is None:
-            raise TypeError("cls_token not found in the vocabulary")
+        if add_special_tokens and vocab_file is not None:
+            sep_token_id = tokenizer.token_to_id(sep_token)
+            if sep_token_id is None:
+                raise TypeError("sep_token not found in the vocabulary")
+            cls_token_id = tokenizer.token_to_id(cls_token)
+            if cls_token_id is None:
+                raise TypeError("cls_token not found in the vocabulary")
 
-        if add_special_tokens:
             tokenizer.post_processor = BertProcessing.new(
                 (sep_token, sep_token_id),
                 (cls_token, cls_token_id)
@@ -81,4 +81,6 @@ class BertWordPieceTokenizer(BaseTokenizer):
             show_progress=show_progress,
             continuing_subword_prefix=wordpieces_prefix
         )
+        if isinstance(files, str):
+            files = [files]
         self._tokenizer.train(trainer, files)
diff --git a/bindings/python/tokenizers/implementations/bpe.py b/bindings/python/tokenizers/implementations/bpe.py
index 70c86860..eae03502 100644
--- a/bindings/python/tokenizers/implementations/bpe.py
+++ b/bindings/python/tokenizers/implementations/bpe.py
@@ -61,4 +61,6 @@ class BPETokenizer(BaseTokenizer):
             end_of_word_suffix=suffix,
             show_progress=show_progress
         )
+        if isinstance(files, str):
+            files = [files]
         self._tokenizer.train(trainer, files)
diff --git a/bindings/python/tokenizers/implementations/byte_level_bpe.py b/bindings/python/tokenizers/implementations/byte_level_bpe.py
index 118e516c..141cb9cd 100644
--- a/bindings/python/tokenizers/implementations/byte_level_bpe.py
+++ b/bindings/python/tokenizers/implementations/byte_level_bpe.py
@@ -45,4 +45,6 @@ class ByteLevelBPETokenizer(BaseTokenizer):
             special_tokens=special_tokens,
             initial_alphabet=pre_tokenizers.ByteLevel.alphabet()
         )
+        if isinstance(files, str):
+            files = [files]
         self._tokenizer.train(trainer, files)
diff --git a/bindings/python/tokenizers/implementations/sentencepiece_bpe.py b/bindings/python/tokenizers/implementations/sentencepiece_bpe.py
index 65c26bd7..733024b5 100644
--- a/bindings/python/tokenizers/implementations/sentencepiece_bpe.py
+++ b/bindings/python/tokenizers/implementations/sentencepiece_bpe.py
@@ -59,4 +59,6 @@ class SentencePieceBPETokenizer(BaseTokenizer):
             initial_alphabet=initial_alphabet,
             show_progress=show_progress
         )
+        if isinstance(files, str):
+            files = [files]
         self._tokenizer.train(trainer, files)