Horizon-Labs's picture
v1.0: multilingual punctuation + truecasing (small)
45abde7 verified
Raw History Blame Contribute Delete
37.4 kB
{
"Horizon-Labs/multilingual-punctuation-truecase-small": {
"per_lang": {
"europarl": {
"eng_Latn": {
"punct_f1": 0.7627714581178904,
"case_acc": 0.9767967866474282,
"case_f1": 0.8985603177229853,
"n_words": 25643
},
"deu_Latn": {
"punct_f1": 0.8803182289865099,
"case_acc": 0.9883478800230384,
"case_f1": 0.9803293020544951,
"n_words": 22571
},
"fra_Latn": {
"punct_f1": 0.8065700483091788,
"case_acc": 0.9829336307863915,
"case_f1": 0.8856015779092702,
"n_words": 26895
},
"spa_Latn": {
"punct_f1": 0.8016928657799275,
"case_acc": 0.9775942953649841,
"case_f1": 0.8809103394153424,
"n_words": 26645
},
"ita_Latn": {
"punct_f1": 0.7739041794087665,
"case_acc": 0.9721529015646663,
"case_f1": 0.8283261802575107,
"n_words": 25245
},
"por_Latn": {
"punct_f1": 0.7984618073763328,
"case_acc": 0.976401408178266,
"case_f1": 0.8827067669172932,
"n_words": 25849
},
"nld_Latn": {
"punct_f1": 0.7976359338061466,
"case_acc": 0.977944786434533,
"case_f1": 0.883629191321499,
"n_words": 26479
},
"pol_Latn": {
"punct_f1": 0.8341408870667164,
"case_acc": 0.9693657484560337,
"case_f1": 0.8636657333620504,
"n_words": 20402
},
"ces_Latn": {
"punct_f1": 0.8644444444444445,
"case_acc": 0.978966843565899,
"case_f1": 0.8825079030558483,
"n_words": 20539
},
"bul_Cyrl": {
"punct_f1": 0.8420120439249026,
"case_acc": 0.9788676068196169,
"case_f1": 0.8745661874070402,
"n_words": 23755
},
"slk_Latn": {
"punct_f1": 0.875993346885973,
"case_acc": 0.9790918163672655,
"case_f1": 0.8881789137380192,
"n_words": 20040
},
"slv_Latn": {
"punct_f1": 0.875711084295811,
"case_acc": 0.9803331229058417,
"case_f1": 0.8930354796320631,
"n_words": 20593
}
},
"flores": {
"ace_Arab": {
"punct_f1": 0.22900763358778625,
"case_acc": 0.9999083703669767,
"case_f1": 0.875,
"n_words": 21827
},
"ace_Latn": {
"punct_f1": 0.32039800995024875,
"case_acc": 0.9227195945945946,
"case_f1": 0.666397903648458,
"n_words": 21312
},
"acm_Arab": {
"punct_f1": 0.6431440045897877,
"case_acc": 0.999251617041749,
"case_f1": 0.831858407079646,
"n_words": 18707
},
"acq_Arab": {
"punct_f1": 0.6556927297668038,
"case_acc": 0.9992195223476767,
"case_f1": 0.8214285714285714,
"n_words": 19219
},
"aeb_Arab": {
"punct_f1": 0.5511520737327189,
"case_acc": 0.9994148936170213,
"case_f1": 0.8571428571428571,
"n_words": 18800
},
"afr_Latn": {
"punct_f1": 0.8082191780821918,
"case_acc": 0.9777103209019948,
"case_f1": 0.9068767908309455,
"n_words": 23060
},
"ajp_Arab": {
"punct_f1": 0.5819041986989947,
"case_acc": 0.9993397524071527,
"case_f1": 0.9550173010380623,
"n_words": 18175
},
"aka_Latn": {
"punct_f1": 0.2523680649526387,
"case_acc": 0.9258470618999589,
"case_f1": 0.6349963316214233,
"n_words": 26769
},
"als_Latn": {
"punct_f1": 0.8349267049075845,
"case_acc": 0.9800723900931311,
"case_f1": 0.901775147928994,
"n_words": 24589
},
"amh_Ethi": {
"punct_f1": 0.7607021866338158,
"case_acc": 0.9987201861547411,
"case_f1": 0.8027210884353742,
"n_words": 17190
},
"apc_Arab": {
"punct_f1": 0.5976574865463754,
"case_acc": 0.9985439068100358,
"case_f1": 0.8786610878661087,
"n_words": 17856
},
"arb_Arab": {
"punct_f1": 0.7335344394167923,
"case_acc": 0.9992864060349661,
"case_f1": 0.8347826086956521,
"n_words": 19619
},
"arb_Latn": {
"punct_f1": 0.2886916248552682,
"case_acc": 0.9095831077422848,
"case_f1": 0.5073673870333988,
"n_words": 22164
},
"ars_Arab": {
"punct_f1": 0.731286475513829,
"case_acc": 0.9992869512070898,
"case_f1": 0.7764705882352941,
"n_words": 19634
},
"ary_Arab": {
"punct_f1": 0.49725776965265084,
"case_acc": 0.9989498004620878,
"case_f1": 0.8456375838926175,
"n_words": 19044
},
"arz_Arab": {
"punct_f1": 0.6502283105022831,
"case_acc": 0.9992790937178166,
"case_f1": 0.7529411764705882,
"n_words": 19420
},
"asm_Beng": {
