Initial commit
Browse files- .gitattributes +1 -0
- README.md +0 -0
- benchmark_results.txt +326 -0
- benchmark_translations.zip +0 -0
- config.json +41 -0
- generation_config.json +16 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- source.spm +3 -0
- special_tokens_map.json +1 -0
- target.spm +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.spm filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
The diff for this file is too large to render.
See raw diff
|
|
benchmark_results.txt
ADDED
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
multi-multi tatoeba-test-v2020-07-28-v2023-09-26 0.69187 49.4 10000 84179
|
2 |
+
afr-deu flores101-devtest 0.57773 28.6 1012 25094
|
3 |
+
afr-eng flores101-devtest 0.74245 53.8 1012 24721
|
4 |
+
afr-fra flores101-devtest 0.61642 35.9 1012 28343
|
5 |
+
afr-por flores101-devtest 0.61404 35.5 1012 26519
|
6 |
+
afr-spa flores101-devtest 0.51062 22.4 1012 29199
|
7 |
+
deu-fra flores101-devtest 0.61951 36.0 1012 28343
|
8 |
+
deu-por flores101-devtest 0.59947 33.2 1012 26519
|
9 |
+
deu-spa flores101-devtest 0.52237 23.8 1012 29199
|
10 |
+
eng-deu flores101-devtest 0.63903 36.7 1012 25094
|
11 |
+
isl-eng flores101-devtest 0.55472 29.6 1012 24721
|
12 |
+
isl-fra flores101-devtest 0.52253 25.7 1012 28343
|
13 |
+
isl-spa flores101-devtest 0.45474 17.9 1012 29199
|
14 |
+
ltz-deu flores101-devtest 0.59731 30.8 1012 25094
|
15 |
+
ltz-eng flores101-devtest 0.63740 38.2 1012 24721
|
16 |
+
ltz-por flores101-devtest 0.53373 26.7 1012 26519
|
17 |
+
nld-fra flores101-devtest 0.55977 27.9 1012 28343
|
18 |
+
nld-por flores101-devtest 0.54181 25.9 1012 26519
|
19 |
+
nld-spa flores101-devtest 0.48625 19.6 1012 29199
|
20 |
+
swe-deu flores101-devtest 0.59763 31.5 1012 25094
|
21 |
+
swe-eng flores101-devtest 0.69769 46.7 1012 24721
|
22 |
+
swe-fra flores101-devtest 0.62898 38.1 1012 28343
|
23 |
+
swe-por flores101-devtest 0.61040 35.3 1012 26519
|
24 |
+
afr-deu flores200-devtest 0.58114 29.2 1012 25094
|
25 |
+
afr-eng flores200-devtest 0.74448 54.0 1012 24721
|
26 |
+
afr-fra flores200-devtest 0.62075 37.0 1012 28343
|
27 |
+
afr-por flores200-devtest 0.61878 36.3 1012 26519
|
28 |
+
afr-spa flores200-devtest 0.51524 23.0 1012 29199
|
29 |
+
dan-deu flores200-devtest 0.60226 31.4 1012 25094
|
30 |
+
dan-eng flores200-devtest 0.70847 47.1 1012 24721
|
31 |
+
dan-fra flores200-devtest 0.63937 38.9 1012 28343
|
32 |
+
dan-por flores200-devtest 0.62188 36.3 1012 26519
|
33 |
+
dan-spa flores200-devtest 0.52699 24.2 1012 29199
|
34 |
+
deu-eng flores200-devtest 0.67277 41.6 1012 24721
|
35 |
+
deu-fra flores200-devtest 0.62557 36.7 1012 28343
|
36 |
+
deu-por flores200-devtest 0.60450 34.1 1012 26519
|
37 |
+
deu-spa flores200-devtest 0.52346 24.0 1012 29199
|
38 |
+
eng-deu flores200-devtest 0.64294 37.3 1012 25094
|
39 |
