Update README.md
Browse files
README.md
CHANGED
|
@@ -14,3 +14,33 @@ language:
|
|
| 14 |
| `vi` | Diacritics | | [`VI_DIACRITICS.txt`](https://huggingface.co/onelevelstudio/NLPT/raw/main/VI_DIACRITICS.txt) |
|
| 15 |
| `vi` | Stopwords | [source](https://github.com/stopwords/vietnamese-stopwords) | [`VI_STOPWORDS.txt`](https://huggingface.co/onelevelstudio/NLPT/raw/main/VI_STOPWORDS.txt) |
|
| 16 |
| `en` | Stopwords | nltk | [`EN_STOPWORDS.txt`](https://huggingface.co/onelevelstudio/NLPT/raw/main/EN_STOPWORDS.txt) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
| `vi` | Diacritics | | [`VI_DIACRITICS.txt`](https://huggingface.co/onelevelstudio/NLPT/raw/main/VI_DIACRITICS.txt) |
|
| 15 |
| `vi` | Stopwords | [source](https://github.com/stopwords/vietnamese-stopwords) | [`VI_STOPWORDS.txt`](https://huggingface.co/onelevelstudio/NLPT/raw/main/VI_STOPWORDS.txt) |
|
| 16 |
| `en` | Stopwords | nltk | [`EN_STOPWORDS.txt`](https://huggingface.co/onelevelstudio/NLPT/raw/main/EN_STOPWORDS.txt) |
|
| 17 |
+
|
| 18 |
+
## Short-term Usage
|
| 19 |
+
```python
|
| 20 |
+
import requests
|
| 21 |
+
punctuation = requests.get("https://huggingface.co/onelevelstudio/NLPT/raw/main/PUNCTUATION.txt").text.splitlines()
|
| 22 |
+
```
|
| 23 |
+
|
| 24 |
+
## Long-term Usage
|
| 25 |
+
```python
|
| 26 |
+
from huggingface_hub import hf_hub_download as HF_Download
|
| 27 |
+
import json
|
| 28 |
+
|
| 29 |
+
with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="PUNCTUATION.txt"), mode="r", encoding="utf-8") as f:
|
| 30 |
+
DATASET_punctuation = set(f.read().splitlines())
|
| 31 |
+
|
| 32 |
+
with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="VI_DIACRITICS.txt"), mode="r", encoding="utf-8") as f:
|
| 33 |
+
DATASET_diacritics_vi = f.read().splitlines()
|
| 34 |
+
|
| 35 |
+
with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="VI_VOCAB.txt"), mode="r", encoding="utf-8") as f:
|
| 36 |
+
DATASET_vocab_vi = f.read().splitlines()
|
| 37 |
+
|
| 38 |
+
with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="VI_STOPWORDS.txt"), mode="r", encoding="utf-8") as f:
|
| 39 |
+
DATASET_stopwords_vi = f.read().splitlines()
|
| 40 |
+
|
| 41 |
+
with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="EN_STOPWORDS.txt"), mode="r", encoding="utf-8") as f:
|
| 42 |
+
DATASET_stopwords_en = f.read().splitlines()
|
| 43 |
+
|
| 44 |
+
with open(HF_Download(repo_id="onelevelstudio/NLPT", filename="VI_SYNONYMS.json"), mode="r", encoding="utf-8") as f:
|
| 45 |
+
DATASET_synonyms_vi = json.load(f)
|
| 46 |
+
```
|