"punct_f1": 0.6578129415089008,
"case_acc": 0.9992717057691307,
"case_f1": 0.8862275449101796,
"n_words": 19223
},
"ast_Latn": {
"punct_f1": 0.7206477732793523,
"case_acc": 0.9609040371821744,
"case_f1": 0.8197541154407169,
"n_words": 21946
},
"awa_Deva": {
"punct_f1": 0.7103631532329495,
"case_acc": 0.9994873210553299,
"case_f1": 0.7837837837837838,
"n_words": 25357
},
"ayr_Latn": {
"punct_f1": 0.23311165558277913,
"case_acc": 0.9020515386539905,
"case_f1": 0.6147058823529412,
"n_words": 15988
},
"azb_Arab": {
"punct_f1": 0.5243370258475999,
"case_acc": 0.9989197179895383,
"case_f1": 0.6666666666666666,
"n_words": 17588
},
"azj_Latn": {
"punct_f1": 0.8176071177710138,
"case_acc": 0.9754973821989529,
"case_f1": 0.9066929133858268,
"n_words": 19100
},
"bak_Cyrl": {
"punct_f1": 0.5724959140789166,
"case_acc": 0.9473152667901027,
"case_f1": 0.776608187134503,
"n_words": 17823
},
"bam_Latn": {
"punct_f1": 0.22811671087533156,
"case_acc": 0.9249600851516764,
"case_f1": 0.603641456582633,
"n_words": 22548
},
"ban_Latn": {
"punct_f1": 0.464041095890411,
"case_acc": 0.9294181299493385,
"case_f1": 0.7411385606874329,
"n_words": 20331
},
"bel_Cyrl": {
"punct_f1": 0.8768866528558745,
"case_acc": 0.9768835616438356,
"case_f1": 0.8985921240563151,
"n_words": 21024
},
"bem_Latn": {
"punct_f1": 0.34203480589022756,
"case_acc": 0.9325960571753289,
"case_f1": 0.7068181818181818,
"n_words": 22877
},
"ben_Beng": {
"punct_f1": 0.7390275952693824,
"case_acc": 0.999486573907686,
"case_f1": 0.8870967741935484,
"n_words": 19477
},
"bho_Deva": {
"punct_f1": 0.6793981481481481,
"case_acc": 0.999140154772141,
"case_f1": 0.8627450980392157,
"n_words": 25586
},
"bjn_Arab": {
"punct_f1": 0.21343283582089553,
"case_acc": 1.0,
"case_f1": 1.0,
"n_words": 19846
},
"bjn_Latn": {
"punct_f1": 0.44258872651356995,
"case_acc": 0.9296201232032855,
"case_f1": 0.7402524015822188,
"n_words": 19480
},
"bos_Latn": {
"punct_f1": 0.8608971454463072,
"case_acc": 0.9821674876847291,
"case_f1": 0.920478837109876,
"n_words": 20300
},
"bug_Latn": {
"punct_f1": 0.2597402597402597,
"case_acc": 0.8997275775356245,
"case_f1": 0.623407175063713,
"n_words": 19088
},
"bul_Cyrl": {
"punct_f1": 0.886347642505278,
"case_acc": 0.984739634690332,
"case_f1": 0.9250497457439752,
"n_words": 21297
},
"cat_Latn": {
"punct_f1": 0.8432773109243697,
"case_acc": 0.9836622717222177,
"case_f1": 0.9156429156429157,
"n_words": 24422
},
"ceb_Latn": {
"punct_f1": 0.6804651162790698,
"case_acc": 0.9667605848309473,
"case_f1": 0.8499660556687033,
"n_words": 26264
},
"ces_Latn": {
"punct_f1": 0.9157873780609198,
"case_acc": 0.9831950315745525,
"case_f1": 0.9277861608105195,
"n_words": 19161
},
"cjk_Latn": {
"punct_f1": 0.254601226993865,
"case_acc": 0.9172301465870392,
"case_f1": 0.5742474070326334,
"n_words": 20261
},
"ckb_Arab": {
"punct_f1": 0.6229885057471264,
"case_acc": 0.9994873897888046,
"case_f1": 0.8907563025210085,
"n_words": 19508
},
"crh_Latn": {
"punct_f1": 0.7039744175422568,
"case_acc": 0.9641440938285395,
"case_f1": 0.8633696563285834,
"n_words": 17905
},
"cym_Latn": {
"punct_f1": 0.749671772428884,
"case_acc": 0.967705875046578,
"case_f1": 0.8698799144596151,
"n_words": 24153
},
"dan_Latn": {
"punct_f1": 0.8881067061874769,
"case_acc": 0.9888098136529637,
"case_f1": 0.946551724137931,
"n_words": 21358
},
"deu_Latn": {
"punct_f1": 0.9235714285714286,
"case_acc": 0.9903863845446182,
"case_f1": 0.9852455703024995,
"n_words": 21740
},
"dik_Latn": {
"punct_f1": 0.2579881656804734,
"case_acc": 0.9275907788375176,
"case_f1": 0.6204118173679498,
"n_words": 23381
},
"dyu_Latn": {
"punct_f1": 0.2156648451730419,
"case_acc": 0.9200722140160841,
"case_f1": 0.5453699395067473,
"n_words": 24372
},
"dzo_Tibt": {
"punct_f1": 0.002320185614849188,
"case_acc": 1.0,
"case_f1": 1.0,
"n_words": 6817
},
"ell_Grek": {
"punct_f1": 0.8107517482517482,
"case_acc": 0.9749267475931352,
