.dvcignore
.gitignore
.pre-commit-config.yaml
.zenodo.json
ADD_NEW_DATASET.md
AUTHORS
CITATION.cff
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
Makefile
README.md
SECURITY.md
additional-tests-requirements.txt
dvc.yaml
pyproject.toml
setup.py
.dvc/.gitignore
.dvc/config
.dvc/plots/confusion.json
.dvc/plots/default.json
.dvc/plots/scatter.json
.dvc/plots/smooth.json
.github/ISSUE_TEMPLATE/bug-report.yml
.github/ISSUE_TEMPLATE/config.yml
.github/ISSUE_TEMPLATE/feature-request.yml
.github/conda/build.sh
.github/conda/meta.yaml
.github/workflows/benchmarks.yaml
.github/workflows/build_documentation.yml
.github/workflows/build_pr_documentation.yml
.github/workflows/ci.yml
.github/workflows/release-conda.yml
.github/workflows/self-assign.yaml
.github/workflows/trufflehog.yml
.github/workflows/upload_pr_documentation.yml
benchmarks/benchmark_array_xd.py
benchmarks/benchmark_getitem_100B.py
benchmarks/benchmark_indices_mapping.py
benchmarks/benchmark_iterating.py
benchmarks/benchmark_map_filter.py
benchmarks/format.py
benchmarks/utils.py
benchmarks/results/.gitkeep
benchmarks/results/benchmark_array_xd.json
benchmarks/results/benchmark_getitem_100B.json
benchmarks/results/benchmark_indices_mapping.json
benchmarks/results/benchmark_iterating.json
benchmarks/results/benchmark_map_filter.json
docs/README.md
docs/source/_config.py
docs/source/_redirects.yml
docs/source/_toctree.yml
docs/source/about_arrow.md
docs/source/about_cache.mdx
docs/source/about_dataset_features.mdx
docs/source/about_dataset_load.mdx
docs/source/about_map_batch.mdx
docs/source/about_mapstyle_vs_iterable.mdx
docs/source/about_metrics.mdx
docs/source/access.mdx
docs/source/audio_dataset.mdx
docs/source/audio_load.mdx
docs/source/audio_process.mdx
docs/source/beam.mdx
docs/source/cache.mdx
docs/source/cli.mdx
docs/source/create_dataset.mdx
docs/source/dataset_card.mdx
docs/source/dataset_script.mdx
docs/source/depth_estimation.mdx
docs/source/faiss_es.mdx
docs/source/filesystems.mdx
docs/source/how_to.md
docs/source/how_to_metrics.mdx
docs/source/image_classification.mdx
docs/source/image_dataset.mdx
docs/source/image_load.mdx
docs/source/image_process.mdx
docs/source/index.mdx
docs/source/installation.md
docs/source/load_hub.mdx
docs/source/loading.mdx
docs/source/metrics.mdx
docs/source/nlp_load.mdx
docs/source/nlp_process.mdx
docs/source/object_detection.mdx
docs/source/process.mdx
docs/source/quickstart.mdx
docs/source/repository_structure.mdx
docs/source/semantic_segmentation.mdx
docs/source/share.mdx
docs/source/stream.mdx
docs/source/tabular_load.mdx
docs/source/troubleshoot.mdx
docs/source/tutorial.md
docs/source/upload_dataset.mdx
docs/source/use_dataset.mdx
docs/source/use_with_jax.mdx
docs/source/use_with_pytorch.mdx
docs/source/use_with_spark.mdx
docs/source/use_with_tensorflow.mdx
docs/source/imgs/course_banner.png
docs/source/imgs/datasets_logo_name.jpg
docs/source/package_reference/builder_classes.mdx
docs/source/package_reference/loading_methods.mdx
docs/source/package_reference/main_classes.mdx
docs/source/package_reference/table_classes.mdx
docs/source/package_reference/task_templates.mdx
docs/source/package_reference/utilities.mdx
metrics/accuracy/README.md
metrics/accuracy/accuracy.py
metrics/bertscore/README.md
metrics/bertscore/bertscore.py
metrics/bleu/README.md
metrics/bleu/bleu.py
metrics/bleurt/bleurt.py
metrics/cer/README.md
metrics/cer/cer.py
