system HF staff commited on
Commit
832fc84
1 Parent(s): 85042ad

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +121 -0
README.md ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-gem
10
+
11
+ * source group: English
12
+ * target group: Germanic languages
13
+ * OPUS readme: [eng-gem](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-gem/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): afr ang_Latn dan deu enm_Latn fao frr fry gos got_Goth gsw isl ksh ltz nds nld nno nob nob_Hebr non_Latn pdc sco stq swe swg yid
18
+ * model: transformer
19
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
20
+ * a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
21
+ * download original weights: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-gem/opus2m-2020-08-01.zip)
22
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-gem/opus2m-2020-08-01.test.txt)
23
+ * test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-gem/opus2m-2020-08-01.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | newssyscomb2009-engdeu.eng.deu | 20.9 | 0.521 |
30
+ | news-test2008-engdeu.eng.deu | 21.1 | 0.511 |
31
+ | newstest2009-engdeu.eng.deu | 20.5 | 0.516 |
32
+ | newstest2010-engdeu.eng.deu | 22.5 | 0.526 |
33
+ | newstest2011-engdeu.eng.deu | 20.5 | 0.508 |
34
+ | newstest2012-engdeu.eng.deu | 20.8 | 0.507 |
35
+ | newstest2013-engdeu.eng.deu | 24.6 | 0.534 |
36
+ | newstest2015-ende-engdeu.eng.deu | 27.9 | 0.569 |
37
+ | newstest2016-ende-engdeu.eng.deu | 33.2 | 0.607 |
38
+ | newstest2017-ende-engdeu.eng.deu | 26.5 | 0.560 |
39
+ | newstest2018-ende-engdeu.eng.deu | 39.4 | 0.648 |
40
+ | newstest2019-ende-engdeu.eng.deu | 35.0 | 0.613 |
41
+ | Tatoeba-test.eng-afr.eng.afr | 56.5 | 0.745 |
42
+ | Tatoeba-test.eng-ang.eng.ang | 6.7 | 0.154 |
43
+ | Tatoeba-test.eng-dan.eng.dan | 58.0 | 0.726 |
44
+ | Tatoeba-test.eng-deu.eng.deu | 40.3 | 0.615 |
45
+ | Tatoeba-test.eng-enm.eng.enm | 1.4 | 0.215 |
46
+ | Tatoeba-test.eng-fao.eng.fao | 7.2 | 0.304 |
47
+ | Tatoeba-test.eng-frr.eng.frr | 5.5 | 0.159 |
48
+ | Tatoeba-test.eng-fry.eng.fry | 19.4 | 0.433 |
49
+ | Tatoeba-test.eng-gos.eng.gos | 1.0 | 0.182 |
50
+ | Tatoeba-test.eng-got.eng.got | 0.3 | 0.012 |
51
+ | Tatoeba-test.eng-gsw.eng.gsw | 0.9 | 0.130 |
52
+ | Tatoeba-test.eng-isl.eng.isl | 23.4 | 0.505 |
53
+ | Tatoeba-test.eng-ksh.eng.ksh | 1.1 | 0.141 |
54
+ | Tatoeba-test.eng-ltz.eng.ltz | 20.3 | 0.379 |
55
+ | Tatoeba-test.eng.multi | 46.5 | 0.641 |
56
+ | Tatoeba-test.eng-nds.eng.nds | 20.6 | 0.458 |
57
+ | Tatoeba-test.eng-nld.eng.nld | 53.4 | 0.702 |
58
+ | Tatoeba-test.eng-non.eng.non | 0.6 | 0.166 |
59
+ | Tatoeba-test.eng-nor.eng.nor | 50.3 | 0.679 |
60
+ | Tatoeba-test.eng-pdc.eng.pdc | 3.9 | 0.189 |
61
+ | Tatoeba-test.eng-sco.eng.sco | 33.0 | 0.542 |
62
+ | Tatoeba-test.eng-stq.eng.stq | 2.3 | 0.274 |
63
+ | Tatoeba-test.eng-swe.eng.swe | 57.9 | 0.719 |
64
+ | Tatoeba-test.eng-swg.eng.swg | 1.2 | 0.171 |
65
+ | Tatoeba-test.eng-yid.eng.yid | 7.2 | 0.304 |
66
+
67
+
68
+ ### System Info:
69
+ - hf_name: eng-gem
70
+
71
+ - source_languages: eng
72
+
73
+ - target_languages: gem
74
+
75
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-gem/README.md
76
+
77
+ - original_repo: Tatoeba-Challenge
78
+
79
+ - tags: ['translation']
80
+
81
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
82
+
83
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-gem/opus2m-2020-08-01.zip
84
+
85
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-gem/opus2m-2020-08-01.test.txt
86
+
87
+ - src_alpha3: eng
88
+
89
+ - tgt_alpha3: gem
90
+
91
+ - short_pair: en-gem
92
+
93
+ - chrF2_score: 0.6409999999999999
94
+
95
+ - bleu: 46.5
96
+
97
+ - brevity_penalty: 0.9790000000000001
98
+
99
+ - ref_len: 73328.0
100
+
101
+ - src_name: English
102
+
103
+ - tgt_name: Germanic languages
104
+
105
+ - train_date: 2020-08-01
106
+
107
+ - src_alpha2: en
108
+
109
+ - tgt_alpha2: gem
110
+
111
+ - prefer_old: False
112
+
113
+ - long_pair: eng-gem
114
+
115
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
116
+
117
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
118
+
119
+ - port_machine: brutasse
120
+
121
+ - port_time: 2020-08-18-01:48