text-data-filtering / languages_id.py
HugoLaurencon's picture
7 languages supported
ea01f38
raw
history blame
5.39 kB
import pandas as pd
langs_id = [
{
"lang": "Afrikaans",
"dataset_id": "af",
"stopwords_id": "af",
"flagged_words_id": None,
"fasttext_id": "af",
"sentencepiece_id": "af",
"kenlm_id": "af",
},
{
"lang": "Arabic",
"dataset_id": "ar",
"stopwords_id": "ar",
"flagged_words_id": "ar",
"fasttext_id": "ar",
"sentencepiece_id": "ar",
"kenlm_id": "ar",
},
{
"lang": "Egyptian Arabic",
"dataset_id": "arz",
"stopwords_id": None,
"flagged_words_id": None,
"fasttext_id": "arz",
"sentencepiece_id": "arz",
"kenlm_id": "arz",
},
{
"lang": "Assamese",
"dataset_id": "as",
"stopwords_id": None,
"flagged_words_id": None,
"fasttext_id": "as",
"sentencepiece_id": "as",
"kenlm_id": "as",
},
{
"lang": "Bengali",
"dataset_id": "bn",
"stopwords_id": "bn",
"flagged_words_id": None,
"fasttext_id": "bn",
"sentencepiece_id": "bn",
"kenlm_id": "bn",
},
{
"lang": "Catalan",
"dataset_id": "ca",
"stopwords_id": "ca",
"flagged_words_id": "ca",
"fasttext_id": "ca",
"sentencepiece_id": "ca",
"kenlm_id": "ca",
},
{
"lang": "English",
"dataset_id": "en",
"stopwords_id": "en",
"flagged_words_id": "en",
"fasttext_id": "en",
"sentencepiece_id": "en",
"kenlm_id": "en",
},
{
"lang": "Spanish",
"dataset_id": "es",
"stopwords_id": "es",
"flagged_words_id": "es",
"fasttext_id": "es",
"sentencepiece_id": "es",
"kenlm_id": "es",
},
{
"lang": "Basque",
"dataset_id": "eu",
"stopwords_id": "eu",
"flagged_words_id": "eu",
"fasttext_id": "eu",
"sentencepiece_id": "eu",
"kenlm_id": "eu",
},
{
"lang": "French",
"dataset_id": "fr",
"stopwords_id": "fr",
"flagged_words_id": "fr",
"fasttext_id": "fr",
"sentencepiece_id": "fr",
"kenlm_id": "fr",
},
{
"lang": "Gujarati",
"dataset_id": "gu",
"stopwords_id": None,
"flagged_words_id": None,
"fasttext_id": "gu",
"sentencepiece_id": "gu",
"kenlm_id": "gu",
},
{
"lang": "Hindi",
"dataset_id": "hi",
"stopwords_id": "hi",
"flagged_words_id": "hi",
"fasttext_id": "hi",
"sentencepiece_id": "hi",
"kenlm_id": "hi",
},
{
"lang": "Indonesian",
"dataset_id": "id",
"stopwords_id": "id",
"flagged_words_id": "id",
"fasttext_id": "id",
"sentencepiece_id": "id",
"kenlm_id": "id",
},
{
"lang": "Kannada",
"dataset_id": "kn",
"stopwords_id": None,
"flagged_words_id": "kn",
"fasttext_id": "kn",
"sentencepiece_id": "kn",
"kenlm_id": "kn",
},
{
"lang": "Malayalam",
"dataset_id": "ml",
"stopwords_id": None,
"flagged_words_id": "ml",
"fasttext_id": "ml",
"sentencepiece_id": "ml",
"kenlm_id": "ml",
},
{
"lang": "Marathi",
"dataset_id": "mr",
"stopwords_id": "mr",
"flagged_words_id": "mr",
"fasttext_id": "mr",
"sentencepiece_id": "mr",
"kenlm_id": "mr",
},
{
"lang": "Portuguese",
"dataset_id": "pt",
"stopwords_id": "pt",
"flagged_words_id": "pt",
"fasttext_id": "pt",
"sentencepiece_id": "pt",
"kenlm_id": "pt",
},
{
"lang": "Swahili",
"dataset_id": "sw",
"stopwords_id": "sw",
"flagged_words_id": None,
"fasttext_id": "sw",
"sentencepiece_id": "sw",
"kenlm_id": "sw",
},
{
"lang": "Tamil",
"dataset_id": "ta",
"stopwords_id": None,
"flagged_words_id": "ta",
"fasttext_id": "ta",
"sentencepiece_id": "ta",
"kenlm_id": "ta",
},
{
"lang": "Telugu",
"dataset_id": "te",
"stopwords_id": None,
"flagged_words_id": "te",
"fasttext_id": "te",
"sentencepiece_id": "te",
"kenlm_id": "te",
},
{
"lang": "Urdu",
"dataset_id": "ur",
"stopwords_id": "ur",
"flagged_words_id": None,
"fasttext_id": "ur",
"sentencepiece_id": "ur",
"kenlm_id": "ur",
},
{
"lang": "Vietnamese",
"dataset_id": "vi",
"stopwords_id": "vi",
"flagged_words_id": "vi",
"fasttext_id": "vi",
"sentencepiece_id": "vi",
"kenlm_id": "vi",
},
{
"lang": "Yoruba",
"dataset_id": "yo",
"stopwords_id": "yo",
"flagged_words_id": None,
"fasttext_id": "yo",
"sentencepiece_id": "yo",
"kenlm_id": "yo",
},
{
"lang": "Chinese",
"dataset_id": "zh",
"stopwords_id": "zh",
"flagged_words_id": "zh",
"fasttext_id": "zh",
"sentencepiece_id": "zh",
"kenlm_id": "zh",
},
]
langs_id = pd.DataFrame(langs_id)