[console_scripts]
add_id = nemo_curator.scripts.add_id:console_script
blend_datasets = nemo_curator.scripts.blend_datasets:console_script
deidentify = nemo_curator.scripts.find_pii_and_deidentify:console_script
domain_classifier_inference = nemo_curator.distributed_data_classification.domain_classifier_inference:console_script
download_and_extract = nemo_curator.scripts.download_and_extract:console_script
filter_documents = nemo_curator.scripts.filter_documents:console_script
find_matching_ngrams = nemo_curator.scripts.find_matching_ngrams:console_script
generate_statistics = nemo_curator.distributed_data_classification.generate_statistics:console_script
get_common_crawl_urls = nemo_curator.scripts.get_common_crawl_urls:console_script
get_metadata_from_corpus = nemo_curator.get_metadata_from_corpus:console_script
get_wikipedia_urls = nemo_curator.scripts.get_wikipedia_urls:console_script
gpu_compute_minhashes = nemo_curator.scripts.fuzzy_deduplication.compute_minhashes:console_script
gpu_connected_component = nemo_curator.scripts.fuzzy_deduplication.connected_components:console_script
gpu_exact_dups = nemo_curator.scripts.find_exact_duplicates:console_script
jaccard_compute = nemo_curator.scripts.fuzzy_deduplication.jaccard_compute:console_script
jaccard_map_buckets = nemo_curator.scripts.fuzzy_deduplication.map_buckets:console_script
jaccard_shuffle = nemo_curator.scripts.fuzzy_deduplication.jaccard_shuffle:console_script
make_data_shards = nemo_curator.scripts.make_data_shards:console_script
minhash_buckets = nemo_curator.scripts.fuzzy_deduplication.minhash_lsh:console_script
prepare_fasttext_training_data = nemo_curator.scripts.prepare_fasttext_training_data:console_script
prepare_task_data = nemo_curator.scripts.prepare_task_data:console_script
quality_classifier_inference = nemo_curator.distributed_data_classification.quality_classifier_inference:console_script
quality_classifier_multiple_models_inference = nemo_curator.distributed_data_classification.quality_classifier_multiple_models_inference:console_script
remove_matching_ngrams = nemo_curator.scripts.remove_matching_ngrams:console_script
separate_by_metadata = nemo_curator.scripts.separate_by_metadata:console_script
text_cleaning = nemo_curator.scripts.text_cleaning:console_script
train_fasttext = nemo_curator.scripts.train_fasttext:console_script
verify_results = nemo_curator.distributed_data_classification.verify_results:console_script
