diff --git a/poetry.lock b/poetry.lock
index 10de0a7..6341461 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -386,27 +386,26 @@ toml = ["tomli"]
 
 [[package]]
 name = "datasets"
-version = "2.20.0"
+version = "2.21.0"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.20.0-py3-none-any.whl", hash = "sha256:76ac02e3bdfff824492e20678f0b6b1b6d080515957fe834b00c2ba8d6b18e5e"},
-    {file = "datasets-2.20.0.tar.gz", hash = "sha256:3c4dbcd27e0f642b9d41d20ff2efa721a5e04b32b2ca4009e0fc9139e324553f"},
+    {file = "datasets-2.21.0-py3-none-any.whl", hash = "sha256:25e4e097110ce28824b746a107727ada94024cba11db8bc588d468414692b65a"},
+    {file = "datasets-2.21.0.tar.gz", hash = "sha256:998f85a8460f1bd982e5bd058f8a0808eef424249e3df1e8cdd594ccd0dc8ba2"},
 ]
 
 [package.dependencies]
 aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
-fsspec = {version = ">=2023.1.0,<=2024.5.0", extras = ["http"]}
+fsspec = {version = ">=2023.1.0,<=2024.6.1", extras = ["http"]}
 huggingface-hub = ">=0.21.2"
 multiprocess = "*"
 numpy = ">=1.17"
 packaging = "*"
 pandas = "*"
 pyarrow = ">=15.0.0"
-pyarrow-hotfix = "*"
 pyyaml = ">=5.1"
 requests = ">=2.32.2"
 tqdm = ">=4.66.3"
@@ -414,17 +413,18 @@ xxhash = "*"
 
 [package.extras]
 apache-beam = ["apache-beam (>=2.26.0)"]
-audio = ["librosa", "soundfile (>=0.12.1)"]
+audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=9.4.0)", "absl-py", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
 docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
-metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
+metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk (<3.8.2)", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
 tensorflow = ["tensorflow (>=2.6.0)"]
 tensorflow-gpu = ["tensorflow (>=2.6.0)"]
-tests = ["Pillow (>=9.4.0)", "absl-py", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tensorflow (>=2.16.0)", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers (>=4.42.0)", "typing-extensions (>=4.6.1)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (<8.0.0)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0)", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "typing-extensions (>=4.6.1)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=9.4.0)"]
 
@@ -1446,17 +1446,6 @@ files = [
 [package.dependencies]
 numpy = ">=1.16.6,<2"
 
-[[package]]
-name = "pyarrow-hotfix"
-version = "0.6"
-description = ""
-optional = false
-python-versions = ">=3.5"
-files = [
-    {file = "pyarrow_hotfix-0.6-py3-none-any.whl", hash = "sha256:dcc9ae2d220dff0083be6a9aa8e0cdee5182ad358d4931fce825c545e5c89178"},
-    {file = "pyarrow_hotfix-0.6.tar.gz", hash = "sha256:79d3e030f7ff890d408a100ac16d6f00b14d44a502d7897cd9fc3e3a534e9945"},
-]
-
 [[package]]
 name = "pytest"
 version = "8.3.2"
@@ -2584,4 +2573,4 @@ multidict = ">=4.0"
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<3.13"
-content-hash = "99b991ee8b49d9c79c32345b5e5f5b69e900b48cb19ecceaf505332777c0006a"
+content-hash = "7dc8ef9f4af1af6ea96f5cdf7c3b36ada04c8216b6867ce7aaad103c5e6658b0"
diff --git a/pyproject.toml b/pyproject.toml
index 0a0169f..245cf2a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -11,7 +11,7 @@ python = ">=3.9,<3.13"
 pandas = "2.2.2"
 pre-commit = "3.8.0"
 loguru = "0.7.2"
-datasets = "2.20.0"
+datasets = "2.21.0"
 transformers = "4.43.3"
 scikit-learn = "1.5.1"
 tqdm = "4.66.4"