"case_f1": 0.889886833123765,
"n_words": 23890
},
"eng_Latn": {
"punct_f1": 0.826048951048951,
"case_acc": 0.9812217297939416,
"case_f1": 0.9282051282051282,
"n_words": 21887
},
"epo_Latn": {
"punct_f1": 0.8489181561618062,
"case_acc": 0.9758757116665059,
"case_f1": 0.894453642384106,
"n_words": 20726
},
"est_Latn": {
"punct_f1": 0.9053465346534654,
"case_acc": 0.9816777438476738,
"case_f1": 0.9286367795059469,
"n_words": 16701
},
"eus_Latn": {
"punct_f1": 0.7885823025689819,
"case_acc": 0.9668664480379962,
"case_f1": 0.8745791245791246,
"n_words": 17686
},
"ewe_Latn": {
"punct_f1": 0.1615700593336376,
"case_acc": 0.9340364102975379,
"case_f1": 0.6267510167193855,
"n_words": 24938
},
"fao_Latn": {
"punct_f1": 0.8261397122551569,
"case_acc": 0.984031177225417,
"case_f1": 0.9232500562682872,
"n_words": 21041
},
"fij_Latn": {
"punct_f1": 0.24746450304259635,
"case_acc": 0.9255673121714247,
"case_f1": 0.5518896220755849,
"n_words": 30054
},
"fin_Latn": {
"punct_f1": 0.8959613696224759,
"case_acc": 0.9818341267852668,
"case_f1": 0.9320119843281862,
"n_words": 15964
},
"fon_Latn": {
"punct_f1": 0.2198100407055631,
"case_acc": 0.9279903290097037,
"case_f1": 0.5506187867721647,
"n_words": 30607
},
"fra_Latn": {
"punct_f1": 0.8709805478364431,
"case_acc": 0.9880588834077206,
"case_f1": 0.9335328061551613,
"n_words": 25542
},
"fur_Latn": {
"punct_f1": 0.6355047240179016,
"case_acc": 0.9559715264961771,
"case_f1": 0.7501064282673479,
"n_words": 26551
},
"fuv_Latn": {
"punct_f1": 0.2612312811980033,
"case_acc": 0.9149211736858559,
"case_f1": 0.5573314801945796,
"n_words": 22391
},
"gaz_Latn": {
"punct_f1": 0.2356020942408377,
"case_acc": 0.8820244864504893,
"case_f1": 0.4090210148641722,
"n_words": 19521
},
"gla_Latn": {
"punct_f1": 0.6863323500491643,
"case_acc": 0.9571263467919323,
"case_f1": 0.7882783882783883,
"n_words": 26823
},
"gle_Latn": {
"punct_f1": 0.7291116974494283,
"case_acc": 0.9654824305960008,
"case_f1": 0.8439507030029508,
"n_words": 25755
},
"glg_Latn": {
"punct_f1": 0.8490995653073897,
"case_acc": 0.9822151045178692,
"case_f1": 0.9142519219396806,
"n_words": 23728
},
"grn_Latn": {
"punct_f1": 0.2672322375397667,
"case_acc": 0.900502627370345,
"case_f1": 0.6329697986577181,
"n_words": 17508
},
"guj_Gujr": {
"punct_f1": 0.75006435006435,
"case_acc": 0.9995686969856712,
"case_f1": 0.9019607843137255,
"n_words": 20867
},
"hat_Latn": {
"punct_f1": 0.5481239804241436,
"case_acc": 0.9454820579334198,
"case_f1": 0.7232181897682554,
"n_words": 23130
},
"hau_Latn": {
"punct_f1": 0.6046867040244523,
"case_acc": 0.9577862656162967,
"case_f1": 0.7917235994534453,
"n_words": 25134
},
"heb_Hebr": {
"punct_f1": 0.7890750516410374,
"case_acc": 0.9984438040345821,
"case_f1": 0.8584070796460177,
"n_words": 17350
},
"hin_Deva": {
"punct_f1": 0.792204628501827,
"case_acc": 0.9994143827594284,
"case_f1": 0.822429906542056,
"n_words": 25614
},
"hne_Deva": {
"punct_f1": 0.6288502592253736,
"case_acc": 1.0,
"case_f1": 1.0,
"n_words": 25119
},
"hrv_Latn": {
"punct_f1": 0.8534019172317044,
"case_acc": 0.9827214930270713,
"case_f1": 0.9259259259259259,
"n_words": 19504
},
"hun_Latn": {
"punct_f1": 0.8669215365010012,
"case_acc": 0.977091473532088,
"case_f1": 0.9004566210045662,
"n_words": 18683
},
"hye_Armn": {
"punct_f1": 0.5768855973494446,
"case_acc": 0.9759017412935324,
"case_f1": 0.8913043478260869,
"n_words": 19296
},
"ibo_Latn": {
"punct_f1": 0.22980251346499103,
"case_acc": 0.9089886737890593,
"case_f1": 0.5430064308681672,
"n_words": 24898
},
"ilo_Latn": {
"punct_f1": 0.44585619405140053,
"case_acc": 0.9467149907464528,
"case_f1": 0.7377760996790637,
"n_words": 25936
},
"ind_Latn": {
"punct_f1": 0.8054651919323357,
"case_acc": 0.9721324717285945,
"case_f1": 0.9070264933355274,
"n_words": 19808
},
"isl_Latn": {
"punct_f1": 0.8280911062906724,
"case_acc": 0.9840035438302899,
"case_f1": 0.9275988761616598,
