system HF staff commited on
Commit
134a1ac
1 Parent(s): 869c138

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: gem
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### gem-eng
10
+
11
+ * source group: Germanic languages
12
+ * target group: English
13
+ * OPUS readme: [gem-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/gem-eng/README.md)
14
+
15
+ * model: transformer
16
+ * source 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
17
+ * target language(s): eng
18
+ * model: transformer
19
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
20
+ * download original weights: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gem-eng/opus2m-2020-08-01.zip)
21
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gem-eng/opus2m-2020-08-01.test.txt)
22
+ * test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gem-eng/opus2m-2020-08-01.eval.txt)
23
+
24
+ ## Benchmarks
25
+
26
+ | testset | BLEU | chr-F |
27
+ |-----------------------|-------|-------|
28
+ | newssyscomb2009-deueng.deu.eng | 27.2 | 0.542 |
29
+ | news-test2008-deueng.deu.eng | 26.3 | 0.536 |
30
+ | newstest2009-deueng.deu.eng | 25.1 | 0.531 |
31
+ | newstest2010-deueng.deu.eng | 28.3 | 0.569 |
32
+ | newstest2011-deueng.deu.eng | 26.0 | 0.543 |
33
+ | newstest2012-deueng.deu.eng | 26.8 | 0.550 |
34
+ | newstest2013-deueng.deu.eng | 30.2 | 0.570 |
35
+ | newstest2014-deen-deueng.deu.eng | 30.7 | 0.574 |
36
+ | newstest2015-ende-deueng.deu.eng | 32.1 | 0.581 |
37
+ | newstest2016-ende-deueng.deu.eng | 36.9 | 0.624 |
38
+ | newstest2017-ende-deueng.deu.eng | 32.8 | 0.588 |
39
+ | newstest2018-ende-deueng.deu.eng | 40.2 | 0.640 |
40
+ | newstest2019-deen-deueng.deu.eng | 36.8 | 0.614 |
41
+ | Tatoeba-test.afr-eng.afr.eng | 62.8 | 0.758 |
42
+ | Tatoeba-test.ang-eng.ang.eng | 10.5 | 0.262 |
43
+ | Tatoeba-test.dan-eng.dan.eng | 61.6 | 0.754 |
44
+ | Tatoeba-test.deu-eng.deu.eng | 49.7 | 0.665 |
45
+ | Tatoeba-test.enm-eng.enm.eng | 23.9 | 0.491 |
46
+ | Tatoeba-test.fao-eng.fao.eng | 23.4 | 0.446 |
47
+ | Tatoeba-test.frr-eng.frr.eng | 10.2 | 0.184 |
48
+ | Tatoeba-test.fry-eng.fry.eng | 29.6 | 0.486 |
49
+ | Tatoeba-test.gos-eng.gos.eng | 17.8 | 0.352 |
50
+ | Tatoeba-test.got-eng.got.eng | 0.1 | 0.058 |
51
+ | Tatoeba-test.gsw-eng.gsw.eng | 15.3 | 0.333 |
52
+ | Tatoeba-test.isl-eng.isl.eng | 51.0 | 0.669 |
53
+ | Tatoeba-test.ksh-eng.ksh.eng | 6.7 | 0.266 |
54
+ | Tatoeba-test.ltz-eng.ltz.eng | 33.0 | 0.505 |
55
+ | Tatoeba-test.multi.eng | 54.0 | 0.687 |
56
+ | Tatoeba-test.nds-eng.nds.eng | 33.6 | 0.529 |
57
+ | Tatoeba-test.nld-eng.nld.eng | 58.9 | 0.733 |
58
+ | Tatoeba-test.non-eng.non.eng | 37.3 | 0.546 |
59
+ | Tatoeba-test.nor-eng.nor.eng | 54.9 | 0.696 |
60
+ | Tatoeba-test.pdc-eng.pdc.eng | 29.6 | 0.446 |
61
+ | Tatoeba-test.sco-eng.sco.eng | 40.5 | 0.581 |
62
+ | Tatoeba-test.stq-eng.stq.eng | 14.5 | 0.361 |
63
+ | Tatoeba-test.swe-eng.swe.eng | 62.0 | 0.745 |
64
+ | Tatoeba-test.swg-eng.swg.eng | 17.1 | 0.334 |
65
+ | Tatoeba-test.yid-eng.yid.eng | 19.4 | 0.400 |
66
+
67
+
68
+ ### System Info:
69
+ - hf_name: gem-eng
70
+
71
+ - source_languages: gem
72
+
73
+ - target_languages: eng
74
+
75
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/gem-eng/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/gem-eng/opus2m-2020-08-01.zip
84
+
85
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/gem-eng/opus2m-2020-08-01.test.txt
86
+
87
+ - src_alpha3: gem
88
+
89
+ - tgt_alpha3: eng
90
+
91
+ - short_pair: gem-en
92
+
93
+ - chrF2_score: 0.687
94
+
95
+ - bleu: 54.0
96
+
97
+ - brevity_penalty: 0.993
98
+
99
+ - ref_len: 72120.0
100
+
101
+ - src_name: Germanic languages
102
+
103
+ - tgt_name: English
104
+
105
+ - train_date: 2020-08-01
106
+
107
+ - src_alpha2: gem
108
+
109
+ - tgt_alpha2: en
110
+
111
+ - prefer_old: False
112
+
113
+ - long_pair: gem-eng
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