README.md
23.8 KB · 546 lines · markdown Raw
1 ---
2 language:
3 - ca
4 - es
5 - os
6 - eo
7 - ro
8 - fy
9 - cy
10 - is
11 - lb
12 - su
13 - an
14 - sq
15 - fr
16 - ht
17 - rm
18 - cv
19 - ig
20 - am
21 - eu
22 - tr
23 - ps
24 - af
25 - ny
26 - ch
27 - uk
28 - sl
29 - lt
30 - tk
31 - sg
32 - ar
33 - lg
34 - bg
35 - be
36 - ka
37 - gd
38 - ja
39 - si
40 - br
41 - mh
42 - km
43 - th
44 - ty
45 - rw
46 - te
47 - mk
48 - or
49 - wo
50 - kl
51 - mr
52 - ru
53 - yo
54 - hu
55 - fo
56 - zh
57 - ti
58 - co
59 - ee
60 - oc
61 - sn
62 - mt
63 - ts
64 - pl
65 - gl
66 - nb
67 - bn
68 - tt
69 - bo
70 - lo
71 - id
72 - gn
73 - nv
74 - hy
75 - kn
76 - to
77 - io
78 - so
79 - vi
80 - da
81 - fj
82 - gv
83 - sm
84 - nl
85 - mi
86 - pt
87 - hi
88 - se
89 - as
90 - ta
91 - et
92 - kw
93 - ga
94 - sv
95 - ln
96 - na
97 - mn
98 - gu
99 - wa
100 - lv
101 - jv
102 - el
103 - my
104 - ba
105 - it
106 - hr
107 - ur
108 - ce
109 - nn
110 - fi
111 - mg
112 - rn
113 - xh
114 - ab
115 - de
116 - cs
117 - he
118 - zu
119 - yi
120 - ml
121 - mul
122 - en
123
124 tags:
125 - translation
126
127 license: apache-2.0
128 ---
129
130 ### mul-eng
131
132 * source group: Multiple languages
133 * target group: English
134 * OPUS readme: [mul-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/mul-eng/README.md)
135
136 * model: transformer
137 * source language(s): abk acm ady afb afh_Latn afr akl_Latn aln amh ang_Latn apc ara arg arq ary arz asm ast avk_Latn awa aze_Latn bak bam_Latn bel bel_Latn ben bho bod bos_Latn bre brx brx_Latn bul bul_Latn cat ceb ces cha che chr chv cjy_Hans cjy_Hant cmn cmn_Hans cmn_Hant cor cos crh crh_Latn csb_Latn cym dan deu dsb dtp dws_Latn egl ell enm_Latn epo est eus ewe ext fao fij fin fkv_Latn fra frm_Latn frr fry fuc fuv gan gcf_Latn gil gla gle glg glv gom gos got_Goth grc_Grek grn gsw guj hat hau_Latn haw heb hif_Latn hil hin hnj_Latn hoc hoc_Latn hrv hsb hun hye iba ibo ido ido_Latn ike_Latn ile_Latn ilo ina_Latn ind isl ita izh jav jav_Java jbo jbo_Cyrl jbo_Latn jdt_Cyrl jpn kab kal kan kat kaz_Cyrl kaz_Latn kek_Latn kha khm khm_Latn kin kir_Cyrl kjh kpv krl ksh kum kur_Arab kur_Latn lad lad_Latn lao lat_Latn lav ldn_Latn lfn_Cyrl lfn_Latn lij lin lit liv_Latn lkt lld_Latn lmo ltg ltz lug lzh lzh_Hans mad mah mai mal mar max_Latn mdf mfe mhr mic min mkd mlg mlt mnw moh mon mri mwl mww mya myv nan nau nav nds niu nld nno nob nob_Hebr nog non_Latn nov_Latn npi nya oci ori orv_Cyrl oss ota_Arab ota_Latn pag pan_Guru pap pau pdc pes pes_Latn pes_Thaa pms pnb pol por ppl_Latn prg_Latn pus quc qya qya_Latn rap rif_Latn roh rom ron rue run rus sag sah san_Deva scn sco sgs shs_Latn shy_Latn sin sjn_Latn slv sma sme smo sna snd_Arab som spa sqi srp_Cyrl srp_Latn stq sun swe swg swh tah tam tat tat_Arab tat_Latn tel tet tgk_Cyrl tha tir tlh_Latn tly_Latn tmw_Latn toi_Latn ton tpw_Latn tso tuk tuk_Latn tur tvl tyv tzl tzl_Latn udm uig_Arab uig_Cyrl ukr umb urd uzb_Cyrl uzb_Latn vec vie vie_Hani vol_Latn vro war wln wol wuu xal xho yid yor yue yue_Hans yue_Hant zho zho_Hans zho_Hant zlm_Latn zsm_Latn zul zza
138 * target language(s): eng
139 * model: transformer
140 * pre-processing: normalization + SentencePiece (spm32k,spm32k)
