manually fix PLBart tokenizer

* clean_up_tokenization_spaces=False if unset

* deprecate warning

* updating param for old models

* update models

* make fix-copies

* fix-copies and update bert models

* warning msg

* update prophet and clvp

* updating test since space before is arbitrarily removed

* remove warning for 4.45

examples/flax/question-answering/run_qa.py

@@ -61,7 +61,7 @@ from transformers.utils import check_min_version, send_example_telemetry
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 Array = Any
 Dataset = datasets.arrow_dataset.Dataset

examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py

@@ -60,7 +60,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risk.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/flax/speech-recognition/requirements.txt")
 

examples/flax/text-classification/run_flax_glue.py

@@ -56,7 +56,7 @@ from transformers.utils import check_min_version, send_example_telemetry
 
 logger = logging.getLogger(__name__)
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 Array = Any
 Dataset = datasets.arrow_dataset.Dataset

examples/flax/token-classification/run_flax_ner.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 logger = logging.getLogger(__name__)
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/token-classification/requirements.txt")
 

examples/pytorch/audio-classification/run_audio_classification.py

@@ -45,7 +45,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.14.0", "To fix: pip install -r examples/pytorch/audio-classification/requirements.txt")
 

examples/pytorch/contrastive-image-text/run_clip.py

@@ -54,7 +54,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/contrastive-image-text/requirements.txt")
 

examples/pytorch/image-classification/run_image_classification.py

@@ -56,7 +56,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/image-classification/requirements.txt")
 

examples/pytorch/image-classification/run_image_classification_no_trainer.py

@@ -49,7 +49,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 

examples/pytorch/image-pretraining/run_mae.py

@@ -43,7 +43,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 

examples/pytorch/image-pretraining/run_mim.py

@@ -48,7 +48,7 @@ Any model supported by the AutoModelForMaskedImageModeling API can be used.
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 

examples/pytorch/image-pretraining/run_mim_no_trainer.py

@@ -53,7 +53,7 @@ Any model supported by the AutoModelForMaskedImageModeling API can be used.
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 

examples/pytorch/instance-segmentation/run_instance_segmentation.py

@@ -46,7 +46,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/instance-segmentation/requirements.txt")
 

examples/pytorch/instance-segmentation/run_instance_segmentation_no_trainer.py

@@ -52,7 +52,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/instance-segmentation/requirements.txt")
 

examples/pytorch/language-modeling/run_clm.py

@@ -55,7 +55,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 

examples/pytorch/language-modeling/run_clm_no_trainer.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 

examples/pytorch/language-modeling/run_fim.py

@@ -58,7 +58,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 

examples/pytorch/language-modeling/run_fim_no_trainer.py

@@ -60,7 +60,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 

examples/pytorch/language-modeling/run_mlm.py

@@ -54,7 +54,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 

examples/pytorch/language-modeling/run_mlm_no_trainer.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")

examples/pytorch/language-modeling/run_plm.py

@@ -47,7 +47,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 

examples/pytorch/multiple-choice/run_swag.py

@@ -47,7 +47,7 @@ from transformers.utils import PaddingStrategy, check_min_version, send_example_
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = logging.getLogger(__name__)
 

examples/pytorch/multiple-choice/run_swag_no_trainer.py

@@ -56,7 +56,7 @@ from transformers.utils import PaddingStrategy, check_min_version, send_example_
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 # You should update this to your particular problem to have better documentation of `model_type`

examples/pytorch/object-detection/run_object_detection.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/object-detection/requirements.txt")
 

examples/pytorch/object-detection/run_object_detection_no_trainer.py

@@ -51,7 +51,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logging.basicConfig(level=logging.INFO)
 logger = get_logger(__name__)

examples/pytorch/question-answering/run_qa.py

@@ -50,7 +50,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/question-answering/run_qa_beam_search.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/question-answering/run_qa_beam_search_no_trainer.py

@@ -56,7 +56,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/question-answering/run_qa_no_trainer.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/question-answering/run_seq2seq_qa.py

@@ -46,7 +46,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/semantic-segmentation/run_semantic_segmentation.py