+
eng-fra flores200-devtest 0.70649 49.0 1012 28343
|
40 |
+
eng-por flores200-devtest 0.70802 48.9 1012 26519
|
41 |
+
eng-spa flores200-devtest 0.55605 27.1 1012 29199
|
42 |
+
fao-deu flores200-devtest 0.42553 16.2 1012 25094
|
43 |
+
fao-eng flores200-devtest 0.45067 22.5 1012 24721
|
44 |
+
fao-fra flores200-devtest 0.40660 17.5 1012 28343
|
45 |
+
fao-por flores200-devtest 0.40555 16.5 1012 26519
|
46 |
+
fao-spa flores200-devtest 0.36084 11.9 1012 29199
|
47 |
+
isl-deu flores200-devtest 0.49977 21.9 1012 25094
|
48 |
+
isl-eng flores200-devtest 0.56358 30.4 1012 24721
|
49 |
+
isl-fra flores200-devtest 0.53181 26.6 1012 28343
|
50 |
+
isl-por flores200-devtest 0.51706 25.3 1012 26519
|
51 |
+
isl-spa flores200-devtest 0.46015 18.4 1012 29199
|
52 |
+
lim-deu flores200-devtest 0.44990 15.8 1012 25094
|
53 |
+
lim-eng flores200-devtest 0.47463 21.5 1012 24721
|
54 |
+
lim-fra flores200-devtest 0.44097 18.2 1012 28343
|
55 |
+
lim-por flores200-devtest 0.43247 17.2 1012 26519
|
56 |
+
lim-spa flores200-devtest 0.39179 13.7 1012 29199
|
57 |
+
ltz-deu flores200-devtest 0.60196 31.3 1012 25094
|
58 |
+
ltz-eng flores200-devtest 0.64373 38.9 1012 24721
|
59 |
+
ltz-fra flores200-devtest 0.59216 33.4 1012 28343
|
60 |
+
ltz-por flores200-devtest 0.53423 26.8 1012 26519
|
61 |
+
ltz-spa flores200-devtest 0.45465 18.2 1012 29199
|
62 |
+
nld-deu flores200-devtest 0.53629 22.3 1012 25094
|
63 |
+
nld-eng flores200-devtest 0.59199 30.7 1012 24721
|
64 |
+
nld-fra flores200-devtest 0.56488 28.4 1012 28343
|
65 |
+
nld-por flores200-devtest 0.54554 26.2 1012 26519
|
66 |
+
nld-spa flores200-devtest 0.48955 20.0 1012 29199
|
67 |
+
nno-deu flores200-devtest 0.57440 28.4 1012 25094
|
68 |
+
nno-eng flores200-devtest 0.68265 43.8 1012 24721
|
69 |
+
nno-fra flores200-devtest 0.60865 35.6 1012 28343
|
70 |
+
nno-por flores200-devtest 0.59792 33.8 1012 26519
|
71 |
+
nno-spa flores200-devtest 0.51118 22.8 1012 29199
|
72 |
+
nob-deu flores200-devtest 0.56226 26.6 1012 25094
|
73 |
+
nob-eng flores200-devtest 0.67302 42.9 1012 24721
|
74 |
+
nob-fra flores200-devtest 0.60587 34.3 1012 28343
|
75 |
+
nob-por flores200-devtest 0.59086 32.4 1012 26519
|
76 |
+
nob-spa flores200-devtest 0.50910 22.0 1012 29199
|
77 |
+
swe-deu flores200-devtest 0.59867 31.7 1012 25094
|
78 |
+
swe-eng flores200-devtest 0.70155 47.4 1012 24721
|
79 |
+
swe-fra flores200-devtest 0.63360 39.0 1012 28343
|
80 |
+
swe-por flores200-devtest 0.61265 35.8 1012 26519
|
81 |
+
swe-spa flores200-devtest 0.52209 24.1 1012 29199
|
82 |
+
tpi-deu flores200-devtest 0.40345 10.6 1012 25094
|
83 |
+
tpi-eng flores200-devtest 0.48317 19.5 1012 24721
|
84 |
+
tpi-fra flores200-devtest 0.43681 16.1 1012 28343
|
85 |
+
tpi-por flores200-devtest 0.43402 16.0 1012 26519
|
86 |
+
tpi-spa flores200-devtest 0.39430 12.7 1012 29199