metrics/cer/test_cer.py
metrics/chrf/README.md
metrics/chrf/chrf.py
metrics/code_eval/README.md
metrics/code_eval/code_eval.py
metrics/code_eval/execute.py
metrics/comet/README.md
metrics/comet/comet.py
metrics/competition_math/README.md
metrics/competition_math/competition_math.py
metrics/coval/README.md
metrics/coval/coval.py
metrics/cuad/README.md
metrics/cuad/cuad.py
metrics/cuad/evaluate.py
metrics/exact_match/README.md
metrics/exact_match/exact_match.py
metrics/f1/README.md
metrics/f1/f1.py
metrics/frugalscore/README.md
metrics/frugalscore/frugalscore.py
metrics/glue/README.md
metrics/glue/glue.py
metrics/google_bleu/README.md
metrics/google_bleu/google_bleu.py
metrics/indic_glue/README.md
metrics/indic_glue/indic_glue.py
metrics/mae/README.md
metrics/mae/mae.py
metrics/mahalanobis/README.md
metrics/mahalanobis/mahalanobis.py
metrics/matthews_correlation/README.md
metrics/matthews_correlation/matthews_correlation.py
metrics/mauve/README.md
metrics/mauve/mauve.py
metrics/mean_iou/README.md
metrics/mean_iou/mean_iou.py
metrics/meteor/README.md
metrics/meteor/meteor.py
metrics/mse/README.md
metrics/mse/mse.py
metrics/pearsonr/README.md
metrics/pearsonr/pearsonr.py
metrics/perplexity/README.md
metrics/perplexity/perplexity.py
metrics/precision/README.md
metrics/precision/precision.py
metrics/recall/README.md
metrics/recall/recall.py
metrics/roc_auc/README.md
metrics/roc_auc/roc_auc.py
metrics/rouge/README.md
metrics/rouge/rouge.py
metrics/sacrebleu/README.md
metrics/sacrebleu/sacrebleu.py
metrics/sari/README.md
metrics/sari/sari.py
metrics/seqeval/README.md
metrics/seqeval/seqeval.py
metrics/spearmanr/README.md
metrics/spearmanr/spearmanr.py
metrics/squad/README.md
metrics/squad/evaluate.py
metrics/squad/squad.py
metrics/squad_v2/README.md
metrics/squad_v2/evaluate.py
metrics/squad_v2/squad_v2.py
metrics/super_glue/README.md
metrics/super_glue/record_evaluation.py
metrics/super_glue/super_glue.py
metrics/ter/README.md
metrics/ter/ter.py
metrics/wer/README.md
metrics/wer/wer.py
metrics/wiki_split/README.md
metrics/wiki_split/wiki_split.py
metrics/xnli/README.md
metrics/xnli/xnli.py
metrics/xtreme_s/README.md
metrics/xtreme_s/xtreme_s.py
notebooks/Overview.ipynb
notebooks/README.md
src/datasets/__init__.py
src/datasets/arrow_dataset.py
src/datasets/arrow_reader.py
src/datasets/arrow_writer.py
src/datasets/builder.py
src/datasets/combine.py
src/datasets/config.py
src/datasets/data_files.py
src/datasets/dataset_dict.py
src/datasets/distributed.py
src/datasets/exceptions.py
src/datasets/fingerprint.py
src/datasets/hub.py
src/datasets/info.py
src/datasets/inspect.py
src/datasets/iterable_dataset.py
src/datasets/keyhash.py
src/datasets/load.py
src/datasets/metric.py
src/datasets/naming.py
src/datasets/search.py
src/datasets/splits.py
src/datasets/streaming.py
src/datasets/table.py
src/datasets.egg-info/PKG-INFO
src/datasets.egg-info/SOURCES.txt
src/datasets.egg-info/dependency_links.txt
src/datasets.egg-info/entry_points.txt
src/datasets.egg-info/not-zip-safe
src/datasets.egg-info/requires.txt
src/datasets.egg-info/top_level.txt
src/datasets/commands/__init__.py
src/datasets/commands/convert.py
src/datasets/commands/convert_to_parquet.py
src/datasets/commands/datasets_cli.py
src/datasets/commands/delete_from_hub.py
src/datasets/commands/dummy_data.py
src/datasets/commands/env.py
src/datasets/commands/run_beam.py