@@ -51,7 +51,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/semantic-segmentation/requirements.txt")
 

examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py

@@ -50,7 +50,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 

examples/pytorch/speech-recognition/run_speech_recognition_ctc.py

@@ -50,7 +50,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 

examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py

@@ -53,7 +53,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 

examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 

examples/pytorch/summarization/run_summarization.py

@@ -52,7 +52,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
 

examples/pytorch/summarization/run_summarization_no_trainer.py

@@ -56,7 +56,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")

examples/pytorch/text-classification/run_classification.py

@@ -47,7 +47,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 

examples/pytorch/text-classification/run_glue.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 

examples/pytorch/text-classification/run_glue_no_trainer.py

@@ -49,7 +49,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 

examples/pytorch/text-classification/run_xnli.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 

examples/pytorch/token-classification/run_ner.py

@@ -49,7 +49,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/token-classification/requirements.txt")
 

examples/pytorch/token-classification/run_ner_no_trainer.py

@@ -56,7 +56,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/token-classification/requirements.txt")

examples/pytorch/translation/run_translation.py

@@ -52,7 +52,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/translation/requirements.txt")
 

examples/pytorch/translation/run_translation_no_trainer.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = get_logger(__name__)
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/translation/requirements.txt")

examples/tensorflow/contrastive-image-text/run_clip.py

@@ -51,7 +51,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version(
     "datasets>=1.8.0", "To fix: pip install -r examples/tensorflow/contrastive-image-text/requirements.txt"

examples/tensorflow/image-classification/run_image_classification.py

@@ -55,7 +55,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-classification/requirements.txt")
 

examples/tensorflow/multiple-choice/run_swag.py

@@ -50,7 +50,7 @@ from transformers.utils import PaddingStrategy, check_min_version, send_example_
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = logging.getLogger(__name__)
 

examples/tensorflow/question-answering/run_qa.py

@@ -62,7 +62,7 @@ except (ModuleNotFoundError, ImportError):
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 logger = logging.getLogger(__name__)
 

examples/tensorflow/summarization/run_summarization.py

@@ -53,7 +53,7 @@ from transformers.utils.versions import require_version
 
 # region Checking dependencies
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
 

examples/tensorflow/text-classification/run_glue.py

@@ -47,7 +47,7 @@ from transformers.utils import check_min_version, send_example_telemetry
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 task_to_keys = {
     "cola": ("sentence", None),

examples/tensorflow/translation/run_translation.py

@@ -56,7 +56,7 @@ from transformers.utils.versions import require_version
 
 # region Dependencies and constants
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.45.0.dev0")
+check_min_version("4.45.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
 

setup.py

@@ -436,7 +436,7 @@ install_requires = [
 
 setup(
     name="transformers",
-    version="4.45.0.dev0",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
+    version="4.45.1",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
     author="The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)",
     author_email="transformers@huggingface.co",
     description="State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow",

src/transformers/__init__.py

@@ -18,7 +18,7 @@
 # to defer the actual importing for when the objects are requested. This way `import transformers` provides the names
 # in the namespace without actually importing anything (and especially none of the backends).
 
-__version__ = "4.45.0.dev0"
+__version__ = "4.45.1"
 
 from typing import TYPE_CHECKING
 

src/transformers/modeling_utils.py

@@ -1645,6 +1645,12 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, GenerationMixin, PushToHubMix
         # Model class overwrites `generate` (e.g. time series models) -> can generate
         if str(cls.__name__) in str(cls.generate):
             return True
+        # The class inherits from a class that can generate (recursive check) -> can generate
+        for base in cls.__bases__:
+            if not hasattr(base, "can_generate"):
+                continue
+            if "PreTrainedModel" not in str(base) and base.can_generate():
+                return True
         # BC: Detects whether `prepare_inputs_for_generation` has been overwritten in the model. Prior to v4.45, this
         # was how we detected whether a model could generate.
         if "GenerationMixin" not in str(cls.prepare_inputs_for_generation):

src/transformers/models/bert/tokenization_bert.py

@@ -88,6 +88,9 @@ class BertTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original BERT).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -105,6 +108,7 @@ class BertTokenizer(PreTrainedTokenizer):
         mask_token="[MASK]",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -136,6 +140,7 @@ class BertTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/convbert/tokenization_convbert.py