|
87 |
+
deu-eng generaltest2022 0.55482 30.2 1984 37634
|
88 |
+
deu-fra generaltest2022 0.60682 37.2 1984 38276
|
89 |
+
eng-deu generaltest2022 0.60337 32.5 2037 38914
|
90 |
+
deu-eng multi30k_task2_test_2016 0.21481 3.9 5000 67382
|
91 |
+
eng-deu multi30k_task2_test_2016 0.26954 2.7 5000 51501
|
92 |
+
deu-eng multi30k_test_2016_flickr 0.60928 40.0 1000 12955
|
93 |
+
deu-fra multi30k_test_2016_flickr 0.62274 37.9 1000 13505
|
94 |
+
eng-deu multi30k_test_2016_flickr 0.63626 34.7 1000 12106
|
95 |
+
eng-fra multi30k_test_2016_flickr 0.69972 48.3 1000 13505
|
96 |
+
deu-eng multi30k_test_2017_flickr 0.63346 40.7 1000 11374
|
97 |
+
deu-fra multi30k_test_2017_flickr 0.62340 36.9 1000 12118
|
98 |
+
eng-deu multi30k_test_2017_flickr 0.62213 33.2 1000 10755
|
99 |
+
eng-fra multi30k_test_2017_flickr 0.71289 50.2 1000 12118
|
100 |
+
deu-eng multi30k_test_2017_mscoco 0.55818 32.5 461 5231
|
101 |
+
deu-fra multi30k_test_2017_mscoco 0.59452 34.4 461 5484
|
102 |
+
eng-deu multi30k_test_2017_mscoco 0.57860 29.2 461 5158
|
103 |
+
eng-fra multi30k_test_2017_mscoco 0.72971 54.1 461 5484
|
104 |
+
deu-eng multi30k_test_2018_flickr 0.59041 36.1 1071 14689
|
105 |
+
deu-fra multi30k_test_2018_flickr 0.56956 30.6 1071 15867
|
106 |
+
eng-deu multi30k_test_2018_flickr 0.59517 30.5 1071 13703
|
107 |
+
eng-fra multi30k_test_2018_flickr 0.64575 40.6 1071 15867
|
108 |
+
eng-fra newsdiscusstest2015 0.63295 37.4 1500 27975
|
109 |
+
deu-eng newssyscomb2009 0.55577 29.0 502 11818
|
110 |
+
deu-fra newssyscomb2009 0.55843 27.4 502 12331
|
111 |
+
deu-spa newssyscomb2009 0.55364 28.0 502 12503
|
112 |
+
eng-deu newssyscomb2009 0.53472 22.7 502 11271
|
113 |
+
eng-fra newssyscomb2009 0.58209 29.0 502 12331
|
114 |
+
eng-spa newssyscomb2009 0.58210 31.1 502 12503
|
115 |
+
deu-eng newstest2008 0.54406 26.9 2051 49380
|
116 |
+
deu-fra newstest2008 0.54711 25.8 2051 52685
|
117 |
+
deu-spa newstest2008 0.53767 25.4 2051 52586
|
118 |
+
eng-deu newstest2008 0.52827 23.0 2051 47447
|
119 |
+
eng-fra newstest2008 0.55113 26.4 2051 52685
|
120 |
+
eng-spa newstest2008 0.56379 29.5 2051 52586
|
121 |
+
deu-eng newstest2009 0.53786 26.3 2525 65399
|
122 |
+
deu-fra newstest2009 0.53993 25.6 2525 69263
|
123 |
+
deu-spa newstest2009 0.53437 25.3 2525 68111
|
124 |
+
eng-deu newstest2009 0.52924 22.0 2525 62816
|
125 |
+
eng-fra newstest2009 0.57445 28.9 2525 69263
|
126 |
+
eng-spa newstest2009 0.57630 29.7 2525 68111
|
127 |
+
deu-eng newstest2010 0.58260 30.2 2489 61711
|
128 |
+
deu-fra newstest2010 0.57553 28.6 2489 66022
|
129 |
+
deu-spa newstest2010 0.59093 32.1 2489 65480
|
130 |
+
eng-deu newstest2010 0.54601 25.2 2489 61503
|
131 |
+
eng-fra newstest2010 0.59310 31.5 2489 66022
|
132 |
+
eng-spa newstest2010 0.61660 36.1 2489 65480
|
133 |
+
deu-eng newstest2011 0.54865 26.6 3003 74681