141 * download original weights: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/mul-eng/opus2m-2020-08-01.zip)
142 * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/mul-eng/opus2m-2020-08-01.test.txt)
143 * test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/mul-eng/opus2m-2020-08-01.eval.txt)
144
145 ## Benchmarks
146
147 | testset | BLEU | chr-F |
148 |-----------------------|-------|-------|
149 | newsdev2014-hineng.hin.eng | 8.5 | 0.341 |
150 | newsdev2015-enfi-fineng.fin.eng | 16.8 | 0.441 |
151 | newsdev2016-enro-roneng.ron.eng | 31.3 | 0.580 |
152 | newsdev2016-entr-tureng.tur.eng | 16.4 | 0.422 |
153 | newsdev2017-enlv-laveng.lav.eng | 21.3 | 0.502 |
154 | newsdev2017-enzh-zhoeng.zho.eng | 12.7 | 0.409 |
155 | newsdev2018-enet-esteng.est.eng | 19.8 | 0.467 |
156 | newsdev2019-engu-gujeng.guj.eng | 13.3 | 0.385 |
157 | newsdev2019-enlt-liteng.lit.eng | 19.9 | 0.482 |
158 | newsdiscussdev2015-enfr-fraeng.fra.eng | 26.7 | 0.520 |
159 | newsdiscusstest2015-enfr-fraeng.fra.eng | 29.8 | 0.541 |
160 | newssyscomb2009-ceseng.ces.eng | 21.1 | 0.487 |
161 | newssyscomb2009-deueng.deu.eng | 22.6 | 0.499 |
162 | newssyscomb2009-fraeng.fra.eng | 25.8 | 0.530 |
163 | newssyscomb2009-huneng.hun.eng | 15.1 | 0.430 |
164 | newssyscomb2009-itaeng.ita.eng | 29.4 | 0.555 |
165 | newssyscomb2009-spaeng.spa.eng | 26.1 | 0.534 |
166 | news-test2008-deueng.deu.eng | 21.6 | 0.491 |
167 | news-test2008-fraeng.fra.eng | 22.3 | 0.502 |
168 | news-test2008-spaeng.spa.eng | 23.6 | 0.514 |
169 | newstest2009-ceseng.ces.eng | 19.8 | 0.480 |
170 | newstest2009-deueng.deu.eng | 20.9 | 0.487 |
171 | newstest2009-fraeng.fra.eng | 25.0 | 0.523 |
172 | newstest2009-huneng.hun.eng | 14.7 | 0.425 |
173 | newstest2009-itaeng.ita.eng | 27.6 | 0.542 |
174 | newstest2009-spaeng.spa.eng | 25.7 | 0.530 |
175 | newstest2010-ceseng.ces.eng | 20.6 | 0.491 |
176 | newstest2010-deueng.deu.eng | 23.4 | 0.517 |
177 | newstest2010-fraeng.fra.eng | 26.1 | 0.537 |
178 | newstest2010-spaeng.spa.eng | 29.1 | 0.561 |
179 | newstest2011-ceseng.ces.eng | 21.0 | 0.489 |
180 | newstest2011-deueng.deu.eng | 21.3 | 0.494 |
181 | newstest2011-fraeng.fra.eng | 26.8 | 0.546 |
182 | newstest2011-spaeng.spa.eng | 28.2 | 0.549 |
183 | newstest2012-ceseng.ces.eng | 20.5 | 0.485 |
184 | newstest2012-deueng.deu.eng | 22.3 | 0.503 |
185 | newstest2012-fraeng.fra.eng | 27.5 | 0.545 |
186 | newstest2012-ruseng.rus.eng | 26.6 | 0.532 |
187 | newstest2012-spaeng.spa.eng | 30.3 | 0.567 |
188 | newstest2013-ceseng.ces.eng | 22.5 | 0.498 |
189 | newstest2013-deueng.deu.eng | 25.0 | 0.518 |
190 | newstest2013-fraeng.fra.eng | 27.4 | 0.537 |
191 | newstest2013-ruseng.rus.eng | 21.6 | 0.484 |
192 | newstest2013-spaeng.spa.eng | 28.4 | 0.555 |
193 | newstest2014-csen-ceseng.ces.eng | 24.0 | 0.517 |
194 | newstest2014-deen-deueng.deu.eng | 24.1 | 0.511 |
195 | newstest2014-fren-fraeng.fra.eng | 29.1 | 0.563 |
196 | newstest2014-hien-hineng.hin.eng | 14.0 | 0.414 |
197 | newstest2014-ruen-ruseng.rus.eng | 24.0 | 0.521 |
198 | newstest2015-encs-ceseng.ces.eng | 21.9 | 0.481 |
199 | newstest2015-ende-deueng.deu.eng | 25.5 | 0.519 |
200 | newstest2015-enfi-fineng.fin.eng | 17.4 | 0.441 |
201 | newstest2015-enru-ruseng.rus.eng | 22.4 | 0.494 |