@@ -91,6 +91,9 @@ class ConvBertTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original ConvBERT).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -108,6 +111,7 @@ class ConvBertTokenizer(PreTrainedTokenizer):
         mask_token="[MASK]",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -139,6 +143,7 @@ class ConvBertTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/distilbert/tokenization_distilbert.py

@@ -90,6 +90,9 @@ class DistilBertTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original BERT).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -108,6 +111,7 @@ class DistilBertTokenizer(PreTrainedTokenizer):
         mask_token="[MASK]",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -138,6 +142,7 @@ class DistilBertTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/electra/tokenization_electra.py

@@ -90,6 +90,9 @@ class ElectraTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original Electra).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -107,6 +110,7 @@ class ElectraTokenizer(PreTrainedTokenizer):
         mask_token="[MASK]",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -138,6 +142,7 @@ class ElectraTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/funnel/tokenization_funnel.py

@@ -107,6 +107,9 @@ class FunnelTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original BERT).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -127,6 +130,7 @@ class FunnelTokenizer(PreTrainedTokenizer):
         eos_token="</s>",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -159,6 +163,7 @@ class FunnelTokenizer(PreTrainedTokenizer):
             eos_token=eos_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/layoutlm/tokenization_layoutlm.py

@@ -91,6 +91,9 @@ class LayoutLMTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original LayoutLM).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -108,6 +111,7 @@ class LayoutLMTokenizer(PreTrainedTokenizer):
         mask_token="[MASK]",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -139,6 +143,7 @@ class LayoutLMTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/lxmert/tokenization_lxmert.py

@@ -90,6 +90,9 @@ class LxmertTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original Lxmert).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -107,6 +110,7 @@ class LxmertTokenizer(PreTrainedTokenizer):
         mask_token="[MASK]",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -138,6 +142,7 @@ class LxmertTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/mllama/processing_mllama.py

@@ -12,11 +12,9 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""
-Processor class for Mllama.
-"""
 
-from statistics import mean
+"""Processor class for Mllama."""
+
 from typing import List, Optional, Union
 
 import numpy as np
@@ -296,25 +294,27 @@ class MllamaProcessor(ProcessorMixin):
             encoding = self.tokenizer(text, **text_kwargs)
             data.update(encoding)
 
+        n_images_in_images = [0]
         if images is not None:
             images = make_list_of_images(images)
             n_images_in_images = [len(sample) for sample in images]
 
-            if text is not None:
-                if (
-                    not all(batch_img_per_prompt == n_images_in_images for batch_img_per_prompt in n_images_in_text)
-                    and len(text) > 1
-                ):
+        if text is not None:
+            if any(batch_img == 0 for batch_img in n_images_in_text) and not all(
+                batch_img == 0 for batch_img in n_images_in_text
+            ):
+                raise ValueError(
+                    "If a batch of text is provided, there should be either no images or at least one image per sample"
+                )
+            if sum(n_images_in_images) != sum(n_images_in_text):
+                if images is None:
+                    raise ValueError("No image were provided, but there are image tokens in the prompt")
+                else:
                     raise ValueError(
-                        f"The number of images in each batch {n_images_in_text} should be the same  {n_images_in_images} should be the same. Yes, the model does not \
-                        support having a different number of images per batch."
-                    )
-                if int(mean(n_images_in_text)) != int(mean(n_images_in_images)):
-                    raise ValueError(
-                        f"The number of images in the text ({n_images_in_text}) should be the same as in the number of provided images ({n_images_in_images}) \
-                        should be the same."
+                        f"The number of image token ({sum(n_images_in_images)}) should be the same as in the number of provided images ({sum(n_images_in_images)})"
                     )
 
+        if images is not None:
             image_features = self.image_processor(images, **images_kwargs)
             num_tiles = image_features.pop("num_tiles")
             data.update(image_features)

src/transformers/models/mobilebert/tokenization_mobilebert.py

@@ -92,6 +92,9 @@ class MobileBertTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original MobileBERT).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -109,6 +112,7 @@ class MobileBertTokenizer(PreTrainedTokenizer):
         mask_token="[MASK]",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -140,6 +144,7 @@ class MobileBertTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/mpnet/tokenization_mpnet.py