|
134 |
+
deu-fra newstest2011 0.55548 27.0 3003 80626
|
135 |
+
deu-spa newstest2011 0.56405 30.1 3003 79476
|
136 |
+
eng-deu newstest2011 0.52308 22.5 3003 72981
|
137 |
+
eng-fra newstest2011 0.60656 33.6 3003 80626
|
138 |
+
eng-spa newstest2011 0.61760 38.1 3003 79476
|
139 |
+
deu-eng newstest2012 0.56119 28.1 3003 72812
|
140 |
+
deu-fra newstest2012 0.55823 27.1 3003 78011
|
141 |
+
deu-spa newstest2012 0.57080 30.9 3003 79006
|
142 |
+
eng-deu newstest2012 0.52461 23.2 3003 72886
|
143 |
+
eng-fra newstest2012 0.58890 31.2 3003 78011
|
144 |
+
eng-spa newstest2012 0.62050 38.2 3003 79006
|
145 |
+
deu-eng newstest2013 0.57911 31.4 3000 64505
|
146 |
+
deu-fra newstest2013 0.56212 29.6 3000 70037
|
147 |
+
deu-spa newstest2013 0.56814 31.4 3000 70528
|
148 |
+
eng-deu newstest2013 0.55370 27.0 3000 63737
|
149 |
+
eng-fra newstest2013 0.58712 33.0 3000 70037
|
150 |
+
eng-spa newstest2013 0.59653 35.0 3000 70528
|
151 |
+
deu-eng newstest2014 0.59441 32.7 3003 67337
|
152 |
+
eng-deu newstest2014 0.58610 27.3 3003 62688
|
153 |
+
eng-fra newstest2014 0.64743 38.9 3003 77306
|
154 |
+
deu-eng newstest2015 0.59573 33.6 2169 46443
|
155 |
+
eng-deu newstest2015 0.59581 31.3 2169 44260
|
156 |
+
deu-eng newstest2016 0.64594 40.0 2999 64119
|
157 |
+
eng-deu newstest2016 0.63617 36.8 2999 62669
|
158 |
+
deu-eng newstest2017 0.60931 35.5 3004 64399
|
159 |
+
eng-deu newstest2017 0.58459 29.3 3004 61287
|
160 |
+
deu-eng newstest2018 0.66399 42.9 2998 67012
|
161 |
+
eng-deu newstest2018 0.68676 44.7 2998 64276
|
162 |
+
deu-eng newstest2019 0.63254 39.0 2000 39227
|
163 |
+
deu-fra newstest2019 0.62658 35.7 1701 42509
|
164 |
+
eng-deu newstest2019 0.65659 40.9 1997 48746
|
165 |
+
deu-eng newstest2020 0.60708 34.3 785 38220
|
166 |
+
deu-fra newstest2020 0.60215 32.7 1619 36890
|
167 |
+
eng-deu newstest2020 0.59764 31.2 1418 52383
|
168 |
+
deu-eng newstest2021 0.59635 31.7 1000 20180
|
169 |
+
deu-fra newstest2021 0.58868 31.0 1000 23757
|
170 |
+
eng-deu newstest2021 0.56042 25.5 1002 27970
|
171 |
+
isl-eng newstest2021 0.54878 30.5 1000 22529
|
172 |
+
deu-eng newstestALL2020 0.60708 34.3 785 38220
|
173 |
+
eng-deu newstestALL2020 0.59764 31.2 1418 52383
|
174 |
+
deu-eng newstestB2020 0.60692 34.1 785 37696
|
175 |
+
eng-deu newstestB2020 0.58796 30.6 1418 53092
|
176 |
+
afr-deu ntrex128 0.55455 26.1 1997 48761
|
177 |
+
afr-eng ntrex128 0.72478 51.5 1997 47673
|
178 |
+
afr-fra ntrex128 0.56551 29.1 1997 53481
|
179 |
+
afr-por ntrex128 0.55192 28.0 1997 51631
|
180 |
+
afr-spa ntrex128 0.58404 33.5 1997 54107
|
181 |
+
dan-deu ntrex128 0.53830 24.6 1997 48761
|
182 |
+
dan-eng ntrex128 0.62590 38.0 1997 47673
|
183 |
+
dan-fra ntrex128 0.53853 26.2 1997 53481
|
184 |
+
dan-por ntrex128 0.53295 26.6 1997 51631
|
185 |
+
dan-spa ntrex128 0.55771 30.2 1997 54107
