remove duplicate words in msg (#31876)

examples/flax/language-modeling/run_bart_dlm_flax.py

@@ -290,7 +290,7 @@ class FlaxDataCollatorForBartDenoisingLM:
     def __post_init__(self):
         if self.tokenizer.mask_token is None or self.tokenizer.eos_token is None:
             raise ValueError(
-                "This tokenizer does not have a mask token or eos token token which is necessary for denoising"
+                "This tokenizer does not have a mask token or eos token which is necessary for denoising"
                 " language modeling. "
             )
 

examples/research_projects/codeparrot/scripts/arguments.py

@@ -132,7 +132,7 @@ class PreprocessingArguments:
         default="transformersbook/codeparrot", metadata={"help": "Folder or name of dataset to process."}
     )
     output_dir: Optional[str] = field(
-        default="codeparrot-clean", metadata={"help": "Folder to save processed processed dataset."}
+        default="codeparrot-clean", metadata={"help": "Folder to save processed dataset."}
     )
     samples_per_file: Optional[int] = field(
         default=100_000, metadata={"help": "Number of files to save per JSON output file."}

src/transformers/models/whisper/convert_openai_to_hf.py

@@ -176,7 +176,7 @@ def _download(url: str, root: str) -> Any:
     model_bytes = open(download_target, "rb").read()
     if insecure_hashlib.sha256(model_bytes).hexdigest() != expected_sha256:
         raise RuntimeError(
-            "Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model."
+            "Model has been downloaded but the SHA256 checksum does not match. Please retry loading the model."
         )
 
     return torch.load(io.BytesIO(model_bytes))