Fix typo (#25966)

* Update feature_extraction_clap.py

* changed all lenght to length

examples/legacy/seq2seq/seq2seq_training_args.py

@@ -31,7 +31,7 @@ class Seq2SeqTrainingArguments(TrainingArguments):
         label_smoothing (:obj:`float`, `optional`, defaults to 0):
             The label smoothing epsilon to apply (if not zero).
         sortish_sampler (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            Whether to SortishSamler or not. It sorts the inputs according to lenghts in-order to minimizing the padding size.
+            Whether to SortishSamler or not. It sorts the inputs according to lengths in-order to minimizing the padding size.
         predict_with_generate (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether to use generate to calculate generative metrics (ROUGE, BLEU).
     """

examples/pytorch/speech-recognition/run_speech_recognition_ctc.py

@@ -311,7 +311,7 @@ class DataCollatorCTCWithPadding:
     pad_to_multiple_of_labels: Optional[int] = None
 
     def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
-        # split inputs and labels since they have to be of different lenghts and need
+        # split inputs and labels since they have to be of different lengths and need
         # different padding methods
         input_features = [{"input_values": feature["input_values"]} for feature in features]
         label_features = [{"input_ids": feature["labels"]} for feature in features]

examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py

@@ -307,7 +307,7 @@ class DataCollatorCTCWithPadding:
     pad_to_multiple_of_labels: Optional[int] = None
 
     def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
-        # split inputs and labels since they have to be of different lenghts and need
+        # split inputs and labels since they have to be of different lengths and need
         # different padding methods
         input_features = [{"input_values": feature["input_values"]} for feature in features]
         label_features = [{"input_ids": feature["labels"]} for feature in features]

examples/research_projects/robust-speech-event/run_speech_recognition_ctc_bnb.py

@@ -292,7 +292,7 @@ class DataCollatorCTCWithPadding:
     pad_to_multiple_of_labels: Optional[int] = None
 
     def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
-        # split inputs and labels since they have to be of different lenghts and need
+        # split inputs and labels since they have to be of different lengths and need
         # different padding methods
         input_features = [{"input_values": feature["input_values"]} for feature in features]
         label_features = [{"input_ids": feature["labels"]} for feature in features]

examples/research_projects/robust-speech-event/run_speech_recognition_ctc_streaming.py

@@ -284,7 +284,7 @@ class DataCollatorCTCWithPadding:
     pad_to_multiple_of_labels: Optional[int] = None
 
     def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
-        # split inputs and labels since they have to be of different lenghts and need
+        # split inputs and labels since they have to be of different lengths and need
         # different padding methods
         input_features = []
         label_features = []

examples/research_projects/wav2vec2/run_asr.py

@@ -254,7 +254,7 @@ class DataCollatorCTCWithPadding:
     pad_to_multiple_of_labels: Optional[int] = None
 
     def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
-        # split inputs and labels since they have to be of different lenghts and need
+        # split inputs and labels since they have to be of different lengths and need
         # different padding methods
         input_features = [{"input_values": feature["input_values"]} for feature in features]
         label_features = [{"input_ids": feature["labels"]} for feature in features]

examples/research_projects/wav2vec2/run_common_voice.py

@@ -173,7 +173,7 @@ class DataCollatorCTCWithPadding:
     pad_to_multiple_of_labels: Optional[int] = None
 
     def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
-        # split inputs and labels since they have to be of different lenghts and need
+        # split inputs and labels since they have to be of different lengths and need
         # different padding methods
         input_features = [{"input_values": feature["input_values"]} for feature in features]
         label_features = [{"input_ids": feature["labels"]} for feature in features]

examples/research_projects/xtreme-s/run_xtreme_s.py

@@ -335,7 +335,7 @@ class SpeechDataCollatorWithPadding:
     pad_to_multiple_of_labels: Optional[int] = None
 
     def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
-        # split inputs and labels since they have to be of different lenghts and need
+        # split inputs and labels since they have to be of different lengths and need
         # different padding methods
         input_features = [{"input_values": feature["input_values"]} for feature in features]