|
186 |
+
deu-eng ntrex128 0.61495 33.5 1997 47673
|
187 |
+
deu-fra ntrex128 0.55631 28.1 1997 53481
|
188 |
+
deu-por ntrex128 0.54078 25.6 1997 51631
|
189 |
+
deu-spa ntrex128 0.56793 30.6 1997 54107
|
190 |
+
eng-deu ntrex128 0.58373 29.7 1997 48761
|
191 |
+
eng-fra ntrex128 0.61168 34.9 1997 53481
|
192 |
+
eng-por ntrex128 0.59703 33.3 1997 51631
|
193 |
+
eng-spa ntrex128 0.63737 39.8 1997 54107
|
194 |
+
fao-deu ntrex128 0.42430 16.0 1997 48761
|
195 |
+
fao-eng ntrex128 0.47552 24.2 1997 47673
|
196 |
+
fao-fra ntrex128 0.40501 16.8 1997 53481
|
197 |
+
fao-por ntrex128 0.40261 15.9 1997 51631
|
198 |
+
fao-spa ntrex128 0.41996 18.2 1997 54107
|
199 |
+
isl-deu ntrex128 0.49197 19.9 1997 48761
|
200 |
+
isl-eng ntrex128 0.55641 28.4 1997 47673
|
201 |
+
isl-fra ntrex128 0.50981 23.2 1997 53481
|
202 |
+
isl-por ntrex128 0.49008 20.9 1997 51631
|
203 |
+
isl-spa ntrex128 0.52176 26.1 1997 54107
|
204 |
+
ltz-deu ntrex128 0.51598 22.0 1997 48761
|
205 |
+
ltz-eng ntrex128 0.58852 33.1 1997 47673
|
206 |
+
ltz-fra ntrex128 0.50270 22.5 1997 53481
|
207 |
+
ltz-por ntrex128 0.46568 19.7 1997 51631
|
208 |
+
ltz-spa ntrex128 0.48287 22.3 1997 54107
|
209 |
+
nld-deu ntrex128 0.55925 25.7 1997 48761
|
210 |
+
nld-eng ntrex128 0.63556 36.2 1997 47673
|
211 |
+
nld-fra ntrex128 0.55930 27.7 1997 53481
|
212 |
+
nld-por ntrex128 0.54481 27.1 1997 51631
|
213 |
+
nld-spa ntrex128 0.57597 32.0 1997 54107
|
214 |
+
nno-deu ntrex128 0.52772 24.1 1997 48761
|
215 |
+
nno-eng ntrex128 0.65262 41.9 1997 47673
|
216 |
+
nno-fra ntrex128 0.54074 27.0 1997 53481
|
217 |
+
nno-por ntrex128 0.52446 25.3 1997 51631
|
218 |
+
nno-spa ntrex128 0.55555 30.1 1997 54107
|
219 |
+
nob-deu ntrex128 0.55215 26.2 1997 48761
|
220 |
+
nob-eng ntrex128 0.64785 39.6 1997 47673
|
221 |
+
nob-fra ntrex128 0.55925 28.9 1997 53481
|
222 |
+
nob-por ntrex128 0.54040 26.1 1997 51631
|
223 |
+
nob-spa ntrex128 0.57388 31.9 1997 54107
|
224 |
+
swe-deu ntrex128 0.55195 26.2 1997 48761
|
225 |
+
swe-eng ntrex128 0.65697 41.4 1997 47673
|
226 |
+
swe-fra ntrex128 0.56103 29.1 1997 53481
|
227 |
+
swe-por ntrex128 0.54574 27.3 1997 51631
|
228 |
+
swe-spa ntrex128 0.57745 32.3 1997 54107
|
229 |
+
dan-por tatoeba-test-v2020-07-28 0.76640 59.4 871 5351
|
230 |
+
eng-deu tatoeba-test-v2020-07-28 0.62977 42.2 10000 83347
|
231 |
+
eng-por tatoeba-test-v2020-07-28 0.71335 52.3 10000 75371
|
232 |
+
gos-eng tatoeba-test-v2020-07-28 0.37440 21.4 1152 5622
|
233 |
+
isl-eng tatoeba-test-v2020-07-28 0.65720 49.8 2500 19763
|
234 |
+
ltz-deu tatoeba-test-v2020-07-28 0.54029 36.9 337 2144
|
235 |
+
nds-spa tatoeba-test-v2020-07-28 0.64968 46.0 913 5477
|
236 |
+
nld-eng tatoeba-test-v2020-07-28 0.74695 61.0 10000 69848
|
237 |
+
nld-fra tatoeba-test-v2020-07-28 0.68413 50.4 10000 69981
|
238 |
+