src/datasets/commands/test.py
src/datasets/download/__init__.py
src/datasets/download/download_config.py
src/datasets/download/download_manager.py
src/datasets/download/mock_download_manager.py
src/datasets/download/streaming_download_manager.py
src/datasets/features/__init__.py
src/datasets/features/audio.py
src/datasets/features/features.py
src/datasets/features/image.py
src/datasets/features/translation.py
src/datasets/filesystems/__init__.py
src/datasets/filesystems/compression.py
src/datasets/filesystems/s3filesystem.py
src/datasets/formatting/__init__.py
src/datasets/formatting/formatting.py
src/datasets/formatting/jax_formatter.py
src/datasets/formatting/np_formatter.py
src/datasets/formatting/polars_formatter.py
src/datasets/formatting/tf_formatter.py
src/datasets/formatting/torch_formatter.py
src/datasets/io/__init__.py
src/datasets/io/abc.py
src/datasets/io/csv.py
src/datasets/io/generator.py
src/datasets/io/json.py
src/datasets/io/parquet.py
src/datasets/io/spark.py
src/datasets/io/sql.py
src/datasets/io/text.py
src/datasets/packaged_modules/__init__.py
src/datasets/packaged_modules/arrow/__init__.py
src/datasets/packaged_modules/arrow/arrow.py
src/datasets/packaged_modules/audiofolder/__init__.py
src/datasets/packaged_modules/audiofolder/audiofolder.py
src/datasets/packaged_modules/cache/__init__.py
src/datasets/packaged_modules/cache/cache.py
src/datasets/packaged_modules/csv/__init__.py
src/datasets/packaged_modules/csv/csv.py
src/datasets/packaged_modules/folder_based_builder/__init__.py
src/datasets/packaged_modules/folder_based_builder/folder_based_builder.py
src/datasets/packaged_modules/generator/__init__.py
src/datasets/packaged_modules/generator/generator.py
src/datasets/packaged_modules/imagefolder/__init__.py
src/datasets/packaged_modules/imagefolder/imagefolder.py
src/datasets/packaged_modules/json/__init__.py
src/datasets/packaged_modules/json/json.py
src/datasets/packaged_modules/pandas/__init__.py
src/datasets/packaged_modules/pandas/pandas.py
src/datasets/packaged_modules/parquet/__init__.py
src/datasets/packaged_modules/parquet/parquet.py
src/datasets/packaged_modules/spark/__init__.py
src/datasets/packaged_modules/spark/spark.py
src/datasets/packaged_modules/sql/__init__.py
src/datasets/packaged_modules/sql/sql.py
src/datasets/packaged_modules/text/__init__.py
src/datasets/packaged_modules/text/text.py
src/datasets/packaged_modules/webdataset/__init__.py
src/datasets/packaged_modules/webdataset/_tenbin.py
src/datasets/packaged_modules/webdataset/webdataset.py
src/datasets/parallel/__init__.py
src/datasets/parallel/parallel.py
src/datasets/tasks/__init__.py
src/datasets/tasks/audio_classification.py
src/datasets/tasks/automatic_speech_recognition.py
src/datasets/tasks/base.py
src/datasets/tasks/image_classification.py
src/datasets/tasks/language_modeling.py
src/datasets/tasks/question_answering.py
src/datasets/tasks/summarization.py
src/datasets/tasks/text_classification.py
src/datasets/utils/__init__.py
src/datasets/utils/_dataset_viewer.py
src/datasets/utils/_dill.py
src/datasets/utils/_filelock.py
src/datasets/utils/beam_utils.py
src/datasets/utils/cache.py
src/datasets/utils/deprecation_utils.py
src/datasets/utils/doc_utils.py
src/datasets/utils/download_manager.py
src/datasets/utils/experimental.py
src/datasets/utils/extract.py
src/datasets/utils/file_utils.py
src/datasets/utils/filelock.py
src/datasets/utils/hub.py
