Skip to content

Latest commit

 

History

History

eng-alv

opus-2020-07-06.zip

  • dataset: opus
  • model: transformer
  • source language(s): eng
  • target language(s): ewe fuc fuv ibo kin lin lug nya run sag sna swh toi_Latn tso umb wol xho yor zul
  • model: transformer
  • pre-processing: normalization + SentencePiece (spm32k,spm32k)
  • a sentence initial language token is required in the form of >>id<< (id = valid target language ID)
  • download: opus-2020-07-06.zip
  • test set translations: opus-2020-07-06.test.txt
  • test set scores: opus-2020-07-06.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.eng-ewe.eng.ewe 6.4 0.271
Tatoeba-test.eng-ful.eng.ful 0.5 0.080
Tatoeba-test.eng-ibo.eng.ibo 3.6 0.250
Tatoeba-test.eng-kin.eng.kin 11.5 0.518
Tatoeba-test.eng-lin.eng.lin 1.2 0.280
Tatoeba-test.eng-lug.eng.lug 42.2 0.748
Tatoeba-test.eng.multi 13.0 0.473
Tatoeba-test.eng-nya.eng.nya 18.8 0.588
Tatoeba-test.eng-run.eng.run 12.9 0.473
Tatoeba-test.eng-sag.eng.sag 4.4 0.184
Tatoeba-test.eng-sna.eng.sna 18.2 0.546
Tatoeba-test.eng-swa.eng.swa 1.1 0.143
Tatoeba-test.eng-toi.eng.toi 8.3 0.264
Tatoeba-test.eng-tso.eng.tso 10.8 0.473
Tatoeba-test.eng-umb.eng.umb 4.3 0.352
Tatoeba-test.eng-wol.eng.wol 5.2 0.220
Tatoeba-test.eng-xho.eng.xho 27.0 0.609
Tatoeba-test.eng-yor.eng.yor 15.9 0.322
Tatoeba-test.eng-zul.eng.zul 33.3 0.736

opus-2020-07-14.zip

  • dataset: opus
  • model: transformer
  • source language(s): eng
  • target language(s): ewe fuc fuv ibo kin lin lug nya run sag sna swh toi_Latn tso umb wol xho yor zul
  • model: transformer
  • pre-processing: normalization + SentencePiece (spm32k,spm32k)
  • a sentence initial language token is required in the form of >>id<< (id = valid target language ID)
  • download: opus-2020-07-14.zip
  • test set translations: opus-2020-07-14.test.txt
  • test set scores: opus-2020-07-14.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.eng-ewe.eng.ewe 6.8 0.308
Tatoeba-test.eng-ful.eng.ful 0.6 0.084
Tatoeba-test.eng-ibo.eng.ibo 3.6 0.256
Tatoeba-test.eng-kin.eng.kin 6.1 0.516
Tatoeba-test.eng-lin.eng.lin 1.3 0.284
Tatoeba-test.eng-lug.eng.lug 10.2 0.421
Tatoeba-test.eng.multi 11.4 0.430
Tatoeba-test.eng-nya.eng.nya 14.9 0.604
Tatoeba-test.eng-run.eng.run 13.9 0.484
Tatoeba-test.eng-sag.eng.sag 5.1 0.194
Tatoeba-test.eng-sna.eng.sna 24.2 0.582
Tatoeba-test.eng-toi.eng.toi 5.3 0.226
Tatoeba-test.eng-tso.eng.tso 37.8 0.720
Tatoeba-test.eng-umb.eng.umb 5.0 0.365
Tatoeba-test.eng-wol.eng.wol 4.1 0.210
Tatoeba-test.eng-xho.eng.xho 25.0 0.619
Tatoeba-test.eng-yor.eng.yor 14.3 0.344
Tatoeba-test.eng-zul.eng.zul 36.6 0.761