"n_words": 20317
},
"ita_Latn": {
"punct_f1": 0.8352506162695152,
"case_acc": 0.9817351598173516,
"case_f1": 0.9074747474747474,
"n_words": 24309
},
"jav_Latn": {
"punct_f1": 0.6588774341351661,
"case_acc": 0.9522785253364013,
"case_f1": 0.8276599536624487,
"n_words": 19991
},
"jpn_Jpan": {
"punct_f1": 0.9050576752440106,
"case_acc": 0.9965516602087543,
"case_f1": 0.5571428571428572,
"n_words": 53939
},
"kab_Latn": {
"punct_f1": 0.2355059416636658,
"case_acc": 0.8852295409181636,
"case_f1": 0.33708453284480505,
"n_words": 22044
},
"kac_Latn": {
"punct_f1": 0.2261081740544937,
"case_acc": 0.9518155843435324,
"case_f1": 0.600870162583009,
"n_words": 36049
},
"kam_Latn": {
"punct_f1": 0.31439114391143913,
"case_acc": 0.9356346807706838,
"case_f1": 0.6785714285714286,
"n_words": 21176
},
"kan_Knda": {
"punct_f1": 0.7490965410428497,
"case_acc": 0.9988177462510112,
"case_f1": 0.8588235294117647,
"n_words": 16071
},
"kas_Arab": {
"punct_f1": 0.34299917149958575,
"case_acc": 0.9983821600349804,
"case_f1": 0.7752808988764045,
"n_words": 22870
},
"kas_Deva": {
"punct_f1": 0.24624373956594323,
"case_acc": 0.9978511839555069,
"case_f1": 0.9583892617449664,
"n_words": 23734
},
"kat_Geor": {
"punct_f1": 0.7789527985555842,
"case_acc": 0.9987182474947565,
"case_f1": 0.8755364806866953,
"n_words": 17164
},
"kaz_Cyrl": {
"punct_f1": 0.8415476738830032,
"case_acc": 0.979026651216686,
"case_f1": 0.9179964539007093,
"n_words": 17260
},
"kbp_Latn": {
"punct_f1": 0.22625400213447172,
"case_acc": 0.9141780686099544,
"case_f1": 0.5603395997574288,
"n_words": 25215
},
"kea_Latn": {
"punct_f1": 0.4854838709677419,
"case_acc": 0.9323794849218578,
"case_f1": 0.6914765906362546,
"n_words": 22715
},
"khk_Cyrl": {
"punct_f1": 0.8391451068616423,
"case_acc": 0.9712248535777948,
"case_f1": 0.8762068225702639,
"n_words": 19635
},
"kik_Latn": {
"punct_f1": 0.3012640449438202,
"case_acc": 0.9333723702371491,
"case_f1": 0.6692799669898907,
"n_words": 23909
},
"kin_Latn": {
"punct_f1": 0.5704539490947258,
"case_acc": 0.9505784959106324,
"case_f1": 0.7963227783452502,
"n_words": 20052
},
"kir_Cyrl": {
"punct_f1": 0.8548966756513926,
"case_acc": 0.9763109475620975,
"case_f1": 0.9061096136567834,
"n_words": 17392
},
"kmb_Latn": {
"punct_f1": 0.25344714379514116,
"case_acc": 0.9196475309719072,
"case_f1": 0.6254045307443366,
"n_words": 22924
},
"kmr_Latn": {
"punct_f1": 0.644758934996402,
"case_acc": 0.9552113670461566,
"case_f1": 0.802321083172147,
"n_words": 22662
},
"knc_Arab": {
"punct_f1": 0.11269430051813471,
"case_acc": 0.9964681590958487,
"case_f1": 0.8497854077253219,
"n_words": 18404
},
"knc_Latn": {
"punct_f1": 0.22722159730033745,
"case_acc": 0.9009469696969697,
"case_f1": 0.5969632904093792,
"n_words": 21120
},
"kon_Latn": {
"punct_f1": 0.2938611204293861,
"case_acc": 0.9348878134623845,
"case_f1": 0.6231516687790452,
"n_words": 27276
},
"kor_Hang": {
"punct_f1": 0.8750740082889283,
"case_acc": 0.9968881685575365,
"case_f1": 0.9070146818923328,
"n_words": 15425
},
"lij_Latn": {
"punct_f1": 0.5283505154639175,
"case_acc": 0.9528611722885515,
"case_f1": 0.7279151943462897,
"n_words": 25881
},
"lim_Latn": {
"punct_f1": 0.7142857142857143,
"case_acc": 0.9567584452675264,
"case_f1": 0.8135269392434085,
"n_words": 22409
},
"lin_Latn": {
"punct_f1": 0.2895957587806494,
"case_acc": 0.9319179169975341,
"case_f1": 0.6395425555311194,
"n_words": 23927
},
"lit_Latn": {
"punct_f1": 0.8681716353610202,
"case_acc": 0.9763279445727483,
"case_f1": 0.9105621805792163,
"n_words": 17320
},
"lmo_Latn": {
"punct_f1": 0.56,
"case_acc": 0.9529040638337354,
"case_f1": 0.7222101370458995,
"n_words": 26945
},
"ltg_Latn": {
"punct_f1": 0.7140707298720843,
"case_acc": 0.9413176996091569,
"case_f1": 0.7472110135295514,
"n_words": 17910
},
"ltz_Latn": {
"punct_f1": 0.8320364395520972,
"case_acc": 0.9864326727171698,
"case_f1": 0.9776570048309179,
