fix some typos in docs, comments, logging/errors (#11432)

Author: LSinev

src/transformers/commands/add_new_model.py

@@ -57,14 +57,14 @@ def run(self):
         if not _has_cookiecutter:
             raise ImportError(
                 "Model creation dependencies are required to use the `add_new_model` command. Install them by running "
-                "the folowing at the root of your `transformers` clone:\n\n\t$ pip install -e .[modelcreation]\n"
+                "the following at the root of your `transformers` clone:\n\n\t$ pip install -e .[modelcreation]\n"
             )
         # Ensure that there is no other `cookiecutter-template-xxx` directory in the current working directory
         directories = [directory for directory in os.listdir() if "cookiecutter-template-" == directory[:22]]
         if len(directories) > 0:
             raise ValueError(
                 "Several directories starting with `cookiecutter-template-` in current working directory. "
-                "Please clean your directory by removing all folders startign with `cookiecutter-template-` or "
+                "Please clean your directory by removing all folders starting with `cookiecutter-template-` or "
                 "change your working directory."
             )
 

src/transformers/data/processors/squad.py

@@ -244,7 +244,7 @@ def squad_convert_example_to_features(
         cls_index = span["input_ids"].index(tokenizer.cls_token_id)
 
         # p_mask: mask with 1 for token than cannot be in the answer (0 for token which can be in an answer)
-        # Original TF implem also keep the classification token (set to 0)
+        # Original TF implementation also keep the classification token (set to 0)
         p_mask = np.ones_like(span["token_type_ids"])
         if tokenizer.padding_side == "right":
             p_mask[len(truncated_query) + sequence_added_tokens :] = 0

src/transformers/feature_extraction_sequence_utils.py

@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 """
- Sequence feature extraction class for common feature extrcactors to preprocess sequences.
+ Sequence feature extraction class for common feature extractors to preprocess sequences.
 """
 from typing import Dict, List, Optional, Union
 

src/transformers/file_utils.py

@@ -551,7 +551,7 @@ def wrapper(*args, **kwargs):
         ("sklearn", (is_sklearn_available, SKLEARN_IMPORT_ERROR)),
         ("speech", (is_speech_available, SPEECH_IMPORT_ERROR)),
         ("tf", (is_tf_available, TENSORFLOW_IMPORT_ERROR)),
-        ("tokenziers", (is_tokenizers_available, TOKENIZERS_IMPORT_ERROR)),
+        ("tokenizers", (is_tokenizers_available, TOKENIZERS_IMPORT_ERROR)),
         ("torch", (is_torch_available, PYTORCH_IMPORT_ERROR)),
         ("vision", (is_vision_available, VISION_IMPORT_ERROR)),
     ]

src/transformers/generation_logits_process.py

@@ -446,7 +446,7 @@ def _set_scores_to_inf_for_banned_tokens(self, scores: torch.Tensor, banned_toke
 
 class PrefixConstrainedLogitsProcessor(LogitsProcessor):
     r"""
-    :class:`transformers.LogitsProcessor` that enforces contrained generation and is useful for prefix-conditioned
+    :class:`transformers.LogitsProcessor` that enforces constrained generation and is useful for prefix-conditioned
     constrained generation. See `Autoregressive Entity Retrieval <https://arxiv.org/abs/2010.00904>`__ for more
     information.
 

src/transformers/generation_stopping_criteria.py

@@ -23,7 +23,7 @@
             Prediction scores of a language modeling head. These can be scores for each vocabulary token before SoftMax
             or scores for each vocabulary token after SoftMax.
         kwargs:
-            Additional stopping critera specific kwargs.
+            Additional stopping criteria specific kwargs.
 
     Return:
         :obj:`bool`. :obj:`False` indicates we should continue, :obj:`True` indicates we should stop.

src/transformers/generation_tf_utils.py

@@ -442,8 +442,8 @@ def _generate_no_beam_search(
         **kwargs
     ):
         """
-        Generate sequences for each example without beam search (num_beams == 1). All returned sequence are generated
-        independantly.
+        Generate sequences for each example without beam search (num_beams == 1). All returned sequences are generated
+        independently.
         """
 
         # length of generated sentences / unfinished sentences

src/transformers/generation_utils.py

@@ -821,7 +821,7 @@ def generate(
             ... "at least two people were killed in a suspected bomb attack on a passenger bus "
             ... "in the strife-torn southern philippines on monday , the military said."
             ... )
-            >>> # encode input contex
+            >>> # encode input context
             >>> input_ids = tokenizer(document, return_tensors="pt").input_ids
             >>> # generate 3 independent sequences using beam search decoding (5 beams)
             >>> # with T5 encoder-decoder model conditioned on short news article.

src/transformers/modeling_flax_utils.py

@@ -94,7 +94,7 @@ def __init__(
         self.key = PRNGKey(seed)
         self.dtype = dtype
 
-        # randomely initialized parameters
+        # randomly initialized parameters
         random_params = self.init_weights(self.key, input_shape)
 
         # save required_params as set

src/transformers/modeling_outputs.py

@@ -343,7 +343,7 @@ class CausalLMOutputWithPast(ModelOutput):
             Language modeling loss (for next-token prediction).
         logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`):
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
-        past_key_values (:obj:`tuple(tupel(torch.FloatTensor))`, `optional`, returned when ``use_cache=True`` is passed or when ``config.use_cache=True``):
+        past_key_values (:obj:`tuple(tuple(torch.FloatTensor))`, `optional`, returned when ``use_cache=True`` is passed or when ``config.use_cache=True``):
             Tuple of :obj:`tuple(torch.FloatTensor)` of length :obj:`config.n_layers`, with each tuple having 2 tensors
             of shape :obj:`(batch_size, num_heads, sequence_length, embed_size_per_head)`)
 
@@ -423,7 +423,7 @@ class SequenceClassifierOutputWithPast(ModelOutput):
             Classification (or regression if config.num_labels==1) loss.
         logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, config.num_labels)`):
             Classification (or regression if config.num_labels==1) scores (before SoftMax).
-        past_key_values (:obj:`tuple(tupel(torch.FloatTensor))`, `optional`, returned when ``use_cache=True`` is passed or when ``config.use_cache=True``):
+        past_key_values (:obj:`tuple(tuple(torch.FloatTensor))`, `optional`, returned when ``use_cache=True`` is passed or when ``config.use_cache=True``):
             Tuple of :obj:`tuple(torch.FloatTensor)` of length :obj:`config.n_layers`, with each tuple having 2 tensors
             of shape :obj:`(batch_size, num_heads, sequence_length, embed_size_per_head)`)