opus-2020-07-19.zip

  • dataset: opus
  • model: transformer
  • source language(s): eng
  • target language(s): ewe fuc fuv ibo kin lin lug nya run sag sna swh toi_Latn tso umb wol xho yor zul
  • model: transformer
  • pre-processing: normalization + SentencePiece (spm32k,spm32k)
  • a sentence initial language token is required in the form of >>id<< (id = valid target language ID)
  • download: opus-2020-07-19.zip
  • test set translations: opus-2020-07-19.test.txt
  • test set scores: opus-2020-07-19.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.eng-ewe.eng.ewe 4.9 0.238
Tatoeba-test.eng-ful.eng.ful 0.6 0.090
Tatoeba-test.eng-ibo.eng.ibo 3.4 0.263
Tatoeba-test.eng-kin.eng.kin 6.0 0.539
Tatoeba-test.eng-lin.eng.lin 1.0 0.303
Tatoeba-test.eng-lug.eng.lug 8.4 0.380
Tatoeba-test.eng.multi 11.8 0.431
Tatoeba-test.eng-nya.eng.nya 17.9 0.601
Tatoeba-test.eng-run.eng.run 14.3 0.486
Tatoeba-test.eng-sag.eng.sag 5.1 0.189
Tatoeba-test.eng-sna.eng.sna 26.2 0.615
Tatoeba-test.eng-swa.eng.swa 1.6 0.149
Tatoeba-test.eng-toi.eng.toi 7.0 0.241
Tatoeba-test.eng-tso.eng.tso 29.5 0.630
Tatoeba-test.eng-umb.eng.umb 5.6 0.358
Tatoeba-test.eng-wol.eng.wol 5.8 0.219
Tatoeba-test.eng-xho.eng.xho 26.8 0.627
Tatoeba-test.eng-yor.eng.yor 15.8 0.352
Tatoeba-test.eng-zul.eng.zul 35.3 0.759

opus-2020-07-26.zip

  • dataset: opus
  • model: transformer
  • source language(s): eng
  • target language(s): ewe fuc fuv ibo kin lin lug nya run sag sna swh toi_Latn tso umb wol xho yor zul
  • model: transformer
  • pre-processing: normalization + SentencePiece (spm32k,spm32k)
  • a sentence initial language token is required in the form of >>id<< (id = valid target language ID)
  • download: opus-2020-07-26.zip
  • test set translations: opus-2020-07-26.test.txt
  • test set scores: opus-2020-07-26.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.eng-ewe.eng.ewe 5.0 0.218
Tatoeba-test.eng-ful.eng.ful 0.6 0.076
Tatoeba-test.eng-ibo.eng.ibo 3.0 0.257
Tatoeba-test.eng-kin.eng.kin 7.3 0.531
Tatoeba-test.eng-lin.eng.lin 1.9 0.306
Tatoeba-test.eng-lug.eng.lug 8.4 0.380
Tatoeba-test.eng.multi 11.2 0.430
Tatoeba-test.eng-nya.eng.nya 19.0 0.609
Tatoeba-test.eng-run.eng.run 13.8 0.483
Tatoeba-test.eng-sag.eng.sag 5.1 0.189
Tatoeba-test.eng-sna.eng.sna 22.4 0.595
Tatoeba-test.eng-swa.eng.swa 1.4 0.158
Tatoeba-test.eng-toi.eng.toi 5.3 0.254
Tatoeba-test.eng-tso.eng.tso 37.8 0.720
Tatoeba-test.eng-umb.eng.umb 5.1 0.330
Tatoeba-test.eng-wol.eng.wol 7.8 0.243
Tatoeba-test.eng-xho.eng.xho 27.1 0.624
Tatoeba-test.eng-yor.eng.yor 15.2 0.372
Tatoeba-test.eng-zul.eng.zul 36.6 0.741

opus2m-2020-08-01.zip

  • dataset: opus2m
  • model: transformer
  • source language(s): eng
  • target language(s): ewe fuc fuv ibo kin lin lug nya run sag sna swh toi_Latn tso umb wol xho yor zul
  • model: transformer
  • pre-processing: normalization + SentencePiece (spm32k,spm32k)
  • a sentence initial language token is required in the form of >>id<< (id = valid target language ID)
  • download: opus2m-2020-08-01.zip
  • test set translations: opus2m-2020-08-01.test.txt
  • test set scores: opus2m-2020-08-01.eval.txt