"n_words": 21596
},
"lua_Latn": {
"punct_f1": 0.27956204379562044,
"case_acc": 0.9347778887489687,
"case_f1": 0.6615798922800719,
"n_words": 23029
},
"lug_Latn": {
"punct_f1": 0.3286486486486486,
"case_acc": 0.9193072118114708,
"case_f1": 0.6671322160148976,
"n_words": 17610
},
"luo_Latn": {
"punct_f1": 0.2150916784203103,
"case_acc": 0.9235671408601266,
"case_f1": 0.6066751161808196,
"n_words": 24322
},
"lus_Latn": {
"punct_f1": 0.2300343905235002,
"case_acc": 0.9468762085574658,
"case_f1": 0.6942880128720836,
"n_words": 28443
},
"lvs_Latn": {
"punct_f1": 0.907520325203252,
"case_acc": 0.9796948802866605,
"case_f1": 0.9136577708006279,
"n_words": 18419
},
"mag_Deva": {
"punct_f1": 0.6197579510273009,
"case_acc": 0.9996401583303347,
"case_f1": 0.8115942028985508,
"n_words": 25011
},
"mai_Deva": {
"punct_f1": 0.6712367894887175,
"case_acc": 0.999308774497845,
"case_f1": 0.8942307692307693,
"n_words": 24594
},
"mal_Mlym": {
"punct_f1": 0.6932655654383736,
"case_acc": 0.9995306108764166,
"case_f1": 0.8484848484848485,
"n_words": 14913
},
"mar_Deva": {
"punct_f1": 0.7519582245430809,
"case_acc": 0.9996321210847172,
"case_f1": 0.9384615384615385,
"n_words": 19028
},
"min_Arab": {
"punct_f1": 0.22451994091580502,
"case_acc": 0.9998533222510145,
"case_f1": 0.4,
"n_words": 20453
},
"min_Latn": {
"punct_f1": 0.399624765478424,
"case_acc": 0.9302609715570326,
"case_f1": 0.7200312377977353,
"n_words": 20462
},
"mkd_Cyrl": {
"punct_f1": 0.8385860306643952,
"case_acc": 0.9804871233642248,
"case_f1": 0.9080385852090033,
"n_words": 21473
},
"mlt_Latn": {
"punct_f1": 0.75482712168837,
"case_acc": 0.9763746819668726,
"case_f1": 0.8959641255605382,
"n_words": 19259
},
"mni_Beng": {
"punct_f1": 0.26044703595724006,
"case_acc": 0.9976115063087387,
"case_f1": 0.784,
"n_words": 19259
},
"mos_Latn": {
"punct_f1": 0.24321223709369025,
"case_acc": 0.927307180582994,
"case_f1": 0.5473631592101974,
"n_words": 24803
},
"mri_Latn": {
"punct_f1": 0.47287483981204614,
"case_acc": 0.952073094303526,
"case_f1": 0.7210103329506314,
"n_words": 30317
},
"nld_Latn": {
"punct_f1": 0.8998576174655909,
"case_acc": 0.987777294475859,
"case_f1": 0.9467107680999632,
"n_words": 22990
},
"nno_Latn": {
"punct_f1": 0.860405499883477,
"case_acc": 0.9883351007423118,
"case_f1": 0.9410446088321004,
"n_words": 21689
},
"nob_Latn": {
"punct_f1": 0.8451431252932895,
"case_acc": 0.9883115054217716,
"case_f1": 0.942907334211682,
"n_words": 21303
},
"npi_Deva": {
"punct_f1": 0.813198800109081,
"case_acc": 0.9991975605841759,
"case_f1": 0.9530864197530864,
"n_words": 18693
},
"nso_Latn": {
"punct_f1": 0.31687791861240827,
"case_acc": 0.9408232071363349,
"case_f1": 0.6501138009517898,
"n_words": 28474
},
"nus_Latn": {
"punct_f1": 0.24485373781148428,
"case_acc": 0.9087059321734834,
"case_f1": 0.38049713193116635,
"n_words": 28337
},
"nya_Latn": {
"punct_f1": 0.28602699744618754,
"case_acc": 0.922409392547218,
"case_f1": 0.6766885454160492,
"n_words": 19590
},
"oci_Latn": {
"punct_f1": 0.7415680142952871,
"case_acc": 0.9730994628031906,
"case_f1": 0.8575692963752666,
"n_words": 24572
},
"ory_Orya": {
"punct_f1": 0.6177494199535963,
"case_acc": 0.9983082128575823,
"case_f1": 0.8592592592592593,
"n_words": 19506
},
"pag_Latn": {
"punct_f1": 0.3028743028743029,
"case_acc": 0.9086604479378758,
"case_f1": 0.6374203224596925,
"n_words": 21119
},
"pan_Guru": {
"punct_f1": 0.7592681752527685,
"case_acc": 0.9995365542810798,
"case_f1": 0.8961038961038961,
"n_words": 25893
},
"pap_Latn": {
"punct_f1": 0.6535211267605634,
"case_acc": 0.9589575776691374,
"case_f1": 0.8022492970946579,
"n_words": 25364
},
"pbt_Arab": {
"punct_f1": 0.7275139294242504,
"case_acc": 0.9985214951853818,
"case_f1": 0.9423076923076923,
"n_words": 26378
},
"pes_Arab": {
"punct_f1": 0.8153733884699587,
"case_acc": 0.9986813560763963,
"case_f1": 0.8936170212765957,
"n_words": 23509
},