nob-fra tatoeba-test-v2020-07-28 0.70440 50.9 322 2261
|
239 |
+
swe-fra tatoeba-test-v2020-07-28 0.72309 57.4 1409 9585
|
240 |
+
yid-eng tatoeba-test-v2020-07-28 0.50702 32.4 1168 7741
|
241 |
+
yid-fra tatoeba-test-v2020-07-28 0.54751 27.7 230 1410
|
242 |
+
dan-deu tatoeba-test-v2021-03-30 0.73088 54.3 10000 76069
|
243 |
+
dan-eng tatoeba-test-v2021-03-30 0.76022 62.8 10437 76848
|
244 |
+
dan-fra tatoeba-test-v2021-03-30 0.76079 60.6 1742 11929
|
245 |
+
dan-por tatoeba-test-v2021-03-30 0.76667 59.4 880 5406
|
246 |
+
deu-eng tatoeba-test-v2021-03-30 0.66256 49.2 12664 105121
|
247 |
+
deu-fra tatoeba-test-v2021-03-30 0.67044 48.3 11388 93145
|
248 |
+
eng-eng tatoeba-test-v2021-03-30 0.82713 65.2 10000 96289
|
249 |
+
eng-por tatoeba-test-v2021-03-30 0.71587 52.7 11574 87572
|
250 |
+
frr-deu tatoeba-test-v2021-03-30 0.25716 5.7 279 1886
|
251 |
+
got-eng tatoeba-test-v2021-03-30 0.034 0.0 208 1110
|
252 |
+
isl-deu tatoeba-test-v2021-03-30 0.66934 48.2 990 6456
|
253 |
+
isl-eng tatoeba-test-v2021-03-30 0.65729 49.8 4994 39502
|
254 |
+
nds-deu tatoeba-test-v2021-03-30 0.66009 47.4 10000 74571
|
255 |
+
nds-spa tatoeba-test-v2021-03-30 0.64977 46.0 917 5502
|
256 |
+
nob-fra tatoeba-test-v2021-03-30 0.70656 51.2 326 2286
|
257 |
+
nob-spa tatoeba-test-v2021-03-30 0.73497 55.5 894 6934
|
258 |
+
nor-fra tatoeba-test-v2021-03-30 0.71975 54.3 481 3238
|
259 |
+
swe-eng tatoeba-test-v2021-03-30 0.75118 62.9 10151 67008
|
260 |
+
swe-por tatoeba-test-v2021-03-30 0.69304 49.2 319 1996
|
261 |
+
yid-eng tatoeba-test-v2021-03-30 0.50329 32.2 1888 11810
|
262 |
+
yid-fra tatoeba-test-v2021-03-30 0.53386 28.9 390 2419
|
263 |
+
yid-spa tatoeba-test-v2021-03-30 0.45161 20.8 336 1932
|
264 |
+
afr-deu tatoeba-test-v2021-08-07 0.69326 49.8 1583 9105
|
265 |
+
afr-eng tatoeba-test-v2021-08-07 0.73601 60.6 1374 9622
|
266 |
+
afr-spa tatoeba-test-v2021-08-07 0.73339 58.3 448 2783
|
267 |
+
dan-deu tatoeba-test-v2021-08-07 0.73535 55.0 9998 76055
|
268 |
+
dan-eng tatoeba-test-v2021-08-07 0.76364 63.1 10795 79684
|
269 |
+
dan-fra tatoeba-test-v2021-08-07 0.76184 60.4 1731 11882
|
270 |
+
dan-por tatoeba-test-v2021-08-07 0.77629 60.6 873 5360
|
271 |
+
dan-spa tatoeba-test-v2021-08-07 0.72253 54.4 5000 35528
|
272 |
+
deu-deu tatoeba-test-v2021-08-07 0.59994 35.5 2500 20806
|
273 |
+
deu-eng tatoeba-test-v2021-08-07 0.66046 48.5 17565 149462
|
274 |
+
deu-fra tatoeba-test-v2021-08-07 0.67616 49.0 12418 102721
|
275 |
+
deu-por tatoeba-test-v2021-08-07 0.63474 42.8 10000 81482
|
276 |
+
deu-spa tatoeba-test-v2021-08-07 0.67787 48.7 10521 82570
|
277 |
+
eng-deu tatoeba-test-v2021-08-07 0.62438 40.8 17565 151568
|
278 |
+
eng-eng tatoeba-test-v2021-08-07 0.80550 59.0 12062 115106
|
279 |
+
eng-fra tatoeba-test-v2021-08-07 0.68113 49.7 12681 106378
|
280 |
+