src/datasets/utils/info_utils.py
src/datasets/utils/logging.py
src/datasets/utils/metadata.py
src/datasets/utils/patching.py
src/datasets/utils/py_utils.py
src/datasets/utils/readme.py
src/datasets/utils/sharding.py
src/datasets/utils/stratify.py
src/datasets/utils/tf_utils.py
src/datasets/utils/tqdm.py
src/datasets/utils/track.py
src/datasets/utils/typing.py
src/datasets/utils/version.py
src/datasets/utils/resources/__init__.py
src/datasets/utils/resources/creators.json
src/datasets/utils/resources/languages.json
src/datasets/utils/resources/multilingualities.json
src/datasets/utils/resources/readme_structure.yaml
src/datasets/utils/resources/size_categories.json
templates/README.md
templates/README_guide.md
templates/metric_card_template.md
templates/new_dataset_script.py
tests/README.md
tests/__init__.py
tests/_test_patching.py
tests/conftest.py
tests/test_arrow_dataset.py
tests/test_arrow_reader.py
tests/test_arrow_writer.py
tests/test_beam.py
tests/test_builder.py
tests/test_data_files.py
tests/test_dataset_dict.py
tests/test_dataset_list.py
tests/test_distributed.py
tests/test_download_manager.py
tests/test_exceptions.py
tests/test_experimental.py
tests/test_extract.py
tests/test_file_utils.py
tests/test_filelock.py
tests/test_filesystem.py
tests/test_fingerprint.py
tests/test_formatting.py
tests/test_hf_gcp.py
tests/test_hub.py
tests/test_info.py
tests/test_info_utils.py
tests/test_inspect.py
tests/test_iterable_dataset.py
tests/test_load.py
tests/test_metadata_util.py
tests/test_metric.py
tests/test_metric_common.py
tests/test_offline_util.py
tests/test_parallel.py
tests/test_patching.py
tests/test_py_utils.py
tests/test_readme_util.py
tests/test_search.py
tests/test_sharding_utils.py
tests/test_splits.py
tests/test_streaming_download_manager.py
tests/test_table.py
tests/test_tasks.py
tests/test_tqdm.py
tests/test_upstream_hub.py
tests/test_version.py
tests/test_warnings.py
tests/utils.py
tests/commands/__init__.py
tests/commands/conftest.py
tests/commands/test_test.py
tests/distributed_scripts/run_torch_distributed.py
tests/features/__init__.py
tests/features/test_array_xd.py
tests/features/test_audio.py
tests/features/test_features.py
tests/features/test_image.py
tests/features/data/test_audio_16000.mp3
tests/features/data/test_audio_16000.pcm
tests/features/data/test_audio_44100.mp3
tests/features/data/test_audio_44100.wav
tests/features/data/test_audio_48000.opus
tests/features/data/test_image_rgb.jpg
tests/features/data/test_image_rgba.png
tests/fixtures/__init__.py
tests/fixtures/files.py
tests/fixtures/fsspec.py
tests/fixtures/hub.py
tests/io/__init__.py
tests/io/test_csv.py
tests/io/test_json.py
tests/io/test_parquet.py
tests/io/test_sql.py
tests/io/test_text.py
tests/io/data/test_file.json.bz2
tests/io/data/test_file.json.gz
tests/io/data/test_file.json.xz
tests/packaged_modules/__init__.py
tests/packaged_modules/test_arrow.py
tests/packaged_modules/test_audiofolder.py
tests/packaged_modules/test_cache.py
tests/packaged_modules/test_csv.py
tests/packaged_modules/test_folder_based_builder.py
tests/packaged_modules/test_imagefolder.py
tests/packaged_modules/test_json.py
tests/packaged_modules/test_pandas.py
tests/packaged_modules/test_parquet.py
tests/packaged_modules/test_spark.py
tests/packaged_modules/test_sql.py
tests/packaged_modules/test_text.py
tests/packaged_modules/test_webdataset.py
utils/release.py