Benchmarks

testset BLEU chr-F
Tatoeba-test.eng-ewe.eng.ewe 4.9 0.212
Tatoeba-test.eng-ful.eng.ful 0.6 0.079
Tatoeba-test.eng-ibo.eng.ibo 3.5 0.255
Tatoeba-test.eng-kin.eng.kin 10.5 0.510
Tatoeba-test.eng-lin.eng.lin 1.1 0.273
Tatoeba-test.eng-lug.eng.lug 5.3 0.340
Tatoeba-test.eng.multi 11.4 0.429
Tatoeba-test.eng-nya.eng.nya 18.1 0.595
Tatoeba-test.eng-run.eng.run 13.9 0.484
Tatoeba-test.eng-sag.eng.sag 5.3 0.194
Tatoeba-test.eng-sna.eng.sna 26.2 0.623
Tatoeba-test.eng-swa.eng.swa 1.0 0.141
Tatoeba-test.eng-toi.eng.toi 7.0 0.224
Tatoeba-test.eng-tso.eng.tso 46.7 0.643
Tatoeba-test.eng-umb.eng.umb 7.8 0.359
Tatoeba-test.eng-wol.eng.wol 6.8 0.191
Tatoeba-test.eng-xho.eng.xho 27.1 0.629
Tatoeba-test.eng-yor.eng.yor 17.4 0.356
Tatoeba-test.eng-zul.eng.zul 34.1 0.729