202 | newstest2016-encs-ceseng.ces.eng | 23.0 | 0.500 |
203 | newstest2016-ende-deueng.deu.eng | 30.1 | 0.560 |
204 | newstest2016-enfi-fineng.fin.eng | 18.5 | 0.461 |
205 | newstest2016-enro-roneng.ron.eng | 29.6 | 0.562 |
206 | newstest2016-enru-ruseng.rus.eng | 22.0 | 0.495 |
207 | newstest2016-entr-tureng.tur.eng | 14.8 | 0.415 |
208 | newstest2017-encs-ceseng.ces.eng | 20.2 | 0.475 |
209 | newstest2017-ende-deueng.deu.eng | 26.0 | 0.523 |
210 | newstest2017-enfi-fineng.fin.eng | 19.6 | 0.465 |
211 | newstest2017-enlv-laveng.lav.eng | 16.2 | 0.454 |
212 | newstest2017-enru-ruseng.rus.eng | 24.2 | 0.510 |
213 | newstest2017-entr-tureng.tur.eng | 15.0 | 0.412 |
214 | newstest2017-enzh-zhoeng.zho.eng | 13.7 | 0.412 |
215 | newstest2018-encs-ceseng.ces.eng | 21.2 | 0.486 |
216 | newstest2018-ende-deueng.deu.eng | 31.5 | 0.564 |
217 | newstest2018-enet-esteng.est.eng | 19.7 | 0.473 |
218 | newstest2018-enfi-fineng.fin.eng | 15.1 | 0.418 |
219 | newstest2018-enru-ruseng.rus.eng | 21.3 | 0.490 |
220 | newstest2018-entr-tureng.tur.eng | 15.4 | 0.421 |
221 | newstest2018-enzh-zhoeng.zho.eng | 12.9 | 0.408 |
222 | newstest2019-deen-deueng.deu.eng | 27.0 | 0.529 |
223 | newstest2019-fien-fineng.fin.eng | 17.2 | 0.438 |
224 | newstest2019-guen-gujeng.guj.eng | 9.0 | 0.342 |
225 | newstest2019-lten-liteng.lit.eng | 22.6 | 0.512 |
226 | newstest2019-ruen-ruseng.rus.eng | 24.1 | 0.503 |
227 | newstest2019-zhen-zhoeng.zho.eng | 13.9 | 0.427 |
228 | newstestB2016-enfi-fineng.fin.eng | 15.2 | 0.428 |
229 | newstestB2017-enfi-fineng.fin.eng | 16.8 | 0.442 |
230 | newstestB2017-fien-fineng.fin.eng | 16.8 | 0.442 |
231 | Tatoeba-test.abk-eng.abk.eng | 2.4 | 0.190 |
232 | Tatoeba-test.ady-eng.ady.eng | 1.1 | 0.111 |
233 | Tatoeba-test.afh-eng.afh.eng | 1.7 | 0.108 |
234 | Tatoeba-test.afr-eng.afr.eng | 53.0 | 0.672 |
235 | Tatoeba-test.akl-eng.akl.eng | 5.9 | 0.239 |
236 | Tatoeba-test.amh-eng.amh.eng | 25.6 | 0.464 |
237 | Tatoeba-test.ang-eng.ang.eng | 11.7 | 0.289 |
238 | Tatoeba-test.ara-eng.ara.eng | 26.4 | 0.443 |
239 | Tatoeba-test.arg-eng.arg.eng | 35.9 | 0.473 |
240 | Tatoeba-test.asm-eng.asm.eng | 19.8 | 0.365 |
241 | Tatoeba-test.ast-eng.ast.eng | 31.8 | 0.467 |
242 | Tatoeba-test.avk-eng.avk.eng | 0.4 | 0.119 |
243 | Tatoeba-test.awa-eng.awa.eng | 9.7 | 0.271 |
244 | Tatoeba-test.aze-eng.aze.eng | 37.0 | 0.542 |
245 | Tatoeba-test.bak-eng.bak.eng | 13.9 | 0.395 |
246 | Tatoeba-test.bam-eng.bam.eng | 2.2 | 0.094 |
247 | Tatoeba-test.bel-eng.bel.eng | 36.8 | 0.549 |
248 | Tatoeba-test.ben-eng.ben.eng | 39.7 | 0.546 |
249 | Tatoeba-test.bho-eng.bho.eng | 33.6 | 0.540 |
250 | Tatoeba-test.bod-eng.bod.eng | 1.1 | 0.147 |
251 | Tatoeba-test.bre-eng.bre.eng | 14.2 | 0.303 |
252 | Tatoeba-test.brx-eng.brx.eng | 1.7 | 0.130 |
253 | Tatoeba-test.bul-eng.bul.eng | 46.0 | 0.621 |
254 | Tatoeba-test.cat-eng.cat.eng | 46.6 | 0.636 |
255 | Tatoeba-test.ceb-eng.ceb.eng | 17.4 | 0.347 |
256 | Tatoeba-test.ces-eng.ces.eng | 41.3 | 0.586 |
257 | Tatoeba-test.cha-eng.cha.eng | 7.9 | 0.232 |
258 | Tatoeba-test.che-eng.che.eng | 0.7 | 0.104 |
259 | Tatoeba-test.chm-eng.chm.eng | 7.3 | 0.261 |
260 | Tatoeba-test.chr-eng.chr.eng | 8.8 | 0.244 |
