system HF staff commited on
Commit
112f0ba
1 Parent(s): d0b927c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +115 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ -pl
4
+ -cs
5
+ -zlw
6
+ -en
7
+
8
+ tags:
9
+ - translation
10
+
11
+ license: apache-2.0
12
+ ---
13
+
14
+ ### zlw-eng
15
+
16
+ * source group: West Slavic languages
17
+ * target group: English
18
+ * OPUS readme: [zlw-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zlw-eng/README.md)
19
+
20
+ * model: transformer
21
+ * source language(s): ces csb_Latn dsb hsb pol
22
+ * target language(s): eng
23
+ * model: transformer
24
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
25
+ * download original weights: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zlw-eng/opus2m-2020-08-01.zip)
26
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zlw-eng/opus2m-2020-08-01.test.txt)
27
+ * test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zlw-eng/opus2m-2020-08-01.eval.txt)
28
+
29
+ ## Benchmarks
30
+
31
+ | testset | BLEU | chr-F |
32
+ |-----------------------|-------|-------|
33
+ | newssyscomb2009-ceseng.ces.eng | 25.7 | 0.536 |
34
+ | newstest2009-ceseng.ces.eng | 24.6 | 0.530 |
35
+ | newstest2010-ceseng.ces.eng | 25.0 | 0.540 |
36
+ | newstest2011-ceseng.ces.eng | 25.9 | 0.539 |
37
+ | newstest2012-ceseng.ces.eng | 24.8 | 0.533 |
38
+ | newstest2013-ceseng.ces.eng | 27.8 | 0.551 |
39
+ | newstest2014-csen-ceseng.ces.eng | 30.3 | 0.585 |
40
+ | newstest2015-encs-ceseng.ces.eng | 27.5 | 0.542 |
41
+ | newstest2016-encs-ceseng.ces.eng | 29.1 | 0.564 |
42
+ | newstest2017-encs-ceseng.ces.eng | 26.0 | 0.537 |
43
+ | newstest2018-encs-ceseng.ces.eng | 27.3 | 0.544 |
44
+ | Tatoeba-test.ces-eng.ces.eng | 53.3 | 0.691 |
45
+ | Tatoeba-test.csb-eng.csb.eng | 10.2 | 0.313 |
46
+ | Tatoeba-test.dsb-eng.dsb.eng | 11.7 | 0.296 |
47
+ | Tatoeba-test.hsb-eng.hsb.eng | 24.6 | 0.426 |
48
+ | Tatoeba-test.multi.eng | 51.8 | 0.680 |
49
+ | Tatoeba-test.pol-eng.pol.eng | 50.4 | 0.667 |
50
+
51
+
52
+ ### System Info:
53
+ - hf_name: zlw-eng
54
+
55
+ - source_languages: zlw
56
+
57
+ - target_languages: eng
58
+
59
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zlw-eng/README.md
60
+
61
+ - original_repo: Tatoeba-Challenge
62
+
63
+ - tags: ['translation']
64
+
65
+ - languages: ['pl', 'cs', 'zlw', 'en']
66
+
67
+ - src_constituents: {'csb_Latn', 'dsb', 'hsb', 'pol', 'ces'}
68
+
69
+ - tgt_constituents: {'eng'}
70
+
71
+ - src_multilingual: True
72
+
73
+ - tgt_multilingual: False
74
+
75
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
76
+
77
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/zlw-eng/opus2m-2020-08-01.zip
78
+
79
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/zlw-eng/opus2m-2020-08-01.test.txt
80
+
81
+ - src_alpha3: zlw
82
+
83
+ - tgt_alpha3: eng
84
+
85
+ - short_pair: zlw-en
86
+
87
+ - chrF2_score: 0.68
88
+
89
+ - bleu: 51.8
90
+
91
+ - brevity_penalty: 0.9620000000000001
92
+
93
+ - ref_len: 75742.0
94
+
95
+ - src_name: West Slavic languages
96
+
97
+ - tgt_name: English
98
+
99
+ - train_date: 2020-08-01
100
+
101
+ - src_alpha2: zlw
102
+
103
+ - tgt_alpha2: en
104
+
105
+ - prefer_old: False
106
+
107
+ - long_pair: zlw-eng
108
+
109
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
110
+
111
+ - transformers_git_sha: 6bdf998dffa70030e42f512a586f33a15e648edd
112
+
113
+ - port_machine: brutasse
114
+
115
+ - port_time: 2020-08-18-21:45