opus1m+bt-2021-04-13.zip

  • dataset: opus1m+bt
  • model: transformer-align
  • source language(s): eng
  • target language(s): ewe fuc ful fuv ibo kin lin lug nya run sag sna swa swc swh toi tso umb wol xho yor zul
  • model: transformer-align
  • pre-processing: normalization + SentencePiece (spm32k,spm32k)
  • a sentence initial language token is required in the form of >>id<< (id = valid target language ID)
  • valid language labels: >>aaa<< >>aab<< >>aba<< >>abb<< >>abi<< >>abm<< >>abn<< >>abo<< >>abr<< >>abu<< >>acd<< >>acp<< >>ada<< >>add<< >>ade<< >>adj<< >>adq<< >>ael<< >>afe<< >>afo<< >>afu<< >>agb<< >>agc<< >>agh<< >>agq<< >>ags<< >>aha<< >>ahi<< >>ahl<< >>ahm<< >>ahn<< >>ahp<< >>ahs<< >>aik<< >>aiy<< >>ajg<< >>aka<< >>akd<< >>akf<< >>akp<< >>aks<< >>aku<< >>akw<< >>ala<< >>ald<< >>alf<< >>amb<< >>amo<< >>anf<< >>ann<< >>anv<< >>anw<< >>any<< >>aqg<< >>asa<< >>asg<< >>asj<< >>ass<< >>atg<< >>ati<< >>ato<< >>aug<< >>auh<< >>aum<< >>avi<< >>avn<< >>awc<< >>awo<< >>axk<< >>ayb<< >>aye<< >>ayg<< >>ayi<< >>ayk<< >>ayu<< >>azo<< >>bab<< >>baf<< >>bag<< >>bas<< >>bau<< >>bav<< >>baw<< >>bax<< >>bba<< >>bbe<< >>bbg<< >>bbi<< >>bbj<< >>bbk<< >>bbm<< >>bbp<< >>bbq<< >>bbs<< >>bbu<< >>bbw<< >>bby<< >>bce<< >>bcg<< >>bci<< >>bcn<< >>bcp<< >>bcs<< >>bcv<< >>bcz<< >>bda<< >>bdj<< >>bdp<< >>bdt<< >>bdu<< >>beb<< >>bec<< >>beh<< >>bem<< >>beq<< >>bes<< >>bet<< >>bev<< >>bez<< >>bfd<< >>bff<< >>bfj<< >>bfl<< >>bfm<< >>bfo<< >>bfp<< >>bga<< >>bgf<< >>bgj<< >>bgo<< >>bgu<< >>bhy<< >>bif<< >>bij<< >>bil<< >>bim<< >>bin<< >>bip<< >>biv<< >>biw<< >>biz<< >>bja<< >>bjg<< >>bjo<< >>bjt<< >>bju<< >>bjw<< >>bka<< >>bkc<< >>bkf<< >>bkh<< >>bkj<< >>bkm<< >>bko<< >>bkp<< >>bkt<< >>bkv<< >>bkw<< >>bky<< >>ble<< >>blh<< >>bli<< >>blo<< >>blv<< >>bly<< >>bma<< >>bmb<< >>bmd<< >>bme<< >>bmf<< >>bmg<< >>bml<< >>bmo<< >>bmq<< >>bmv<< >>bmw<< >>bng<< >>bni<< >>bnm<< >>bnx<< >>bnz<< >>boe<< >>boh<< >>bok<< >>bom<< >>bou<< >>bov<< >>box<< >>boy<< >>bpd<< >>bpj<< >>bqa<< >>bqd<< >>bqg<< >>bqj<< >>bqk<< >>bqm<< >>bqo<< >>bqt<< >>bqu<< >>bqv<< >>bqw<< >>bqx<< >>bqz<< >>brf<< >>bri<< >>brl<< >>brm<< >>brt<< >>bsc<< >>bse<< >>bsf<< >>bsi<< >>bsj<< >>bsl<< >>bsp<< >>bsq<< >>bsr<< >>bss<< >>bsx<< >>btb<< >>btc<< >>bte<< >>btg<< >>btt<< >>btu<< >>bub<< >>bud<< >>buf<< >>bui<< >>buj<< >>bum<< >>bun<< >>buu<< >>buw<< >>buy<< >>buz<< >>bvb<< >>bvg<< >>bvi<< >>bvj<< >>bvm<< >>bvo<< >>bvx<< >>bwc<< >>bwg<< >>bwh<< >>bwj<< >>bwl<< >>bws<< >>bwt<< >>bwu<< >>bww<< >>bwy<< >>bwz<< >>bxc<< >>bxg<< >>bxk<< >>bxp<< >>bxs<< >>byb<< >>byc<< >>byf<< >>byi<< >>byj<< >>byp<< >>bys<< >>byv<< >>bzm<< >>bzo<< >>bzv<< >>bzw<< >>bzy<< >>bzz<< >>cae<< >>cbj<< >>cbo<< >>cbq<< >>cce<< >>ccg<< >>cch<< >>ccj<< >>ccl<< >>cdr<< >>cen<< >>cfa<< >>cfd<< >>cfg<< >>cgg<< >>chw<< >>cib<< >>cjk<< >>cko<< >>ckx<< >>cli<< >>cll<< >>cme<< >>coh<< >>cou<< >>cpn<< >>cry<< >>csk<< >>cug<< >>cuh<< >>cwa<< >>cwb<< >>cwe<< >>cwt<< >>dae<< >>dag<< >>dai<< >>dam<< >>das<< >>dav<< >>dbd<< >>dbi<< >>dbm<< >>dbo<< >>dde<< >>dee<< >>deg<< >>deq<< >>dez<< >>dga<< >>dgd<< >>dgi<< >>dgs<< >>dhm<< >>dhs<< >>dic<< >>dig<< >>dii<< >>dio<< >>dir<< >>diu<< >>diz<< >>dma<< >>dmm<< >>dmo<< >>dmx<< >>dne<< >>doe<< >>doh<< >>doo<< >>dop<< >>dos<< >>dov<< >>dow<< >>doy<< >>dri<< >>dua<< >>dud<< >>dug<< >>dur<< >>duz<< >>dya<< >>dyi<< >>dyo<< >>dza<< >>dzn<< >>ebg<< >>ebo<< >>ebr<< >>ebu<< >>efa<< >>efi<< >>ega<< >>ego<< >>ehu<< >>eja<< >>eka<< >>eke<< >>eki<< >>ekm<< >>eko<< >>ekp<< >>ekr<< >>elm<< >>ema<< >>emn<< >>enn<< >>env<< >>enw<< >>eot<< >>epi<< >>erh<< >>etb<< >>eto<< >>ets<< >>etu<< >>etx<< >>evh<< >>ewe<< >>ewo<< >>eze<< >>fah<< >>fak<< >>fal<< >>fam<< >>fan<< >>fap<< >>fer<< >>ffm<< >>fip<< >>fir<< >>fll<< >>flr<< >>fmp<< >>fni<< >>fod<< >>fon<< >>fub<< >>fuc<< >>fue<< >>fuf<< >>fuh<< >>fui<< >>ful<< >>fum<< >>fuq<< >>fuv<< >>fwe<< >>gaa<< >>gba<< >>gbg<< >>gbh<< >>gbo<< >>gbp<< >>gbq<< >>gbr<< >>gbs<< >>gbv<< >>gbx<< >>gby<< >>gdi<< >>gec<< >>ged<< >>gej<< >>gel<< >>geq<< >>gev<< >>gey<< >>ggb<< >>gie<< >>gix<< >>gjn<< >>gke<< >>gkn<< >>glc<< >>glj<< >>glr<< >>gmd<< >>gmm<< >>gmn<< >>gmx<< >>gna<< >>gne<< >>gng<< >>gnh<< >>gnz<< >>god<< >>gog<< >>gol<< >>gox<< >>goy<< >>gpa<< >>grb<< >>grh<< >>grj<< >>grv<< >>gry<< >>gsl<< >>gso<< >>gua<< >>gud<< >>gur<< >>guw<< >>gux<< >>guz<< >>gvm<< >>gwa<< >>gwb<< >>gwe<< >>gwg<< >>gwr<< >>gwx<< >>gxx<< >>gya<< >>gye<< >>gyg<< >>gyi<< >>hag<< >>han<< >>haq<< >>hav<< >>hay<< >>hba<< >>heh<< >>hem<< >>her<< >>hhr<< >>hij<< >>hka<< >>hke<< >>hoe<< >>hol<< >>hom<< >>hoo<< >>hum<< >>hwa<< >>ibb<< >>ibe<< >>ibm<< >>ibn<< >>ibo<< >>ibr<< >>iby<< >>ica<< >>ich<< >>ida<< >>idc<< >>idd<< >>ide<< >>idr<< >>idu<< >>ife<< >>ifm<< >>igb<< >>ige<< >>igl<< >>igw<< >>ijc<< >>ije<< >>ijj<< >>ijn<< >>ijs<< >>iki<< >>ikk<< >>ikl<< >>iko<< >>ikp<< >>ikv<< >>ikw<< >>ikz<< >>ilb<< >>ilv<< >>iri<< >>ish<< >>isi<< >>isn<< >>iso<< >>isu<< >>itm<< >>its<< >>itw<< >>iya<< >>iyo<< >>iyx<< >>izi<< >>izr<< >>jab<< >>jar<< >>jbu<< >>jen<< >>jer<< >>jgb<< >>jgo<< >>jib<< >>jid<< >>jit<< >>jku<< >>jmc<< >>jmr<< >>jms<< >>jni<< >>job<< >>jrr<< >>jub<< >>juh<< >>juk<< >>juo<< >>juw<< >>jwi<< >>kad<< >>kaj<< >>kam<< >>kbj<< >>kbn<< >>kbp<< >>kbs<< >>kcc<< >>kcf<< >>kcg<< >>kci<< >>kcj<< >>kck<< >>kcq<< >>kcu<< >>kcv<< >>kcw<< >>kcz<< >>kdc<< >>kde<< >>kdg<< >>kdh<< >>kdl<< >>kdm<< >>kdn<< >>kdp<< >>kdx<< >>kdz<< >>keb<< >>ked<< >>kef<< >>ken<< >>kes<< >>keu<< >>kez<< >>kfl<< >>kfn<< >>kfz<< >>kgt<< >>khj<< >>khu<< >>khx<< >>khy<< >>kia<< >>kid<< >>kik<< >>kin<< >>kiv<< >>kiz<< >>kka<< >>kkd<< >>kki<< >>kkj<< >>kkm<< >>kkq<< >>kkw<< >>klc<< >>klk<< >>klo<< >>klu<< >>kma<< >>kmb<< >>kme<< >>kmi<< >>kmp<< >>kmw<< >>kmy<< >>knf<< >>kng<< >>kni<< >>knp<< >>kny<< >>knz<< >>koc<< >>koh<< >>kon<< >>koo<< >>koq<< >>kou<< >>kov<< >>kow<< >>kph<< >>kpk<< >>kpl<< >>kpo<< >>kqg<< >>kqk<< >>kqm<< >>kqn<< >>kqo<< >>kqs<< >>krh<< >>krn<< >>krp<< >>krw<< >>krx<< >>ksb<< >>ksf<< >>