system HF staff commited on
Commit
b725254
1 Parent(s): b93ab38

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +114 -0
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: gmw
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### gmw-eng
10
+
11
+ * source group: West Germanic languages
12
+ * target group: English
13
+ * OPUS readme: [gmw-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/gmw-eng/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): afr ang_Latn deu enm_Latn frr fry gos gsw ksh ltz nds nld pdc sco stq 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/gmw-eng/opus2m-2020-08-01.zip)
21
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmw-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/gmw-eng/opus2m-2020-08-01.eval.txt)
23
+
24
+ ## Benchmarks
25
+
26
+ | testset | BLEU | chr-F |
27
+ |-----------------------|-------|-------|
28
+ | newssyscomb2009-deueng.deu.eng | 27.2 | 0.538 |
29
+ | news-test2008-deueng.deu.eng | 25.7 | 0.534 |
30
+ | newstest2009-deueng.deu.eng | 25.1 | 0.530 |
31
+ | newstest2010-deueng.deu.eng | 27.9 | 0.565 |
32
+ | newstest2011-deueng.deu.eng | 25.3 | 0.539 |
33
+ | newstest2012-deueng.deu.eng | 26.6 | 0.548 |
34
+ | newstest2013-deueng.deu.eng | 29.6 | 0.565 |
35
+ | newstest2014-deen-deueng.deu.eng | 30.2 | 0.571 |
36
+ | newstest2015-ende-deueng.deu.eng | 31.5 | 0.577 |
37
+ | newstest2016-ende-deueng.deu.eng | 36.7 | 0.622 |
38
+ | newstest2017-ende-deueng.deu.eng | 32.3 | 0.585 |
39
+ | newstest2018-ende-deueng.deu.eng | 39.9 | 0.638 |
40
+ | newstest2019-deen-deueng.deu.eng | 35.9 | 0.611 |
41
+ | Tatoeba-test.afr-eng.afr.eng | 61.8 | 0.750 |
42
+ | Tatoeba-test.ang-eng.ang.eng | 7.3 | 0.220 |
43
+ | Tatoeba-test.deu-eng.deu.eng | 48.3 | 0.657 |
44
+ | Tatoeba-test.enm-eng.enm.eng | 16.1 | 0.423 |
45
+ | Tatoeba-test.frr-eng.frr.eng | 7.0 | 0.168 |
46
+ | Tatoeba-test.fry-eng.fry.eng | 28.6 | 0.488 |
47
+ | Tatoeba-test.gos-eng.gos.eng | 15.5 | 0.326 |
48
+ | Tatoeba-test.gsw-eng.gsw.eng | 12.7 | 0.308 |
49
+ | Tatoeba-test.ksh-eng.ksh.eng | 8.4 | 0.254 |
50
+ | Tatoeba-test.ltz-eng.ltz.eng | 28.7 | 0.453 |
51
+ | Tatoeba-test.multi.eng | 48.5 | 0.646 |
52
+ | Tatoeba-test.nds-eng.nds.eng | 31.4 | 0.509 |
53
+ | Tatoeba-test.nld-eng.nld.eng | 58.1 | 0.728 |
54
+ | Tatoeba-test.pdc-eng.pdc.eng | 25.1 | 0.406 |
55
+ | Tatoeba-test.sco-eng.sco.eng | 40.8 | 0.570 |
56
+ | Tatoeba-test.stq-eng.stq.eng | 20.3 | 0.380 |
57
+ | Tatoeba-test.swg-eng.swg.eng | 20.5 | 0.315 |
58
+ | Tatoeba-test.yid-eng.yid.eng | 16.0 | 0.366 |
59
+
60
+
61
+ ### System Info:
62
+ - hf_name: gmw-eng
63
+
64
+ - source_languages: gmw
65
+
66
+ - target_languages: eng
67
+
68
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/gmw-eng/README.md
69
+
70
+ - original_repo: Tatoeba-Challenge
71
+
72
+ - tags: ['translation']
73
+
74
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
75
+
76
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/gmw-eng/opus2m-2020-08-01.zip
77
+
78
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/gmw-eng/opus2m-2020-08-01.test.txt
79
+
80
+ - src_alpha3: gmw
81
+
82
+ - tgt_alpha3: eng
83
+
84
+ - short_pair: gmw-en
85
+
86
+ - chrF2_score: 0.6459999999999999
87
+
88
+ - bleu: 48.5
89
+
90
+ - brevity_penalty: 0.997
91
+
92
+ - ref_len: 72584.0
93
+
94
+ - src_name: West Germanic languages
95
+
96
+ - tgt_name: English
97
+
98
+ - train_date: 2020-08-01
99
+
100
+ - src_alpha2: gmw
101
+
102
+ - tgt_alpha2: en
103
+
104
+ - prefer_old: False
105
+
106
+ - long_pair: gmw-eng
107
+
108
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
109
+
110
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
111
+
112
+ - port_machine: brutasse
113
+
114
+ - port_time: 2020-08-18-01:48