system HF staff commited on
Commit
e9950c1
1 Parent(s): 76d5f80

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: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-gmw
10
+
11
+ * source group: English
12
+ * target group: West Germanic languages
13
+ * OPUS readme: [eng-gmw](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-gmw/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): afr ang_Latn deu enm_Latn frr fry gos gsw ksh ltz nds nld pdc sco stq 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-gmw/opus2m-2020-08-01.zip)
22
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-gmw/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-gmw/opus2m-2020-08-01.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | newssyscomb2009-engdeu.eng.deu | 21.4 | 0.518 |
30
+ | news-test2008-engdeu.eng.deu | 21.0 | 0.510 |
31
+ | newstest2009-engdeu.eng.deu | 20.4 | 0.513 |
32
+ | newstest2010-engdeu.eng.deu | 22.9 | 0.528 |
33
+ | newstest2011-engdeu.eng.deu | 20.5 | 0.508 |
34
+ | newstest2012-engdeu.eng.deu | 21.0 | 0.507 |
35
+ | newstest2013-engdeu.eng.deu | 24.7 | 0.533 |
36
+ | newstest2015-ende-engdeu.eng.deu | 28.2 | 0.568 |
37
+ | newstest2016-ende-engdeu.eng.deu | 33.3 | 0.605 |
38
+ | newstest2017-ende-engdeu.eng.deu | 26.5 | 0.559 |
39
+ | newstest2018-ende-engdeu.eng.deu | 39.9 | 0.649 |
40
+ | newstest2019-ende-engdeu.eng.deu | 35.9 | 0.616 |
41
+ | Tatoeba-test.eng-afr.eng.afr | 55.7 | 0.740 |
42
+ | Tatoeba-test.eng-ang.eng.ang | 6.5 | 0.164 |
43
+ | Tatoeba-test.eng-deu.eng.deu | 40.4 | 0.614 |
44
+ | Tatoeba-test.eng-enm.eng.enm | 2.3 | 0.254 |
45
+ | Tatoeba-test.eng-frr.eng.frr | 8.4 | 0.248 |
46
+ | Tatoeba-test.eng-fry.eng.fry | 17.9 | 0.424 |
47
+ | Tatoeba-test.eng-gos.eng.gos | 2.2 | 0.309 |
48
+ | Tatoeba-test.eng-gsw.eng.gsw | 1.6 | 0.186 |
49
+ | Tatoeba-test.eng-ksh.eng.ksh | 1.5 | 0.189 |
50
+ | Tatoeba-test.eng-ltz.eng.ltz | 20.2 | 0.383 |
51
+ | Tatoeba-test.eng.multi | 41.6 | 0.609 |
52
+ | Tatoeba-test.eng-nds.eng.nds | 18.9 | 0.437 |
53
+ | Tatoeba-test.eng-nld.eng.nld | 53.1 | 0.699 |
54
+ | Tatoeba-test.eng-pdc.eng.pdc | 7.7 | 0.262 |
55
+ | Tatoeba-test.eng-sco.eng.sco | 37.7 | 0.557 |
56
+ | Tatoeba-test.eng-stq.eng.stq | 5.9 | 0.380 |
57
+ | Tatoeba-test.eng-swg.eng.swg | 6.2 | 0.236 |
58
+ | Tatoeba-test.eng-yid.eng.yid | 6.8 | 0.296 |
59
+
60
+
61
+ ### System Info:
62
+ - hf_name: eng-gmw
63
+
64
+ - source_languages: eng
65
+
66
+ - target_languages: gmw
67
+
68
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-gmw/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/eng-gmw/opus2m-2020-08-01.zip
77
+
78
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-gmw/opus2m-2020-08-01.test.txt
79
+
80
+ - src_alpha3: eng
81
+
82
+ - tgt_alpha3: gmw
83
+
84
+ - short_pair: en-gmw
85
+
86
+ - chrF2_score: 0.609
87
+
88
+ - bleu: 41.6
89
+
90
+ - brevity_penalty: 0.9890000000000001
91
+
92
+ - ref_len: 74922.0
93
+
94
+ - src_name: English
95
+
96
+ - tgt_name: West Germanic languages
97
+
98
+ - train_date: 2020-08-01
99
+
100
+ - src_alpha2: en
101
+
102
+ - tgt_alpha2: gmw
103
+
104
+ - prefer_old: False
105
+
106
+ - long_pair: eng-gmw
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