eng-por tatoeba-test-v2021-08-07 0.71775 52.9 13222 105265
|
281 |
+
eng-spa tatoeba-test-v2021-08-07 0.72273 54.9 16583 134710
|
282 |
+
fao-eng tatoeba-test-v2021-08-07 0.56661 41.2 294 1984
|
283 |
+
frr-deu tatoeba-test-v2021-08-07 0.25301 6.0 278 1880
|
284 |
+
fry-eng tatoeba-test-v2021-08-07 0.55624 36.5 220 1573
|
285 |
+
gos-deu tatoeba-test-v2021-08-07 0.44090 22.9 207 1168
|
286 |
+
gos-eng tatoeba-test-v2021-08-07 0.37900 21.1 1154 5635
|
287 |
+
got-eng tatoeba-test-v2021-08-07 0.034 0.0 202 1084
|
288 |
+
gsw-eng tatoeba-test-v2021-08-07 0.45890 31.4 205 990
|
289 |
+
isl-deu tatoeba-test-v2021-08-07 0.67413 49.2 969 6279
|
290 |
+
isl-eng tatoeba-test-v2021-08-07 0.66340 50.5 2503 19788
|
291 |
+
isl-spa tatoeba-test-v2021-08-07 0.65707 46.9 238 1229
|
292 |
+
ltz-deu tatoeba-test-v2021-08-07 0.53615 35.9 347 2208
|
293 |
+
ltz-eng tatoeba-test-v2021-08-07 0.65361 55.5 293 1840
|
294 |
+
nds-deu tatoeba-test-v2021-08-07 0.66127 47.6 9999 74564
|
295 |
+
nds-eng tatoeba-test-v2021-08-07 0.62793 45.8 2500 17589
|
296 |
+
nds-fra tatoeba-test-v2021-08-07 0.61167 43.5 857 5676
|
297 |
+
nds-por tatoeba-test-v2021-08-07 0.59516 41.9 207 1256
|
298 |
+
nds-spa tatoeba-test-v2021-08-07 0.64811 45.8 923 5540
|
299 |
+
nld-deu tatoeba-test-v2021-08-07 0.72788 55.6 10218 74131
|
300 |
+
nld-eng tatoeba-test-v2021-08-07 0.73960 60.2 12696 89978
|
301 |
+
nld-fra tatoeba-test-v2021-08-07 0.68080 47.0 11548 82974
|
302 |
+
nld-por tatoeba-test-v2021-08-07 0.68681 49.2 2500 17326
|
303 |
+
nld-spa tatoeba-test-v2021-08-07 0.69773 51.4 10113 74981
|
304 |
+
nno-eng tatoeba-test-v2021-08-07 0.68656 55.3 460 3524
|
305 |
+
nob-deu tatoeba-test-v2021-08-07 0.69494 49.7 3525 33592
|
306 |
+
nob-eng tatoeba-test-v2021-08-07 0.72289 58.3 4539 36823
|
307 |
+
nob-fra tatoeba-test-v2021-08-07 0.71122 51.7 323 2269
|
308 |
+
nob-spa tatoeba-test-v2021-08-07 0.73468 55.6 885 6866
|
309 |
+
nor-deu tatoeba-test-v2021-08-07 0.69510 49.9 3651 34575
|
310 |
+
nor-eng tatoeba-test-v2021-08-07 0.71970 58.0 5000 40355
|
311 |
+
nor-fra tatoeba-test-v2021-08-07 0.72587 55.0 477 3213
|
312 |
+
nor-por tatoeba-test-v2021-08-07 0.67981 46.3 481 4182
|
313 |
+
nor-spa tatoeba-test-v2021-08-07 0.73337 55.7 960 7311
|
314 |
+
swe-deu tatoeba-test-v2021-08-07 0.71563 54.8 3410 23494
|
315 |
+
swe-eng tatoeba-test-v2021-08-07 0.75486 63.2 10362 68513
|
316 |
+
swe-fra tatoeba-test-v2021-08-07 0.72399 57.2 1407 9580
|
317 |
+
swe-por tatoeba-test-v2021-08-07 0.70201 49.5 320 2032
|
318 |
+
swe-spa tatoeba-test-v2021-08-07 0.70678 54.1 1351 8235
|
319 |
+
swg-deu tatoeba-test-v2021-08-07 0.39415 13.6 1523 15632
|
320 |
+
yid-deu tatoeba-test-v2021-08-07 0.25160 4.9 853 5173
|
321 |
+
yid-eng tatoeba-test-v2021-08-07 0.49708 30.9 2483 15452
|
322 |
+
yid-fra tatoeba-test-v2021-08-07 0.50306 27.5 384 2455
|
323 |
+