261 | Tatoeba-test.chv-eng.chv.eng | 11.0 | 0.319 |
262 | Tatoeba-test.cor-eng.cor.eng | 5.4 | 0.204 |
263 | Tatoeba-test.cos-eng.cos.eng | 58.2 | 0.643 |
264 | Tatoeba-test.crh-eng.crh.eng | 26.3 | 0.399 |
265 | Tatoeba-test.csb-eng.csb.eng | 18.8 | 0.389 |
266 | Tatoeba-test.cym-eng.cym.eng | 23.4 | 0.407 |
267 | Tatoeba-test.dan-eng.dan.eng | 50.5 | 0.659 |
268 | Tatoeba-test.deu-eng.deu.eng | 39.6 | 0.579 |
269 | Tatoeba-test.dsb-eng.dsb.eng | 24.3 | 0.449 |
270 | Tatoeba-test.dtp-eng.dtp.eng | 1.0 | 0.149 |
271 | Tatoeba-test.dws-eng.dws.eng | 1.6 | 0.061 |
272 | Tatoeba-test.egl-eng.egl.eng | 7.6 | 0.236 |
273 | Tatoeba-test.ell-eng.ell.eng | 55.4 | 0.682 |
274 | Tatoeba-test.enm-eng.enm.eng | 28.0 | 0.489 |
275 | Tatoeba-test.epo-eng.epo.eng | 41.8 | 0.591 |
276 | Tatoeba-test.est-eng.est.eng | 41.5 | 0.581 |
277 | Tatoeba-test.eus-eng.eus.eng | 37.8 | 0.557 |
278 | Tatoeba-test.ewe-eng.ewe.eng | 10.7 | 0.262 |
279 | Tatoeba-test.ext-eng.ext.eng | 25.5 | 0.405 |
280 | Tatoeba-test.fao-eng.fao.eng | 28.7 | 0.469 |
281 | Tatoeba-test.fas-eng.fas.eng | 7.5 | 0.281 |
282 | Tatoeba-test.fij-eng.fij.eng | 24.2 | 0.320 |
283 | Tatoeba-test.fin-eng.fin.eng | 35.8 | 0.534 |
284 | Tatoeba-test.fkv-eng.fkv.eng | 15.5 | 0.434 |
285 | Tatoeba-test.fra-eng.fra.eng | 45.1 | 0.618 |
286 | Tatoeba-test.frm-eng.frm.eng | 29.6 | 0.427 |
287 | Tatoeba-test.frr-eng.frr.eng | 5.5 | 0.138 |
288 | Tatoeba-test.fry-eng.fry.eng | 25.3 | 0.455 |
289 | Tatoeba-test.ful-eng.ful.eng | 1.1 | 0.127 |
290 | Tatoeba-test.gcf-eng.gcf.eng | 16.0 | 0.315 |
291 | Tatoeba-test.gil-eng.gil.eng | 46.7 | 0.587 |
292 | Tatoeba-test.gla-eng.gla.eng | 20.2 | 0.358 |
293 | Tatoeba-test.gle-eng.gle.eng | 43.9 | 0.592 |
294 | Tatoeba-test.glg-eng.glg.eng | 45.1 | 0.623 |
295 | Tatoeba-test.glv-eng.glv.eng | 3.3 | 0.119 |
296 | Tatoeba-test.gos-eng.gos.eng | 20.1 | 0.364 |
297 | Tatoeba-test.got-eng.got.eng | 0.1 | 0.041 |
298 | Tatoeba-test.grc-eng.grc.eng | 2.1 | 0.137 |
299 | Tatoeba-test.grn-eng.grn.eng | 1.7 | 0.152 |
300 | Tatoeba-test.gsw-eng.gsw.eng | 18.2 | 0.334 |
301 | Tatoeba-test.guj-eng.guj.eng | 21.7 | 0.373 |
302 | Tatoeba-test.hat-eng.hat.eng | 34.5 | 0.502 |
303 | Tatoeba-test.hau-eng.hau.eng | 10.5 | 0.295 |
304 | Tatoeba-test.haw-eng.haw.eng | 2.8 | 0.160 |
305 | Tatoeba-test.hbs-eng.hbs.eng | 46.7 | 0.623 |
306 | Tatoeba-test.heb-eng.heb.eng | 33.0 | 0.492 |
307 | Tatoeba-test.hif-eng.hif.eng | 17.0 | 0.391 |
308 | Tatoeba-test.hil-eng.hil.eng | 16.0 | 0.339 |
309 | Tatoeba-test.hin-eng.hin.eng | 36.4 | 0.533 |
310 | Tatoeba-test.hmn-eng.hmn.eng | 0.4 | 0.131 |
311 | Tatoeba-test.hoc-eng.hoc.eng | 0.7 | 0.132 |
312 | Tatoeba-test.hsb-eng.hsb.eng | 41.9 | 0.551 |
313 | Tatoeba-test.hun-eng.hun.eng | 33.2 | 0.510 |
314 | Tatoeba-test.hye-eng.hye.eng | 32.2 | 0.487 |
315 | Tatoeba-test.iba-eng.iba.eng | 9.4 | 0.278 |
316 | Tatoeba-test.ibo-eng.ibo.eng | 5.8 | 0.200 |
317 | Tatoeba-test.ido-eng.ido.eng | 31.7 | 0.503 |
318 | Tatoeba-test.iku-eng.iku.eng | 9.1 | 0.164 |
319 | Tatoeba-test.ile-eng.ile.eng | 42.2 | 0.595 |
320 | Tatoeba-test.ilo-eng.ilo.eng | 29.7 | 0.485 |
321 | Tatoeba-test.ina-eng.ina.eng | 42.1 | 0.607 |
322 | Tatoeba-test.isl-eng.isl.eng | 35.7 | 0.527 |