@@ -108,6 +108,9 @@ class MPNetTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original BERT).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -128,6 +131,7 @@ class MPNetTokenizer(PreTrainedTokenizer):
         mask_token="<mask>",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         bos_token = AddedToken(bos_token, special=True) if isinstance(bos_token, str) else bos_token
@@ -170,6 +174,7 @@ class MPNetTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/plbart/tokenization_plbart.py

@@ -130,6 +130,7 @@ class PLBartTokenizer(PreTrainedTokenizer):
         tgt_lang=None,
         sp_model_kwargs: Optional[Dict[str, Any]] = None,
         additional_special_tokens=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         # Mask token behave like a normal word, i.e. include the space before it
@@ -200,6 +201,7 @@ class PLBartTokenizer(PreTrainedTokenizer):
             tgt_lang=tgt_lang,
             additional_special_tokens=_additional_special_tokens,
             sp_model_kwargs=self.sp_model_kwargs,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/prophetnet/tokenization_prophetnet.py

@@ -308,6 +308,9 @@ class ProphetNetTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original BERT).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -330,6 +333,7 @@ class ProphetNetTokenizer(PreTrainedTokenizer):
         mask_token: Optional[str] = "[MASK]",
         tokenize_chinese_chars: Optional[bool] = True,
         strip_accents: Optional[bool] = None,
+        clean_up_tokenization_spaces: bool = True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -360,6 +364,7 @@ class ProphetNetTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/squeezebert/tokenization_squeezebert.py

@@ -91,6 +91,9 @@ class SqueezeBertTokenizer(PreTrainedTokenizer):
         strip_accents (`bool`, *optional*):
             Whether or not to strip all accents. If this option is not specified, then it will be determined by the
             value for `lowercase` (as in the original SqueezeBERT).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -108,6 +111,7 @@ class SqueezeBertTokenizer(PreTrainedTokenizer):
         mask_token="[MASK]",
         tokenize_chinese_chars=True,
         strip_accents=None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not os.path.isfile(vocab_file):
@@ -139,6 +143,7 @@ class SqueezeBertTokenizer(PreTrainedTokenizer):
             mask_token=mask_token,
             tokenize_chinese_chars=tokenize_chinese_chars,
             strip_accents=strip_accents,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/models/tapas/tokenization_tapas.py

@@ -225,6 +225,9 @@ class TapasTokenizer(PreTrainedTokenizer):
             Minimum length of each question in terms of tokens (will be skipped otherwise).
         max_question_length (`int`, *optional*):
             Maximum length of each question in terms of tokens (will be skipped otherwise).
+        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):
+            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
+            extra spaces.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -252,6 +255,7 @@ class TapasTokenizer(PreTrainedTokenizer):
         max_question_length=None,
         model_max_length: int = 512,
         additional_special_tokens: Optional[List[str]] = None,
+        clean_up_tokenization_spaces=True,
         **kwargs,
     ):
         if not is_pandas_available():
@@ -322,6 +326,7 @@ class TapasTokenizer(PreTrainedTokenizer):
             max_question_length=max_question_length,
             model_max_length=model_max_length,
             additional_special_tokens=additional_special_tokens,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
             **kwargs,
         )
 

src/transformers/tokenization_utils_base.py

@@ -1622,7 +1622,7 @@ class PreTrainedTokenizerBase(SpecialTokensMixin, PushToHubMixin):
             )
 
         # By default, cleaning tokenization spaces for both fast and slow tokenizers
-        self.clean_up_tokenization_spaces = kwargs.pop("clean_up_tokenization_spaces", True)
+        self.clean_up_tokenization_spaces = kwargs.pop("clean_up_tokenization_spaces", False)
 