ksm<< >>kss<< >>kst<< >>ksv<< >>ktf<< >>ktj<< >>ktu<< >>kty<< >>kua<< >>kub<< >>kug<< >>kuj<< >>kus<< >>kuw<< >>kvm<< >>kwb<< >>kwc<< >>kwm<< >>kwn<< >>kwp<< >>kws<< >>kwu<< >>kwy<< >>kxb<< >>kxx<< >>kya<< >>kye<< >>kyf<< >>kza<< >>kzc<< >>kzn<< >>kzo<< >>kzr<< >>kzy<< >>lag<< >>lai<< >>lak<< >>lam<< >>lan<< >>lar<< >>las<< >>lch<< >>ldb<< >>ldg<< >>ldh<< >>ldi<< >>ldj<< >>ldk<< >>ldl<< >>ldm<< >>ldo<< >>ldp<< >>ldq<< >>lea<< >>leb<< >>lee<< >>lef<< >>leh<< >>lej<< >>lel<< >>lem<< >>leo<< >>lfa<< >>lgm<< >>lgq<< >>lgz<< >>lia<< >>lie<< >>lik<< >>lin<< >>lip<< >>liy<< >>liz<< >>lkb<< >>lke<< >>lko<< >>lks<< >>lla<< >>llb<< >>lli<< >>lma<< >>lmp<< >>lmx<< >>lna<< >>lnb<< >>lnl<< >>lns<< >>lnu<< >>lob<< >>loi<< >>lol<< >>lon<< >>loo<< >>lop<< >>loq<< >>lor<< >>loz<< >>lri<< >>lrm<< >>lse<< >>lsm<< >>lto<< >>lts<< >>lua<< >>lub<< >>lue<< >>lug<< >>luj<< >>lum<< >>lun<< >>lup<< >>luq<< >>luw<< >>luy<< >>lwa<< >>lwg<< >>lyn<< >>mae<< >>maw<< >>mbm<< >>mbo<< >>mbu<< >>mbv<< >>mcj<< >>mck<< >>mcp<< >>mcs<< >>mcu<< >>mcx<< >>mda<< >>mdd<< >>mdm<< >>mdn<< >>mdp<< >>mdq<< >>mdt<< >>mdu<< >>mdw<< >>mea<< >>mer<< >>mfc<< >>mfd<< >>mff<< >>mfn<< >>mfo<< >>mfq<< >>mfu<< >>mfv<< >>mgg<< >>mgh<< >>mgi<< >>mgj<< >>mgn<< >>mgo<< >>mgq<< >>mgr<< >>mgs<< >>mgv<< >>mgw<< >>mgy<< >>mgz<< >>mhb<< >>mhk<< >>mhm<< >>mho<< >>mhw<< >>mij<< >>mjh<< >>mka<< >>mkk<< >>mkl<< >>mko<< >>mkw<< >>mlb<< >>mlk<< >>mlo<< >>mma<< >>mmu<< >>mmz<< >>mnf<< >>mnh<< >>mny<< >>moi<< >>moj<< >>mor<< >>mos<< >>mow<< >>mpa<< >>mql<< >>mru<< >>msj<< >>msw<< >>mtb<< >>mtk<< >>mua<< >>muc<< >>muh<< >>muo<< >>mvw<< >>mwe<< >>mwn<< >>mws<< >>mwz<< >>mxc<< >>mxg<< >>mxl<< >>mxo<< >>myc<< >>mye<< >>myg<< >>myj<< >>myk<< >>myx<< >>mzd<< >>mzk<< >>mzm<< >>mzv<< >>mzw<< >>naj<< >>nar<< >>nat<< >>naw<< >>nba<< >>nbb<< >>nbd<< >>nbl<< >>nbm<< >>nbo<< >>nbp<< >>nbr<< >>nbv<< >>nbw<< >>ncr<< >>ncu<< >>nda<< >>ndb<< >>ndc<< >>ndd<< >>nde<< >>ndg<< >>ndh<< >>ndi<< >>ndj<< >>ndk<< >>ndl<< >>ndn<< >>ndo<< >>ndq<< >>ndr<< >>ndt<< >>ndu<< >>ndv<< >>ndw<< >>ndz<< >>ned<< >>ney<< >>nfd<< >>nfr<< >>nfu<< >>nga<< >>ngc<< >>ngd<< >>nge<< >>ngg<< >>ngj<< >>ngl<< >>ngn<< >>ngo<< >>ngp<< >>ngq<< >>ngv<< >>ngy<< >>ngz<< >>nhu<< >>nie<< >>nih<< >>nim<< >>nin<< >>nix<< >>njj<< >>njr<< >>njx<< >>njy<< >>nka<< >>nkc<< >>nkn<< >>nkt<< >>nku<< >>nkv<< >>nkw<< >>nkx<< >>nkz<< >>nla<< >>nle<< >>nlj<< >>nlo<< >>nlu<< >>nmd<< >>nmg<< >>nml<< >>nmq<< >>nmr<< >>nmz<< >>nnb<< >>nne<< >>nnh<< >>nnq<< >>nns<< >>nnu<< >>nnw<< >>nnz<< >>noq<< >>now<< >>noy<< >>nqg<< >>nqk<< >>nql<< >>nra<< >>nse<< >>nsh<< >>nso<< >>nsx<< >>nte<< >>nti<< >>ntk<< >>ntm<< >>nto<< >>ntr<< >>nue<< >>nuh<< >>nui<< >>nuj<< >>nup<< >>nuu<< >>nuv<< >>nvo<< >>nwb<< >>nwe<< >>nxd<< >>nxi<< >>nxo<< >>nya<< >>nyb<< >>nyc<< >>nyd<< >>nye<< >>nyf<< >>nyg<< >>nyj<< >>nyk<< >>nym<< >>nyn<< >>nyo<< >>nyr<< >>nyu<< >>nyy<< >>nza<< >>nzb<< >>nzd<< >>nzi<< >>nzk<< >>nzy<< >>obl<< >>obu<< >>odu<< >>ofu<< >>ogb<< >>ogc<< >>ogg<