323 | Tatoeba-test.ita-eng.ita.eng | 54.8 | 0.686 |
324 | Tatoeba-test.izh-eng.izh.eng | 28.3 | 0.526 |
325 | Tatoeba-test.jav-eng.jav.eng | 10.0 | 0.282 |
326 | Tatoeba-test.jbo-eng.jbo.eng | 0.3 | 0.115 |
327 | Tatoeba-test.jdt-eng.jdt.eng | 5.3 | 0.140 |
328 | Tatoeba-test.jpn-eng.jpn.eng | 18.8 | 0.387 |
329 | Tatoeba-test.kab-eng.kab.eng | 3.9 | 0.205 |
330 | Tatoeba-test.kal-eng.kal.eng | 16.9 | 0.329 |
331 | Tatoeba-test.kan-eng.kan.eng | 16.2 | 0.374 |
332 | Tatoeba-test.kat-eng.kat.eng | 31.1 | 0.493 |
333 | Tatoeba-test.kaz-eng.kaz.eng | 24.5 | 0.437 |
334 | Tatoeba-test.kek-eng.kek.eng | 7.4 | 0.192 |
335 | Tatoeba-test.kha-eng.kha.eng | 1.0 | 0.154 |
336 | Tatoeba-test.khm-eng.khm.eng | 12.2 | 0.290 |
337 | Tatoeba-test.kin-eng.kin.eng | 22.5 | 0.355 |
338 | Tatoeba-test.kir-eng.kir.eng | 27.2 | 0.470 |
339 | Tatoeba-test.kjh-eng.kjh.eng | 2.1 | 0.129 |
340 | Tatoeba-test.kok-eng.kok.eng | 4.5 | 0.259 |
341 | Tatoeba-test.kom-eng.kom.eng | 1.4 | 0.099 |
342 | Tatoeba-test.krl-eng.krl.eng | 26.1 | 0.387 |
343 | Tatoeba-test.ksh-eng.ksh.eng | 5.5 | 0.256 |
344 | Tatoeba-test.kum-eng.kum.eng | 9.3 | 0.288 |
345 | Tatoeba-test.kur-eng.kur.eng | 9.6 | 0.208 |
346 | Tatoeba-test.lad-eng.lad.eng | 30.1 | 0.475 |
347 | Tatoeba-test.lah-eng.lah.eng | 11.6 | 0.284 |
348 | Tatoeba-test.lao-eng.lao.eng | 4.5 | 0.214 |
349 | Tatoeba-test.lat-eng.lat.eng | 21.5 | 0.402 |
350 | Tatoeba-test.lav-eng.lav.eng | 40.2 | 0.577 |
351 | Tatoeba-test.ldn-eng.ldn.eng | 0.8 | 0.115 |
352 | Tatoeba-test.lfn-eng.lfn.eng | 23.0 | 0.433 |
353 | Tatoeba-test.lij-eng.lij.eng | 9.3 | 0.287 |
354 | Tatoeba-test.lin-eng.lin.eng | 2.4 | 0.196 |
355 | Tatoeba-test.lit-eng.lit.eng | 44.0 | 0.597 |
356 | Tatoeba-test.liv-eng.liv.eng | 1.6 | 0.115 |
357 | Tatoeba-test.lkt-eng.lkt.eng | 2.0 | 0.113 |
358 | Tatoeba-test.lld-eng.lld.eng | 18.3 | 0.312 |
359 | Tatoeba-test.lmo-eng.lmo.eng | 25.4 | 0.395 |
360 | Tatoeba-test.ltz-eng.ltz.eng | 35.9 | 0.509 |
361 | Tatoeba-test.lug-eng.lug.eng | 5.1 | 0.357 |
362 | Tatoeba-test.mad-eng.mad.eng | 2.8 | 0.123 |
363 | Tatoeba-test.mah-eng.mah.eng | 5.7 | 0.175 |
364 | Tatoeba-test.mai-eng.mai.eng | 56.3 | 0.703 |
365 | Tatoeba-test.mal-eng.mal.eng | 37.5 | 0.534 |
366 | Tatoeba-test.mar-eng.mar.eng | 22.8 | 0.470 |
367 | Tatoeba-test.mdf-eng.mdf.eng | 2.0 | 0.110 |
368 | Tatoeba-test.mfe-eng.mfe.eng | 59.2 | 0.764 |
369 | Tatoeba-test.mic-eng.mic.eng | 9.0 | 0.199 |
370 | Tatoeba-test.mkd-eng.mkd.eng | 44.3 | 0.593 |
371 | Tatoeba-test.mlg-eng.mlg.eng | 31.9 | 0.424 |
372 | Tatoeba-test.mlt-eng.mlt.eng | 38.6 | 0.540 |
373 | Tatoeba-test.mnw-eng.mnw.eng | 2.5 | 0.101 |
374 | Tatoeba-test.moh-eng.moh.eng | 0.3 | 0.110 |
375 | Tatoeba-test.mon-eng.mon.eng | 13.5 | 0.334 |
376 | Tatoeba-test.mri-eng.mri.eng | 8.5 | 0.260 |
377 | Tatoeba-test.msa-eng.msa.eng | 33.9 | 0.520 |
378 | Tatoeba-test.multi.eng | 34.7 | 0.518 |
379 | Tatoeba-test.mwl-eng.mwl.eng | 37.4 | 0.630 |
380 | Tatoeba-test.mya-eng.mya.eng | 15.5 | 0.335 |
381 | Tatoeba-test.myv-eng.myv.eng | 0.8 | 0.118 |
382 | Tatoeba-test.nau-eng.nau.eng | 9.0 | 0.186 |
383 | Tatoeba-test.nav-eng.nav.eng | 1.3 | 0.144 |
384 | Tatoeba-test.nds-eng.nds.eng | 30.7 | 0.495 |
