NLPT

Language	Dataset	Source	Download
all	Punctuation		PUNCTUATION.txt
vi	Synonyms	source	VI_SYNONYMS.json
vi	Vocab	source	VI_VOCAB.txt
vi	Diacritics		VI_DIACRITICS.txt
vi	Stopwords	source	VI_STOPWORDS.txt
en	Stopwords	nltk	EN_STOPWORDS.txt

Short-term Usage

import requests
punctuation = requests.get("https://huggingface.co/onelevelstudio/NLPT/raw/main/PUNCTUATION.txt").text.splitlines()

Long-term Usage

from huggingface_hub import hf_hub_download as HF_Download
import json

with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="PUNCTUATION.txt"), mode="r", encoding="utf-8") as f:
    DATASET_punctuation = set(f.read().splitlines())

with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="VI_DIACRITICS.txt"), mode="r", encoding="utf-8") as f:
    DATASET_diacritics_vi = f.read().splitlines()

with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="VI_VOCAB.txt"), mode="r", encoding="utf-8") as f:
    DATASET_vocab_vi = f.read().splitlines()

with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="VI_STOPWORDS.txt"), mode="r", encoding="utf-8") as f:
    DATASET_stopwords_vi = f.read().splitlines()

with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="EN_STOPWORDS.txt"), mode="r", encoding="utf-8") as f:
    DATASET_stopwords_en = f.read().splitlines()

with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="VI_SYNONYMS.json"), mode="r", encoding="utf-8") as f:
    DATASET_synonyms_vi = json.load(f)