< >>ogo<< >>ogu<< >>okb<< >>okd<< >>oke<< >>okr<< >>oks<< >>oku<< >>okx<< >>old<< >>olm<< >>olu<< >>oml<< >>opa<< >>org<< >>orr<< >>orx<< >>oso<< >>ost<< >>otr<< >>oub<< >>ozm<< >>pae<< >>pai<< >>pbl<< >>pbn<< >>pbo<< >>pbp<< >>pbr<< >>pcn<< >>pem<< >>pfe<< >>pgs<< >>phm<< >>pic<< >>pil<< >>piw<< >>pkb<< >>plr<< >>pmb<< >>pmm<< >>pmn<< >>png<< >>pnl<< >>pnq<< >>pny<< >>pnz<< >>pof<< >>poy<< >>pug<< >>puu<< >>pwb<< >>pye<< >>pym<< >>rag<< >>rax<< >>reg<< >>res<< >>rim<< >>rin<< >>rnd<< >>rng<< >>rnw<< >>rod<< >>rof<< >>rub<< >>ruc<< >>ruf<< >>ruk<< >>run<< >>rwk<< >>rwm<< >>saf<< >>sag<< >>sak<< >>sav<< >>sbk<< >>sbm<< >>sbp<< >>sbs<< >>sbw<< >>sby<< >>scv<< >>sde<< >>sdj<< >>sef<< >>seg<< >>seh<< >>sen<< >>sep<< >>seq<< >>sev<< >>sfw<< >>sgi<< >>sgm<< >>sha<< >>shc<< >>shq<< >>shr<< >>shz<< >>sie<< >>sig<< >>sil<< >>skt<< >>sld<< >>slx<< >>smd<< >>smx<< >>sna<< >>snf<< >>sng<< >>snj<< >>snq<< >>snw<< >>soc<< >>sod<< >>soe<< >>soo<< >>sop<< >>sot<< >>sox<< >>soy<< >>soz<< >>spp<< >>sqa<< >>sqh<< >>sqm<< >>srr<< >>ssc<< >>ssl<< >>ssw<< >>sub<< >>suj<< >>suk<< >>suw<< >>swa<< >>swb<< >>swc<< >>swf<< >>swh<< >>swj<< >>swk<< >>sxb<< >>sxe<< >>sxs<< >>sxw<< >>syi<< >>syx<< >>szg<< >>szv<< >>tap<< >>tbm<< >>tbt<< >>tbz<< >>tcd<< >>tck<< >>tdl<< >>tdo<< >>tdq<< >>tdv<< >>ted<< >>teg<< >>tek<< >>tem<< >>tfi<< >>tga<< >>tgw<< >>tgy<< >>thk<< >>thy<< >>tii<< >>tik<< >>tiq<< >>tiv<< >>tja<< >>tke<< >>tkq<< >>tlj<< >>tll<< >>tmv<< >>tnr<< >>tny<< >>tog<< >>toh<< >>toi<< >>toi_Latn<< >>tor<< >>toz<< >>tpm<< >>tsa<< >>tsc<< >>tsn<< >>tso<< >>tsp<< >>tsv<< >>tsw<< >>ttb<< >>ttf<< >>ttj<< >>ttl<< >>tug<< >>tui<< >>tul<< >>tum<< >>tuz<< >>tvd<< >>tvs<< >>tvu<< >>twl<< >>twn<< >>two<< >>twx<< >>tyi<< >>tyx<< >>uba<< >>uda<< >>uha<< >>uiv<< >>uji<< >>ukh<< >>ukp<< >>ukq<< >>uku<< >>ukw<< >>ula<< >>ulb<< >>umb<< >>umm<< >>une<< >>urh<< >>usk<< >>uta<< >>utr<< >>uya<< >>vag<< >>vau<< >>ven<< >>ver<< >>vid<< >>vif<< >>vig<< >>vin<< >>vit<< >>vki<< >>vmk<< >>vmr<< >>vmw<< >>vor<< >>vum<< >>vun<< >>vut<< >>wav<< >>wbf<< >>wbh<< >>wbi<< >>wci<< >>wdd<< >>wec<< >>weh<< >>wem<< >>wib<< >>wja<< >>wlc<< >>wlx<< >>wmw<< >>wni<< >>wob<< >>wof<< >>wok<< >>wol<< >>wom<< >>won<< >>wss<< >>wud<< >>wum<< >>wun<< >>wwa<< >>www<< >>xab<< >>xdo<< >>xho<< >>xkb<< >>xkt<< >>xku<< >>xkv<< >>xma<< >>xmb<< >>xmc<< >>xmg<< >>xoc<< >>xog<< >>xon<< >>xrb<< >>xsh<< >>xsm<< >>xsn<< >>xsq<< >>xuo<< >>xwe<< >>xwl<< >>xxb<< >>yaf<< >>yaj<< >>yam<< >>yao<< >>yas<< >>yat<< >>yav<< >>yay<< >>yaz<< >>yba<< >>ybb<< >>ybj<< >>ybl<< >>yei<< >>yel<< >>yer<< >>yes<< >>yey<< >>yko<< >>yky<< >>ymk<< >>yng<< >>ynq<< >>yns<< >>yom<< >>yor<< >>yot<< >>yun<< >>zaj<< >>zak<< >>zdj<< >>zga<< >>zhi<< >>zhw<< >>zin<< >>zir<< >>zmb<< >>zmf<< >>zmn<< >>zmp<< >>zmq<< >>zms<< >>zmw<< >>zmx<< >>zmz<< >>zna<< >>zne<< >>zul<<
  • download: opus1m+bt-2021-04-13.zip
  • test set translations: opus1m+bt-2021-04-13.test.txt
  • test set scores: opus1m+bt-2021-04-13.eval.txt