         # By default, do not split special tokens for both fast and slow tokenizers
         self.split_special_tokens = kwargs.pop("split_special_tokens", False)

tests/models/clvp/test_tokenization_clvp.py

@@ -79,7 +79,7 @@ class ClvpTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
     # Copied from transformers.tests.models.gpt2.test_tokenization_gpt2.GPT2TokenizationTest.get_input_output_texts
     def get_input_output_texts(self, tokenizer):
         input_text = "lower newer"
-        output_text = "lower newer"
+        output_text = "lower[SPACE]newer"
         return input_text, output_text
 
     # Copied from transformers.tests.models.layoutxlm.test_tokenization_layoutxlm.LayoutXLMTokenizationTest.test_add_special_tokens

tests/models/mllama/test_processor_mllama.py

@@ -15,6 +15,8 @@
 
 import unittest
 
+import numpy as np
+
 from transformers import MllamaProcessor
 from transformers.testing_utils import require_torch, require_vision
 from transformers.utils import is_vision_available
@@ -177,3 +179,119 @@ class MllamaProcessorTest(unittest.TestCase):
         rendered_list = self.processor.apply_chat_template(messages_list, add_generation_prompt=True, tokenize=False)
         rendered_str = self.processor.apply_chat_template(messages_str, add_generation_prompt=True, tokenize=False)
         self.assertEqual(rendered_list, rendered_str)
+
+    def test_process_interleaved_images_prompts_image_splitting(self):
+        # Test that a single image is processed correctly
+        inputs = self.processor(images=self.image2, size={"width": 224, "height": 224})
+        self.assertEqual(inputs["pixel_values"].shape, (1, 1, 4, 3, 224, 224))
+
+        # Test that text is processed correctly
+        text = "<|begin_of_text|>This is a test sentence.<|end_of_text|>"
+        inputs = self.processor(text=text)
+        expected_ids = [128000, 2028, 374, 264, 1296, 11914, 13, 128001]
+        self.assertEqual(inputs["input_ids"][0], expected_ids)
+        self.assertEqual(inputs["attention_mask"][0], [1] * len(expected_ids))
+        self.assertEqual(inputs.get("cross_attention_mask"), None)
+
+        # Test a single sample with image and text
+        image_str = "<|image|>"
+        text_str = "This is a test sentence."
+        text = image_str + text_str
+        inputs = self.processor(
+            text=text,
+            images=self.image1,
+            size={"width": 128, "height": 128},
+        )
+        expected_ids = [self.image_token_id, self.bos_token_id] + [2028, 374, 264, 1296, 11914, 13]
+
+        self.assertEqual(inputs["pixel_values"].shape, (1, 1, 4, 3, 128, 128))
+        self.assertEqual(inputs["input_ids"][0], expected_ids)
+        self.assertEqual(inputs["attention_mask"][0], [1] * len(expected_ids))
+        cross_attention_mask = inputs["cross_attention_mask"]
+        self.assertEqual(cross_attention_mask.shape, (1, 8, 1, 4))
+        self.assertTrue(
+            np.all(cross_attention_mask == 1), f"Cross attention mask is not all ones: {cross_attention_mask}"
+        )
+
+        # Test batch
+        text = [
+            "<|image|>This is a test sentence.",
+            "This is a test sentence.<|image|><|image|>This is a test sentence.",
+        ]
+        # fmt: off
+        expected_ids = [
+            [self.image_token_id, self.bos_token_id, 2028, 374, 264, 1296, 11914, 13],
+            [self.bos_token_id, 2028, 374, 264, 1296, 11914, 13, self.image_token_id, self.image_token_id, 2028, 374, 264, 1296, 11914, 13],
+        ]
+        # fmt: onn
+        images = [[self.image1], [self.image1, self.image2]]