"plt_Latn": {
"punct_f1": 0.5332252836304701,
"case_acc": 0.9427739636742852,
"case_f1": 0.7424037158892974,
"n_words": 23014
},
"pol_Latn": {
"punct_f1": 0.8875917906232348,
"case_acc": 0.9797564609772389,
"case_f1": 0.9193969849246231,
"n_words": 19463
},
"por_Latn": {
"punct_f1": 0.8528963414634146,
"case_acc": 0.9811530407282363,
"case_f1": 0.9156581642152299,
"n_words": 23399
},
"prs_Arab": {
"punct_f1": 0.782521847690387,
"case_acc": 0.9990920346677672,
"case_f1": 0.8725868725868726,
"n_words": 24230
},
"quy_Latn": {
"punct_f1": 0.2234491718090289,
"case_acc": 0.9074190308812453,
"case_f1": 0.6354679802955665,
"n_words": 15932
},
"ron_Latn": {
"punct_f1": 0.8605877920120573,
"case_acc": 0.9835533251802808,
"case_f1": 0.9206978588421887,
"n_words": 23713
},
"run_Latn": {
"punct_f1": 0.4909344490934449,
"case_acc": 0.9389199623818245,
"case_f1": 0.7404931048892603,
"n_words": 20203
},
"rus_Cyrl": {
"punct_f1": 0.912621359223301,
"case_acc": 0.9833751087012124,
"case_f1": 0.928402494087293,
"n_words": 19549
},
"sag_Latn": {
"punct_f1": 0.25901875901875904,
"case_acc": 0.9382578530282295,
"case_f1": 0.5728709394205443,
"n_words": 31421
},
"san_Deva": {
"punct_f1": 0.5142667551426675,
"case_acc": 0.9987377532006972,
"case_f1": 0.9121621621621622,
"n_words": 16637
},
"sat_Olck": {
"punct_f1": 0.1539319576129392,
"case_acc": 0.9957554825017686,
"case_f1": 0.4375,
"n_words": 24031
},
"scn_Latn": {
"punct_f1": 0.5957128614157527,
"case_acc": 0.951047085500867,
"case_f1": 0.754047460634287,
"n_words": 22491
},
"shn_Mymr": {
"punct_f1": 0.24149895905621097,
"case_acc": 0.9562708776191923,
"case_f1": 0.8188082691528172,
"n_words": 9879
},
"sin_Sinh": {
"punct_f1": 0.7162817222697462,
"case_acc": 0.9991782675947409,
"case_f1": 0.8727272727272727,
"n_words": 20688
},
"slk_Latn": {
"punct_f1": 0.9129013651220919,
"case_acc": 0.9843301925440393,
"case_f1": 0.9308231173380035,
"n_words": 19528
},
"slv_Latn": {
"punct_f1": 0.9187817258883249,
"case_acc": 0.9857561169288799,
"case_f1": 0.9320036264732547,
"n_words": 20149
},
"smo_Latn": {
"punct_f1": 0.34269662921348315,
"case_acc": 0.9435902273370437,
"case_f1": 0.6245306633291614,
"n_words": 31803
},
"sna_Latn": {
"punct_f1": 0.2583868665239115,
"case_acc": 0.929164743885556,
"case_f1": 0.6213054187192119,
"n_words": 17336
},
"snd_Arab": {
"punct_f1": 0.72119140625,
"case_acc": 0.999368362875528,
"case_f1": 0.921875,
"n_words": 25331
},
"som_Latn": {
"punct_f1": 0.5961489088575096,
"case_acc": 0.9507767573598833,
"case_f1": 0.7742690058479532,
"n_words": 23302
},
"sot_Latn": {
"punct_f1": 0.29054520358868186,
"case_acc": 0.9366969928467255,
"case_f1": 0.622286541244573,
"n_words": 28798
},
"spa_Latn": {
"punct_f1": 0.8386853041178692,
"case_acc": 0.9853149802538246,
"case_f1": 0.9220498723738465,
"n_words": 26081
},
"srd_Latn": {
"punct_f1": 0.6596785464709993,
"case_acc": 0.9610825144283263,
"case_f1": 0.78380115706021,
"n_words": 25644
},
"srp_Cyrl": {
"punct_f1": 0.8513396715643907,
"case_acc": 0.9808874050418541,
"case_f1": 0.9118673647469459,
"n_words": 20667
},
"ssw_Latn": {
"punct_f1": 0.4062024931590149,
"case_acc": 0.9247796029682248,
"case_f1": 0.623179227359088,
"n_words": 15767
},
"sun_Latn": {
"punct_f1": 0.6378689704823615,
"case_acc": 0.9529453477181786,
"case_f1": 0.8305635838150289,
"n_words": 19743
},
"swe_Latn": {
"punct_f1": 0.859122401847575,
"case_acc": 0.9897283950617284,
"case_f1": 0.9511210762331839,
"n_words": 20250
},
"swh_Latn": {
"punct_f1": 0.7164390014130947,
"case_acc": 0.9600394903859715,
"case_f1": 0.8446215139442231,
"n_words": 21271
},
"szl_Latn": {
"punct_f1": 0.6391267123287672,
"case_acc": 0.9461926862855102,
"case_f1": 0.782053920559786,
"n_words": 19607
},
"tam_Taml": {
"punct_f1": 0.7108597285067874,
"case_acc": 0.9989853169392384,
"case_f1": 0.8923076923076924,
"n_words": 16754
},
"taq_Latn": {