Benchmarks

testset BLEU chr-F #sent #words BP
Tatoeba-test.eng-ewe 5.8 0.290 6 31 1.000
Tatoeba-test.eng-fuc 2.4 0.056 6 21 1.000
Tatoeba-test.eng-ful 0.5 0.077 41 177 1.000
Tatoeba-test.eng-fuv 0.6 0.080 35 156 1.000
Tatoeba-test.eng-ibo 4.1 0.272 21 142 1.000
Tatoeba-test.eng-kin 8.6 0.490 17 80 0.895
Tatoeba-test.eng-lin 1.2 0.283 28 188 1.000
Tatoeba-test.eng-lug 18.4 0.641 2 8 1.000
Tatoeba-test.eng-multi 14.5 0.473 2972 12670 1.000
Tatoeba-test.eng-nya 23.8 0.655 22 93 1.000
Tatoeba-test.eng-run 13.7 0.488 1703 6708 1.000
Tatoeba-test.eng-sag 2.2 0.112 11 47 1.000
Tatoeba-test.eng-sna 20.0 0.599 41 141 1.000
Tatoeba-test.eng-swa 4.3 0.238 386 1881 1.000
Tatoeba-test.eng-toi 7.0 0.190 2 9 0.882
Tatoeba-test.eng-tso 34.1 0.678 3 14 1.000
Tatoeba-test.eng-umb 6.4 0.351 32 117 1.000
Tatoeba-test.eng-wol 4.1 0.141 7 28 1.000
Tatoeba-test.eng-xho 24.9 0.620 152 651 1.000
Tatoeba-test.eng-yor 12.4 0.350 35 189 1.000
Tatoeba-test.eng-zul 41.5 0.780 34 97 1.000
tico19-test.eng-kin 6.7 0.284 2100 55149 0.876
tico19-test.eng-lin 14.2 0.441 2100 61228 1.000
tico19-test.eng-lug 14.1 0.454 2100 52919 0.931
tico19-test.eng-zul 13.4 0.551 2100 44122 1.000