385 | Tatoeba-test.nep-eng.nep.eng | 3.5 | 0.168 |
386 | Tatoeba-test.niu-eng.niu.eng | 42.7 | 0.492 |
387 | Tatoeba-test.nld-eng.nld.eng | 47.9 | 0.640 |
388 | Tatoeba-test.nog-eng.nog.eng | 12.7 | 0.284 |
389 | Tatoeba-test.non-eng.non.eng | 43.8 | 0.586 |
390 | Tatoeba-test.nor-eng.nor.eng | 45.5 | 0.619 |
391 | Tatoeba-test.nov-eng.nov.eng | 26.9 | 0.472 |
392 | Tatoeba-test.nya-eng.nya.eng | 33.2 | 0.456 |
393 | Tatoeba-test.oci-eng.oci.eng | 17.9 | 0.370 |
394 | Tatoeba-test.ori-eng.ori.eng | 14.6 | 0.305 |
395 | Tatoeba-test.orv-eng.orv.eng | 11.0 | 0.283 |
396 | Tatoeba-test.oss-eng.oss.eng | 4.1 | 0.211 |
397 | Tatoeba-test.ota-eng.ota.eng | 4.1 | 0.216 |
398 | Tatoeba-test.pag-eng.pag.eng | 24.3 | 0.468 |
399 | Tatoeba-test.pan-eng.pan.eng | 16.4 | 0.358 |
400 | Tatoeba-test.pap-eng.pap.eng | 53.2 | 0.628 |
401 | Tatoeba-test.pau-eng.pau.eng | 3.7 | 0.173 |
402 | Tatoeba-test.pdc-eng.pdc.eng | 45.3 | 0.569 |
403 | Tatoeba-test.pms-eng.pms.eng | 14.0 | 0.345 |
404 | Tatoeba-test.pol-eng.pol.eng | 41.7 | 0.588 |
405 | Tatoeba-test.por-eng.por.eng | 51.4 | 0.669 |
406 | Tatoeba-test.ppl-eng.ppl.eng | 0.4 | 0.134 |
407 | Tatoeba-test.prg-eng.prg.eng | 4.1 | 0.198 |
408 | Tatoeba-test.pus-eng.pus.eng | 6.7 | 0.233 |
409 | Tatoeba-test.quc-eng.quc.eng | 3.5 | 0.091 |
410 | Tatoeba-test.qya-eng.qya.eng | 0.2 | 0.090 |
411 | Tatoeba-test.rap-eng.rap.eng | 17.5 | 0.230 |
412 | Tatoeba-test.rif-eng.rif.eng | 4.2 | 0.164 |
413 | Tatoeba-test.roh-eng.roh.eng | 24.6 | 0.464 |
414 | Tatoeba-test.rom-eng.rom.eng | 3.4 | 0.212 |
415 | Tatoeba-test.ron-eng.ron.eng | 45.2 | 0.620 |
416 | Tatoeba-test.rue-eng.rue.eng | 21.4 | 0.390 |
417 | Tatoeba-test.run-eng.run.eng | 24.5 | 0.392 |
418 | Tatoeba-test.rus-eng.rus.eng | 42.7 | 0.591 |
419 | Tatoeba-test.sag-eng.sag.eng | 3.4 | 0.187 |
420 | Tatoeba-test.sah-eng.sah.eng | 5.0 | 0.177 |
421 | Tatoeba-test.san-eng.san.eng | 2.0 | 0.172 |
422 | Tatoeba-test.scn-eng.scn.eng | 35.8 | 0.410 |
423 | Tatoeba-test.sco-eng.sco.eng | 34.6 | 0.520 |
424 | Tatoeba-test.sgs-eng.sgs.eng | 21.8 | 0.299 |
425 | Tatoeba-test.shs-eng.shs.eng | 1.8 | 0.122 |
426 | Tatoeba-test.shy-eng.shy.eng | 1.4 | 0.104 |
427 | Tatoeba-test.sin-eng.sin.eng | 20.6 | 0.429 |
428 | Tatoeba-test.sjn-eng.sjn.eng | 1.2 | 0.095 |
429 | Tatoeba-test.slv-eng.slv.eng | 37.0 | 0.545 |
430 | Tatoeba-test.sma-eng.sma.eng | 4.4 | 0.147 |
431 | Tatoeba-test.sme-eng.sme.eng | 8.9 | 0.229 |
432 | Tatoeba-test.smo-eng.smo.eng | 37.7 | 0.483 |
433 | Tatoeba-test.sna-eng.sna.eng | 18.0 | 0.359 |
434 | Tatoeba-test.snd-eng.snd.eng | 28.1 | 0.444 |
435 | Tatoeba-test.som-eng.som.eng | 23.6 | 0.472 |
436 | Tatoeba-test.spa-eng.spa.eng | 47.9 | 0.645 |
437 | Tatoeba-test.sqi-eng.sqi.eng | 46.9 | 0.634 |
438 | Tatoeba-test.stq-eng.stq.eng | 8.1 | 0.379 |
439 | Tatoeba-test.sun-eng.sun.eng | 23.8 | 0.369 |
440 | Tatoeba-test.swa-eng.swa.eng | 6.5 | 0.193 |
441 | Tatoeba-test.swe-eng.swe.eng | 51.4 | 0.655 |
442 | Tatoeba-test.swg-eng.swg.eng | 18.5 | 0.342 |
443 | Tatoeba-test.tah-eng.tah.eng | 25.6 | 0.249 |
444 | Tatoeba-test.tam-eng.tam.eng | 29.1 | 0.437 |
445 | Tatoeba-test.tat-eng.tat.eng | 12.9 | 0.327 |
446 | Tatoeba-test.tel-eng.tel.eng | 21.2 | 0.386 |
