1-800-SHARED-TASKS/Wiki2018_Devanagari_Script_Language_Identification

---
dataset_info:
features:
- name: sentence
dtype: string
- name: label
dtype:
class_label:
names:
'0': cdo
'1': glk
'2': jam
'3': lug
'4': san
'5': rue
'6': wol
'7': new
'8': mwl
'9': bre
'10': ara
'11': hye
'12': xmf
'13': ext
'14': cor
'15': yor
'16': div
'17': asm
'18': lat
'19': cym
'20': hif
'21': ace
'22': kbd
'23': tgk
'24': rus
'25': nso
'26': mya
'27': msa
'28': ava
'29': cbk
'30': urd
'31': deu
'32': swa
'33': pus
'34': bxr
'35': udm
'36': csb
'37': yid
'38': vro
'39': por
'40': pdc
'41': eng
'42': tha
'43': hat
'44': lmo
'45': pag
'46': jav
'47': chv
'48': nan
'49': sco
'50': kat
'51': bho
'52': bos
'53': kok
'54': oss
'55': mri
'56': fry
'57': cat
'58': azb
'59': kin
'60': hin
'61': sna
'62': dan
'63': egl
'64': mkd
'65': ron
'66': bul
'67': hrv
'68': som
'69': pam
'70': nav
'71': ksh
'72': nci
'73': khm
'74': sgs
'75': srn
'76': bar
'77': cos
'78': ckb
'79': pfl
'80': arz
'81': roa-tara
'82': fra
'83': mai
'84': zh-yue
'85': guj
'86': fin
'87': kir
'88': vol
'89': hau
'90': afr
'91': uig
'92': lao
'93': swe
'94': slv
'95': kor
'96': szl
'97': srp
'98': dty
'99': nrm
'100': dsb
'101': ind
'102': wln
'103': pnb
'104': ukr
'105': bpy
'106': vie
'107': tur
'108': aym
'109': lit
'110': zea
'111': pol
'112': est
'113': scn
'114': vls
'115': stq
'116': gag
'117': grn
'118': kaz
'119': ben
'120': pcd
'121': bjn
'122': krc
'123': amh
'124': diq
'125': ltz
'126': ita
'127': kab
'128': bel
'129': ang
'130': mhr
'131': che
'132': koi
'133': glv
'134': ido
'135': fao
'136': bak
'137': isl
'138': bcl
'139': tet
'140': jpn
'141': kur
'142': map-bms
'143': tyv
'144': olo
'145': arg
'146': ori
'147': lim
'148': tel
'149': lin
'150': roh
'151': sqi
'152': xho
'153': mlg
'154': fas
'155': hbs
'156': tam
'157': aze
'158': lad
'159': nob
'160': sin
'161': gla
'162': nap
'163': snd
'164': ast
'165': mal
'166': mdf
'167': tsn
'168': nds
'169': tgl
'170': nno
'171': sun
'172': lzh
'173': jbo
'174': crh
'175': pap
'176': oci
'177': hak
'178': uzb
'179': zho
'180': hsb
'181': sme
'182': mlt
'183': vep
'184': lez
'185': nld
'186': nds-nl
'187': mrj
'188': spa
'189': ceb
'190': ina
'191': heb
'192': hun
'193': que
'194': kaa
'195': mar
'196': vec
'197': frp
'198': ell
'199': sah
'200': eus
'201': ces
'202': slk
'203': chr
'204': lij
'205': nep
'206': srd
'207': ilo
'208': be-tarask
'209': bod
'210': orm
'211': war
'212': glg
'213': mon
'214': gle
'215': min
'216': ibo
'217': ile
'218': epo
'219': lav
'220': lrc
'221': als
'222': mzn
'223': rup
'224': fur
'225': tat
'226': myv
'227': pan
'228': ton
'229': kom
'230': wuu
'231': tcy
'232': tuk
'233': kan
'234': ltg
splits:
- name: train
num_bytes: 1391662.829787234
num_examples: 2500
- name: test
num_bytes: 1414706.6382978724
num_examples: 2500
download_size: 2350258
dataset_size: 2806369.4680851065
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---