"punct_f1": 0.27511463109629014,
"case_acc": 0.9105492752943384,
"case_f1": 0.5719392314566577,
"n_words": 21319
},
"taq_Tfng": {
"punct_f1": 0.1099815157116451,
"case_acc": 0.9926200996521576,
"case_f1": 0.5975308641975309,
"n_words": 21274
},
"tat_Cyrl": {
"punct_f1": 0.803564028180688,
"case_acc": 0.9739304812834224,
"case_f1": 0.8926428095132252,
"n_words": 17952
},
"tel_Telu": {
"punct_f1": 0.7207510832932114,
"case_acc": 0.9981670904038313,
"case_f1": 0.9316081330868762,
"n_words": 16913
},
"tgk_Cyrl": {
"punct_f1": 0.8827885136355427,
"case_acc": 0.979381443298969,
"case_f1": 0.9049167005282406,
"n_words": 22116
},
"tgl_Latn": {
"punct_f1": 0.7697516930022573,
"case_acc": 0.9736222678871661,
"case_f1": 0.8792497069167644,
"n_words": 26765
},
"tir_Ethi": {
"punct_f1": 0.5106879129420909,
"case_acc": 0.9991144910928221,
"case_f1": 0.8080808080808081,
"n_words": 19198
},
"tpi_Latn": {
"punct_f1": 0.32457406872653766,
"case_acc": 0.9389103090828645,
"case_f1": 0.6598770851624232,
"n_words": 31642
},
"tsn_Latn": {
"punct_f1": 0.26777983920841064,
"case_acc": 0.9472880805456317,
"case_f1": 0.6414430268367796,
"n_words": 30790
},
"tso_Latn": {
"punct_f1": 0.34055727554179566,
"case_acc": 0.9338873636566002,
"case_f1": 0.6481700118063755,
"n_words": 26954
},
"tuk_Latn": {
"punct_f1": 0.8023228803716609,
"case_acc": 0.9692488000892957,
"case_f1": 0.8767605633802817,
"n_words": 17918
},
"tum_Latn": {
"punct_f1": 0.3131578947368421,
"case_acc": 0.9374565954491605,
"case_f1": 0.6948580504268413,
"n_words": 24479
},
"tur_Latn": {
"punct_f1": 0.8013565891472868,
"case_acc": 0.9790932848539938,
"case_f1": 0.9323524134218554,
"n_words": 17602
},
"twi_Latn": {
"punct_f1": 0.237224916076091,
"case_acc": 0.9276058068976112,
"case_f1": 0.6306130417805544,
"n_words": 26038
},
"tzm_Tfng": {
"punct_f1": 0.18328086743616648,
"case_acc": 0.9992027284404482,
"case_f1": 0.7096774193548387,
"n_words": 22577
},
"uig_Arab": {
"punct_f1": 0.7526328106716592,
"case_acc": 0.9990390594087389,
"case_f1": 0.9023255813953488,
"n_words": 17691
},
"ukr_Cyrl": {
"punct_f1": 0.8919961427193829,
"case_acc": 0.9780738564834243,
"case_f1": 0.9081522908152291,
"n_words": 19064
},
"umb_Latn": {
"punct_f1": 0.2666187567373338,
"case_acc": 0.922731555900449,
"case_f1": 0.6231961517904864,
"n_words": 18041
},
"urd_Arab": {
"punct_f1": 0.7691472026072786,
"case_acc": 0.9997829311529973,
"case_f1": 0.9230769230769231,
"n_words": 27641
},
"uzn_Latn": {
"punct_f1": 0.8365361803084223,
"case_acc": 0.974721885670228,
"case_f1": 0.8914694059848146,
"n_words": 18158
},
"vec_Latn": {
"punct_f1": 0.6734475374732334,
"case_acc": 0.9624497655726725,
"case_f1": 0.8049881745861105,
"n_words": 23888
},
"vie_Latn": {
"punct_f1": 0.7646107646107646,
"case_acc": 0.9735222276502198,
"case_f1": 0.8664938431626701,
"n_words": 30705
},
"war_Latn": {
"punct_f1": 0.512241054613936,
"case_acc": 0.9564947399181765,
"case_f1": 0.7812557203002014,
"n_words": 27376
},
"wol_Latn": {
"punct_f1": 0.23393124065769805,
"case_acc": 0.9270475429484618,
"case_f1": 0.577490774907749,
"n_words": 25030
},
"xho_Latn": {
"punct_f1": 0.6551219512195122,
"case_acc": 0.9520826606393283,
"case_f1": 0.7944827586206896,
"n_words": 15485
},
"ydd_Hebr": {
"punct_f1": 0.5611434621492853,
"case_acc": 0.9987366036420667,
"case_f1": 0.8627450980392157,
"n_words": 22954
},
"yor_Latn": {
"punct_f1": 0.4665523156089194,
"case_acc": 0.9439434269595963,
"case_f1": 0.7166866746698679,
"n_words": 25171
},
"yue_Hant": {
"punct_f1": 0.8175210405508799,
"case_acc": 0.9936134362430699,
"case_f1": 0.37333333333333335,
"n_words": 36796
},
"zho_Hans": {
"punct_f1": 0.8294338274691909,
"case_acc": 0.9900376130934228,
"case_f1": 0.30985915492957744,
"n_words": 39348
},
"zho_Hant": {
"punct_f1": 0.7997002061083005,
"case_acc": 0.994530955331645,
"case_f1": 0.414985590778098,
"n_words": 37118
},
"zsm_Latn": {