+        inputs = self.processor(text=text, images=images, padding=True, size={"width": 256, "height": 256})
+
+        self.assertEqual(inputs["pixel_values"].shape, (2, 2, 4, 3, 256, 256))
+        for input_ids_i, attention_mask_i, expected_ids_i in zip(inputs["input_ids"], inputs["attention_mask"], expected_ids):
+            pad_ids = [id for id, m in zip(input_ids_i, attention_mask_i) if m == 0]
+            input_ids = [id for id, m in zip(input_ids_i, attention_mask_i) if m == 1]
+            self.assertEqual(input_ids, expected_ids_i)
+            self.assertEqual(pad_ids, [self.pad_token_id] * len(pad_ids))
+
+        cross_attention_mask = inputs["cross_attention_mask"]
+        self.assertEqual(cross_attention_mask.shape, (2, 15, 2, 4))
+
+        # Check that only first tile of first sample is attended to all text tokens
+        first_sample_mask = cross_attention_mask[0].copy()
+        first_image_first_tile_attention = first_sample_mask[:, :1, :1]  # text tokens, images, tiles
+        self.assertTrue(np.all(first_image_first_tile_attention == 1), f"Cross attention mask is not all ones: {first_image_first_tile_attention}")
+
+        # zero out first tile of first image
+        first_image_first_tile_attention[:, :1, :1] = 0
+        self.assertTrue(np.all(first_image_first_tile_attention == 0), f"Cross attention mask is not all zeros: {first_image_first_tile_attention}")
+
+        # second sample
+        second_sample_mask = cross_attention_mask[1].copy()
+        first_image_first_tile_attention = second_sample_mask[7:, :1, :1]  # text tokens, images, tiles
+        self.assertTrue(np.all(first_image_first_tile_attention == 1), f"Cross attention mask is not all ones: {first_image_first_tile_attention}")
+
+        second_image_two_tiles_attention = second_sample_mask[8:, 1:2, :2]  # text tokens, images, tiles
+        self.assertTrue(np.all(second_image_two_tiles_attention == 1), f"Cross attention mask is not all ones: {second_image_two_tiles_attention}")
+
+        # zero out both images masks
+        second_sample_mask[7:, :1, :1] = 0
+        second_sample_mask[8:, 1:2, :2] = 0
+        self.assertTrue(np.all(second_sample_mask == 0), f"Cross attention mask is not all zeros: {second_sample_mask}")
+
+    def test_process_interleaved_images_prompts_image_error(self):
+        text = [
+            "This is a test sentence.",
+            "In this other sentence we try some good things",
+        ]
+        inputs = self.processor(text=text, images=None, padding=True)
+        self.assertIsNotNone(inputs["input_ids"])
+
+        text = [
+            "This is a test sentence.<|image|>",
+            "In this other sentence we try some good things",
+        ]
+        with self.assertRaises(ValueError):
+            self.processor(text=text, images=None, padding=True)
+
+        images = [[self.image1], []]
+        with self.assertRaises(ValueError):
+            self.processor(text=text, images=images, padding=True)
+
+        text = [
+            "This is a test sentence.<|image|>",
+            "In this other sentence we try some good things<|image|>",
+        ]
+        with self.assertRaises(ValueError):
+            self.processor(text=text, images=None, padding=True)
+
+        text = [
+            "This is a test sentence.<|image|>",
+            "In this other sentence we try some good things<|image|>",
+        ]
+        images = [[self.image1], [self.image2]]
+        inputs = self.processor(text=text, images=images, padding=True)
+
+        images = [[self.image1, self.image2], []]
+        with self.assertRaises(ValueError):
+            self.processor(text=text, images=None, padding=True)