447 | Tatoeba-test.tet-eng.tet.eng | 9.2 | 0.215 |
448 | Tatoeba-test.tgk-eng.tgk.eng | 12.7 | 0.374 |
449 | Tatoeba-test.tha-eng.tha.eng | 36.3 | 0.531 |
450 | Tatoeba-test.tir-eng.tir.eng | 9.1 | 0.267 |
451 | Tatoeba-test.tlh-eng.tlh.eng | 0.2 | 0.084 |
452 | Tatoeba-test.tly-eng.tly.eng | 2.1 | 0.128 |
453 | Tatoeba-test.toi-eng.toi.eng | 5.3 | 0.150 |
454 | Tatoeba-test.ton-eng.ton.eng | 39.5 | 0.473 |
455 | Tatoeba-test.tpw-eng.tpw.eng | 1.5 | 0.160 |
456 | Tatoeba-test.tso-eng.tso.eng | 44.7 | 0.526 |
457 | Tatoeba-test.tuk-eng.tuk.eng | 18.6 | 0.401 |
458 | Tatoeba-test.tur-eng.tur.eng | 40.5 | 0.573 |
459 | Tatoeba-test.tvl-eng.tvl.eng | 55.0 | 0.593 |
460 | Tatoeba-test.tyv-eng.tyv.eng | 19.1 | 0.477 |
461 | Tatoeba-test.tzl-eng.tzl.eng | 17.7 | 0.333 |
462 | Tatoeba-test.udm-eng.udm.eng | 3.4 | 0.217 |
463 | Tatoeba-test.uig-eng.uig.eng | 11.4 | 0.289 |
464 | Tatoeba-test.ukr-eng.ukr.eng | 43.1 | 0.595 |
465 | Tatoeba-test.umb-eng.umb.eng | 9.2 | 0.260 |
466 | Tatoeba-test.urd-eng.urd.eng | 23.2 | 0.426 |
467 | Tatoeba-test.uzb-eng.uzb.eng | 19.0 | 0.342 |
468 | Tatoeba-test.vec-eng.vec.eng | 41.1 | 0.409 |
469 | Tatoeba-test.vie-eng.vie.eng | 30.6 | 0.481 |
470 | Tatoeba-test.vol-eng.vol.eng | 1.8 | 0.143 |
471 | Tatoeba-test.war-eng.war.eng | 15.9 | 0.352 |
472 | Tatoeba-test.wln-eng.wln.eng | 12.6 | 0.291 |
473 | Tatoeba-test.wol-eng.wol.eng | 4.4 | 0.138 |
474 | Tatoeba-test.xal-eng.xal.eng | 0.9 | 0.153 |
475 | Tatoeba-test.xho-eng.xho.eng | 35.4 | 0.513 |
476 | Tatoeba-test.yid-eng.yid.eng | 19.4 | 0.387 |
477 | Tatoeba-test.yor-eng.yor.eng | 19.3 | 0.327 |
478 | Tatoeba-test.zho-eng.zho.eng | 25.8 | 0.448 |
479 | Tatoeba-test.zul-eng.zul.eng | 40.9 | 0.567 |
480 | Tatoeba-test.zza-eng.zza.eng | 1.6 | 0.125 |
481
482
483 ### System Info:
484 - hf_name: mul-eng
485
486 - source_languages: mul
487
488 - target_languages: eng
489
490 - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/mul-eng/README.md
491
492 - original_repo: Tatoeba-Challenge
493
494 - tags: ['translation']
495
496 - languages: ['ca', 'es', 'os', 'eo', 'ro', 'fy', 'cy', 'is', 'lb', 'su', 'an', 'sq', 'fr', 'ht', 'rm', 'cv', 'ig', 'am', 'eu', 'tr', 'ps', 'af', 'ny', 'ch', 'uk', 'sl', 'lt', 'tk', 'sg', 'ar', 'lg', 'bg', 'be', 'ka', 'gd', 'ja', 'si', 'br', 'mh', 'km', 'th', 'ty', 'rw', 'te', 'mk', 'or', 'wo', 'kl', 'mr', 'ru', 'yo', 'hu', 'fo', 'zh', 'ti', 'co', 'ee', 'oc', 'sn', 'mt', 'ts', 'pl', 'gl', 'nb', 'bn', 'tt', 'bo', 'lo', 'id', 'gn', 'nv', 'hy', 'kn', 'to', 'io', 'so', 'vi', 'da', 'fj', 'gv', 'sm', 'nl', 'mi', 'pt', 'hi', 'se', 'as', 'ta', 'et', 'kw', 'ga', 'sv', 'ln', 'na', 'mn', 'gu', 'wa', 'lv', 'jv', 'el', 'my', 'ba', 'it', 'hr', 'ur', 'ce', 'nn', 'fi', 'mg', 'rn', 'xh', 'ab', 'de', 'cs', 'he', 'zu', 'yi', 'ml', 'mul', 'en']
497