"punct_f1": 0.7727272727272727,
"case_acc": 0.9693154216031329,
"case_f1": 0.8909806606195447,
"n_words": 20173
},
"zul_Latn": {
"punct_f1": 0.6432160804020101,
"case_acc": 0.9535163167214774,
"case_f1": 0.7629796839729119,
"n_words": 15812
}
},
"ted": {
"eng_Latn": {
"punct_f1": 0.7172566371681416,
"case_acc": 0.9692956756123287,
"case_f1": 0.870741725054361,
"n_words": 17066
},
"deu_Latn": {
"punct_f1": 0.7954161187300395,
"case_acc": 0.972284166932144,
"case_f1": 0.9504105090311987,
"n_words": 15695
},
"fra_Latn": {
"punct_f1": 0.7331118493909191,
"case_acc": 0.9732604778236355,
"case_f1": 0.8450049784268171,
"n_words": 17203
},
"spa_Latn": {
"punct_f1": 0.7008177008177008,
"case_acc": 0.9703168629355348,
"case_f1": 0.831876260928043,
"n_words": 16474
},
"ita_Latn": {
"punct_f1": 0.6787244169443122,
"case_acc": 0.9636468551644547,
"case_f1": 0.806060606060606,
"n_words": 15597
},
"por_Latn": {
"punct_f1": 0.711483359047829,
"case_acc": 0.9684739941118744,
"case_f1": 0.824083417423478,
"n_words": 16304
},
"nld_Latn": {
"punct_f1": 0.7564926716379532,
"case_acc": 0.9749809014514896,
"case_f1": 0.8754314402259178,
"n_words": 15708
},
"pol_Latn": {
"punct_f1": 0.7640971488912355,
"case_acc": 0.9559388475107801,
"case_f1": 0.8208055819854108,
"n_words": 12755
},
"rus_Cyrl": {
"punct_f1": 0.8235088333041806,
"case_acc": 0.9715913086280852,
"case_f1": 0.859498454139471,
"n_words": 14221
},
"ukr_Cyrl": {
"punct_f1": 0.7943166441136671,
"case_acc": 0.9628096223856093,
"case_f1": 0.831964624131396,
"n_words": 14009
},
"ces_Latn": {
"punct_f1": 0.7716289945440374,
"case_acc": 0.9643970705532594,
"case_f1": 0.8295841854124063,
"n_words": 13791
},
"ron_Latn": {
"punct_f1": 0.6989030669353034,
"case_acc": 0.9666909355660721,
"case_f1": 0.8207758897082398,
"n_words": 16482
},
"hun_Latn": {
"punct_f1": 0.7629457086543631,
"case_acc": 0.9550800515972381,
"case_f1": 0.7863247863247863,
"n_words": 13179
},
"ell_Grek": {
"punct_f1": 0.6559517830236062,
"case_acc": 0.9630396395299275,
"case_f1": 0.8033498759305211,
"n_words": 16423
},
"bul_Cyrl": {
"punct_f1": 0.7354838709677419,
"case_acc": 0.9637648278991379,
"case_f1": 0.8050876589893434,
"n_words": 15427
},
"tur_Latn": {
"punct_f1": 0.6478060046189377,
"case_acc": 0.9580136929802854,
"case_f1": 0.8320512820512821,
"n_words": 12123
},
"arb_Arab": {
"punct_f1": 0.5900240064017072,
"case_acc": 0.9995723754543511,
"case_f1": 0.851063829787234,
"n_words": 14031
},
"heb_Hebr": {
"punct_f1": 0.5997509339975093,
"case_acc": 0.9993061444761391,
"case_f1": 0.8,
"n_words": 12971
},
"pes_Arab": {
"punct_f1": 0.638560411311054,
"case_acc": 0.9996331429170379,
"case_f1": 0.8518518518518519,
"n_words": 19081
},
"hin_Deva": {
"punct_f1": 0.6060122372971535,
"case_acc": 0.9996701302985321,
"case_f1": 0.8301886792452831,
"n_words": 18189
},
"ind_Latn": {
"punct_f1": 0.6858677080790823,
"case_acc": 0.9645056389676884,
"case_f1": 0.8525805531793555,
"n_words": 14453
},
"vie_Latn": {
"punct_f1": 0.6199709161415414,
"case_acc": 0.9706971284088857,
"case_f1": 0.7961346633416458,
"n_words": 22148
},
"jpn_Jpan": {
"punct_f1": 0.7317880794701986,
"case_acc": 0.9974372992551083,
"case_f1": 0.5454545454545454,
"n_words": 29266
},
"kor_Hang": {
"punct_f1": 0.8237269166200336,
"case_acc": 0.9981921487603306,
"case_f1": 0.8082191780821918,
"n_words": 11616
},
"zho_Hans": {
"punct_f1": 0.6125676238035789,
"case_acc": 0.995263820025161,
"case_f1": 0.39622641509433965,
"n_words": 27026
}
}
},
"summary": {
"europarl": {
"punct_f1": 0.8261380273668834,
"case_f1": 0.8868348243994514,
"case_acc": 0.9782330689261637,
"n_langs": 12
},
"flores": {
"punct_f1": 0.5843370537610479,
"case_f1": 0.7838620298007403,
"case_acc": 0.9659089175031863,
"n_langs": 199
},
"ted": {
"punct_f1": 0.706248545676473,
"case_f1": 0.8049908396743891,
"case_acc": 0.9751145103698038,
"n_langs": 25
}
},
"seconds": 154
}
}