tests/models/wav2vec2/test_tokenization_wav2vec2.py

@@ -147,8 +147,8 @@ class Wav2Vec2TokenizerTest(unittest.TestCase):
         batch_tokens = tokenizer.batch_decode(sample_ids)
         batch_tokens_2 = tokenizer.batch_decode(sample_ids, skip_special_tokens=True)
 
-        self.assertEqual(batch_tokens, ["HELLO<unk>!?!?$$$", "BYE BYE<unk>$$$"])
-        self.assertEqual(batch_tokens_2, ["HELO!?!?", "BYE BYE"])
+        self.assertEqual(batch_tokens, ["HELLO<unk>!? !?$$$", "BYE BYE<unk>$$$"])
+        self.assertEqual(batch_tokens_2, ["HELO!? !?", "BYE BYE"])
 
     def test_call(self):
         # Tests that all call wrap to encode_plus and batch_encode_plus
@@ -467,8 +467,8 @@ class Wav2Vec2CTCTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
         batch_tokens = tokenizer.batch_decode(sample_ids)
         batch_tokens_2 = tokenizer.batch_decode(sample_ids, skip_special_tokens=True)
 
-        self.assertEqual(batch_tokens, ["HELLO<unk>!?!?<new_tokens>$$$", "BYE BYE<unk><new_tokens>$$$"])
-        self.assertEqual(batch_tokens_2, ["HELO!?!?<new_tokens>", "BYE BYE<new_tokens>"])
+        self.assertEqual(batch_tokens, ["HELLO<unk>!? !?<new_tokens>$$$", "BYE BYE<unk><new_tokens>$$$"])
+        self.assertEqual(batch_tokens_2, ["HELO!? !?<new_tokens>", "BYE BYE<new_tokens>"])
 
     def test_special_characters_in_vocab(self):
         sent = "ʈʰ æ æ̃ ˧ kʰ"

tests/models/wav2vec2_phoneme/test_tokenization_wav2vec2_phoneme.py

@@ -249,7 +249,7 @@ class Wav2Vec2PhonemeCTCTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
         # fmt: on
 
         batch_tokens = tokenizer.batch_decode(sample_ids)
-        self.assertEqual(batch_tokens, ["k s ɾ ɾ l ɭʲ!?!? $$$", "j ð s j ð s oːɹ $$$"])
+        self.assertEqual(batch_tokens, ["k s ɾ ɾ l ɭʲ ! ? ! ? $$$", "j ð s j ð s oːɹ $$$"])
 
     @staticmethod
     def get_from_offsets(offsets, key):

tests/utils/test_modeling_utils.py

@@ -1718,29 +1718,51 @@ class ModelUtilsTest(TestCasePlus):
 
     def test_can_generate(self):
         """Tests the behavior of `PreTrainedModel.can_generate` method."""
+        logger = logging.get_logger("transformers.modeling_utils")
+        logger.warning_once.cache_clear()
+
         # 1 - By default, a model CAN'T generate
-        self.assertFalse(BertModel.can_generate())
+        can_generate = BertModel.can_generate()
+        self.assertFalse(can_generate)
 
         # 2 - The most common case for a model to be able to generate is to inherit from `GenerationMixin` directly
         class DummyBertWithMixin(BertModel, GenerationMixin):
             pass
 
-        self.assertTrue(DummyBertWithMixin.can_generate())
+        with CaptureLogger(logger) as cl:
+            can_generate = DummyBertWithMixin.can_generate()
+        self.assertTrue("" == cl.out)
+        self.assertTrue(can_generate)
 
         # 3 - Alternatively, a model can implement a `generate` method
         class DummyBertWithGenerate(BertModel):
             def generate(self):
                 pass
 
-        self.assertTrue(DummyBertWithGenerate.can_generate())
+        with CaptureLogger(logger) as cl:
+            can_generate = DummyBertWithGenerate.can_generate()
+        self.assertTrue("" == cl.out)
+        self.assertTrue(can_generate)
 
-        # 4 - BC: models with a custom `prepare_inputs_for_generation` can generate (it was assumed they inherited
+        # 4 - Finally, it can inherit from a model that can generate
+        class DummyBertWithParent(DummyBertWithMixin):
+            pass
+
+        with CaptureLogger(logger) as cl:
+            can_generate = DummyBertWithParent.can_generate()
+        self.assertTrue("" == cl.out)
+        self.assertTrue(can_generate)
+
+        # 5 - BC: models with a custom `prepare_inputs_for_generation` can generate (it was assumed they inherited
         # `GenerationMixin`)
         class DummyBertWithPrepareInputs(BertModel):
             def prepare_inputs_for_generation(self):
                 pass
 
-        self.assertTrue(DummyBertWithPrepareInputs.can_generate())
+        with CaptureLogger(logger) as cl:
+            can_generate = DummyBertWithPrepareInputs.can_generate()
+        self.assertTrue("it doesn't directly inherit from `GenerationMixin`" in cl.out)
+        self.assertTrue(can_generate)
 
     def test_save_and_load_config_with_custom_generation(self):
         """