498 - src_constituents: {'sjn_Latn', 'cat', 'nan', 'spa', 'ile_Latn', 'pap', 'mwl', 'uzb_Latn', 'mww', 'hil', 'lij', 'avk_Latn', 'lad_Latn', 'lat_Latn', 'bos_Latn', 'oss', 'epo', 'ron', 'fry', 'cym', 'toi_Latn', 'awa', 'swg', 'zsm_Latn', 'zho_Hant', 'gcf_Latn', 'uzb_Cyrl', 'isl', 'lfn_Latn', 'shs_Latn', 'nov_Latn', 'bho', 'ltz', 'lzh', 'kur_Latn', 'sun', 'arg', 'pes_Thaa', 'sqi', 'uig_Arab', 'csb_Latn', 'fra', 'hat', 'liv_Latn', 'non_Latn', 'sco', 'cmn_Hans', 'pnb', 'roh', 'chv', 'ibo', 'bul_Latn', 'amh', 'lfn_Cyrl', 'eus', 'fkv_Latn', 'tur', 'pus', 'afr', 'brx_Latn', 'nya', 'acm', 'ota_Latn', 'cha', 'ukr', 'xal', 'slv', 'lit', 'zho_Hans', 'tmw_Latn', 'kjh', 'ota_Arab', 'war', 'tuk', 'sag', 'myv', 'hsb', 'lzh_Hans', 'ara', 'tly_Latn', 'lug', 'brx', 'bul', 'bel', 'vol_Latn', 'kat', 'gan', 'got_Goth', 'vro', 'ext', 'afh_Latn', 'gla', 'jpn', 'udm', 'mai', 'ary', 'sin', 'tvl', 'hif_Latn', 'cjy_Hant', 'bre', 'ceb', 'mah', 'nob_Hebr', 'crh_Latn', 'prg_Latn', 'khm', 'ang_Latn', 'tha', 'tah', 'tzl', 'aln', 'kin', 'tel', 'ady', 'mkd', 'ori', 'wol', 'aze_Latn', 'jbo', 'niu', 'kal', 'mar', 'vie_Hani', 'arz', 'yue', 'kha', 'san_Deva', 'jbo_Latn', 'gos', 'hau_Latn', 'rus', 'quc', 'cmn', 'yor', 'hun', 'uig_Cyrl', 'fao', 'mnw', 'zho', 'orv_Cyrl', 'iba', 'bel_Latn', 'tir', 'afb', 'crh', 'mic', 'cos', 'swh', 'sah', 'krl', 'ewe', 'apc', 'zza', 'chr', 'grc_Grek', 'tpw_Latn', 'oci', 'mfe', 'sna', 'kir_Cyrl', 'tat_Latn', 'gom', 'ido_Latn', 'sgs', 'pau', 'tgk_Cyrl', 'nog', 'mlt', 'pdc', 'tso', 'srp_Cyrl', 'pol', 'ast', 'glg', 'pms', 'fuc', 'nob', 'qya', 'ben', 'tat', 'kab', 'min', 'srp_Latn', 'wuu', 'dtp', 'jbo_Cyrl', 'tet', 'bod', 'yue_Hans', 'zlm_Latn', 'lao', 'ind', 'grn', 'nav', 'kaz_Cyrl', 'rom', 'hye', 'kan', 'ton', 'ido', 'mhr', 'scn', 'som', 'rif_Latn', 'vie', 'enm_Latn', 'lmo', 'npi', 'pes', 'dan', 'fij', 'ina_Latn', 'cjy_Hans', 'jdt_Cyrl', 'gsw', 'glv', 'khm_Latn', 'smo', 'umb', 'sma', 'gil', 'nld', 'snd_Arab', 'arq', 'mri', 'kur_Arab', 'por', 'hin', 'shy_Latn', 'sme', 'rap', 'tyv', 'dsb', 'moh', 'asm', 'lad', 'yue_Hant', 'kpv', 'tam', 'est', 'frm_Latn', 'hoc_Latn', 'bam_Latn', 'kek_Latn', 'ksh', 'tlh_Latn', 'ltg', 'pan_Guru', 'hnj_Latn', 'cor', 'gle', 'swe', 'lin', 'qya_Latn', 'kum', 'mad', 'cmn_Hant', 'fuv', 'nau', 'mon', 'akl_Latn', 'guj', 'kaz_Latn', 'wln', 'tuk_Latn', 'jav_Java', 'lav', 'jav', 'ell', 'frr', 'mya', 'bak', 'rue', 'ita', 'hrv', 'izh', 'ilo', 'dws_Latn', 'urd', 'stq', 'tat_Arab', 'haw', 'che', 'pag', 'nno', 'fin', 'mlg', 'ppl_Latn', 'run', 'xho', 'abk', 'deu', 'hoc', 'lkt', 'lld_Latn', 'tzl_Latn', 'mdf', 'ike_Latn', 'ces', 'ldn_Latn', 'egl', 'heb', 'vec', 'zul', 'max_Latn', 'pes_Latn', 'yid', 'mal', 'nds'}
499
500 - tgt_constituents: {'eng'}
501
502 - src_multilingual: True
503
504 - tgt_multilingual: False
505
506 - prepro: normalization + SentencePiece (spm32k,spm32k)
507
508 - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/mul-eng/opus2m-2020-08-01.zip
509
510 - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/mul-eng/opus2m-2020-08-01.test.txt
511
512 - src_alpha3: mul
513
514 - tgt_alpha3: eng
515
516 - short_pair: mul-en
517
518 - chrF2_score: 0.518
519
520 - bleu: 34.7
521
522 - brevity_penalty: 1.0
523
524 - ref_len: 72346.0
525
526 - src_name: Multiple languages
527
528 - tgt_name: English
529
530 - train_date: 2020-08-01
531
532 - src_alpha2: mul
533
534 - tgt_alpha2: en
535
536 - prefer_old: False
537
538 - long_pair: mul-eng
539
540 - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
541
542 - transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
543
544 - port_machine: brutasse
545
546 - port_time: 2020-08-21-14:41