Fix typos in strings and comments (#1770)

bindings/node/lib/bindings/encoding.test.ts

@@ -122,7 +122,7 @@ describe('Encoding', () => {
       expect(indexes).toEqual([3, 5])
     })
 
-    it('returns the corrent indexes with pair sequences', () => {
+    it('returns the correct indexes with pair sequences', () => {
       expect(encodingDual.wordToTokens(3, 0)).toEqual([3, 5])
       expect(encodingDual.wordToTokens(3, 1)).toEqual([8, 9])
     })

bindings/python/Cargo.toml

@@ -27,4 +27,4 @@ tempfile = "3.10"
 pyo3 = { version = "0.23", features = ["auto-initialize"] }
 
 [features]
-defaut = ["pyo3/extension-module"]
+default = ["pyo3/extension-module"]

bindings/python/scripts/convert.py

@@ -397,7 +397,7 @@ def main():
         "--models",
         type=lambda s: s.split(","),
         default=pretraineds,
-        help=f"The pretrained tokenizers you want to test agains, (default: {pretraineds})",
+        help=f"The pretrained tokenizers you want to test against, (default: {pretraineds})",
     )
     args = parser.parse_args()
 

bindings/python/src/decoders.rs

@@ -404,7 +404,7 @@ impl PyMetaspaceDec {
 ///
 /// Args:
 ///     suffix (:obj:`str`, `optional`, defaults to :obj:`</w>`):
-///         The suffix that was used to caracterize an end-of-word. This suffix will
+///         The suffix that was used to characterize an end-of-word. This suffix will
 ///         be replaced by whitespaces during the decoding
 #[pyclass(extends=PyDecoder, module = "tokenizers.decoders", name = "BPEDecoder")]
 pub struct PyBPEDecoder {}