yid-spa tatoeba-test-v2021-08-07 0.44196 20.8 407 2478
|
324 |
+
eng-fra tico19-test 0.62405 38.9 2100 64661
|
325 |
+
eng-por tico19-test 0.72533 49.5 2100 62729
|
326 |
+
eng-spa tico19-test 0.72498 51.0 2100 66563
|
benchmark_translations.zip
ADDED
File without changes
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pytorch-models/opus-mt-tc-bible-big-gem-deu_eng_fra_por_spa",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"MarianMTModel"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 1024,
|
12 |
+
"decoder_attention_heads": 16,
|
13 |
+
"decoder_ffn_dim": 4096,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 6,
|
16 |
+
"decoder_start_token_id": 48858,
|
17 |
+
"decoder_vocab_size": 48859,
|
18 |
+
"dropout": 0.1,
|
19 |
+
"encoder_attention_heads": 16,
|
20 |
+
"encoder_ffn_dim": 4096,
|
21 |
+
"encoder_layerdrop": 0.0,
|
22 |
+
"encoder_layers": 6,
|
23 |
+
"eos_token_id": 468,
|
24 |
+
"forced_eos_token_id": null,
|
25 |
+
"init_std": 0.02,
|
26 |
+
"is_encoder_decoder": true,
|
27 |
+
"max_length": null,
|
28 |
+
"max_position_embeddings": 1024,
|
29 |
+
"model_type": "marian",
|
30 |
+
"normalize_embedding": false,
|
31 |
+
"num_beams": null,
|
32 |
+
"num_hidden_layers": 6,
|
33 |
+
"pad_token_id": 48858,
|
34 |
+
"scale_embedding": true,
|
35 |
+
"share_encoder_decoder_embeddings": true,
|
36 |
+
"static_position_embeddings": true,
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.45.1",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 48859
|
41 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bad_words_ids": [
|
4 |
+
[
|
5 |
+
48858
|
6 |
+
]
|
7 |
+
],
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"decoder_start_token_id": 48858,
|
10 |
+
"eos_token_id": 468,
|
11 |
+
"forced_eos_token_id": 468,
|
12 |
+
"max_length": 512,
|
13 |
+
"num_beams": 4,
|
14 |
+
"pad_token_id": 48858,
|
15 |
+
"transformers_version": "4.45.1"
|
16 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6b2801450bfb6580e06a0c4ad69fef583ce37115627a8470632200826bc3cab
|
3 |
+
size 905781020
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:153ff0bd21e79b19b5175775c7625caee71ea8c6a78d878558b1d4f1e19a2244
|
3 |
+
size 905832261
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:578a8e23a5c134f64e6bc6c6fd009634a4aa5abe5481dedfe04d53f135aa40e1
|
3 |
+
size 790465
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd09780b5934876f01d2f26af9faf12fe1f67a77516f7b73ca876e9ed7f62503
|
3 |
+
size 807135
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"source_lang": "gem", "target_lang": "deu+eng+fra+por+spa", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "name_or_path": "marian-models/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30/gem-deu+eng+fra+por+spa", "tokenizer_class": "MarianTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|