VaishalBusiness commited on
Commit
6f15db4
·
verified ·
1 Parent(s): 3c3a83d

Add README.md for Helsinki-NLP-opus-mt-en-zlw

Browse files
Files changed (1) hide show
  1. Helsinki-NLP-opus-mt-en-zlw/README.md +117 -0
Helsinki-NLP-opus-mt-en-zlw/README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - pl
5
+ - cs
6
+ - zlw
7
+
8
+ tags:
9
+ - translation
10
+
11
+ license: apache-2.0
12
+ ---
13
+
14
+ ### eng-zlw
15
+
16
+ * source group: English
17
+ * target group: West Slavic languages
18
+ * OPUS readme: [eng-zlw](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-zlw/README.md)
19
+
20
+ * model: transformer
21
+ * source language(s): eng
22
+ * target language(s): ces csb_Latn dsb hsb pol
23
+ * model: transformer
24
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
25
+ * a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
26
+ * download original weights: [opus2m-2020-08-02.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zlw/opus2m-2020-08-02.zip)
27
+ * test set translations: [opus2m-2020-08-02.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zlw/opus2m-2020-08-02.test.txt)
28
+ * test set scores: [opus2m-2020-08-02.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zlw/opus2m-2020-08-02.eval.txt)
29
+
30
+ ## Benchmarks
31
+
32
+ | testset | BLEU | chr-F |
33
+ |-----------------------|-------|-------|
34
+ | newssyscomb2009-engces.eng.ces | 20.6 | 0.488 |
35
+ | news-test2008-engces.eng.ces | 18.3 | 0.466 |
36
+ | newstest2009-engces.eng.ces | 19.8 | 0.483 |
37
+ | newstest2010-engces.eng.ces | 19.8 | 0.486 |
38
+ | newstest2011-engces.eng.ces | 20.6 | 0.489 |
39
+ | newstest2012-engces.eng.ces | 18.6 | 0.464 |
40
+ | newstest2013-engces.eng.ces | 22.3 | 0.495 |
41
+ | newstest2015-encs-engces.eng.ces | 21.7 | 0.502 |
42
+ | newstest2016-encs-engces.eng.ces | 24.5 | 0.521 |
43
+ | newstest2017-encs-engces.eng.ces | 20.1 | 0.480 |
44
+ | newstest2018-encs-engces.eng.ces | 19.9 | 0.483 |
45
+ | newstest2019-encs-engces.eng.ces | 21.2 | 0.490 |
46
+ | Tatoeba-test.eng-ces.eng.ces | 43.7 | 0.632 |
47
+ | Tatoeba-test.eng-csb.eng.csb | 1.2 | 0.188 |
48
+ | Tatoeba-test.eng-dsb.eng.dsb | 1.5 | 0.167 |
49
+ | Tatoeba-test.eng-hsb.eng.hsb | 5.7 | 0.199 |
50
+ | Tatoeba-test.eng.multi | 42.8 | 0.632 |
51
+ | Tatoeba-test.eng-pol.eng.pol | 43.2 | 0.641 |
52
+
53
+
54
+ ### System Info:
55
+ - hf_name: eng-zlw
56
+
57
+ - source_languages: eng
58
+
59
+ - target_languages: zlw
60
+
61
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-zlw/README.md
62
+
63
+ - original_repo: Tatoeba-Challenge
64
+
65
+ - tags: ['translation']
66
+
67
+ - languages: ['en', 'pl', 'cs', 'zlw']
68
+
69
+ - src_constituents: {'eng'}
70
+
71
+ - tgt_constituents: {'csb_Latn', 'dsb', 'hsb', 'pol', 'ces'}
72
+
73
+ - src_multilingual: False
74
+
75
+ - tgt_multilingual: True
76
+
77
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
78
+
79
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zlw/opus2m-2020-08-02.zip
80
+
81
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-zlw/opus2m-2020-08-02.test.txt
82
+
83
+ - src_alpha3: eng
84
+
85
+ - tgt_alpha3: zlw
86
+
87
+ - short_pair: en-zlw
88
+
89
+ - chrF2_score: 0.632
90
+
91
+ - bleu: 42.8
92
+
93
+ - brevity_penalty: 0.973
94
+
95
+ - ref_len: 65397.0
96
+
97
+ - src_name: English
98
+
99
+ - tgt_name: West Slavic languages
100
+
101
+ - train_date: 2020-08-02
102
+
103
+ - src_alpha2: en
104
+
105
+ - tgt_alpha2: zlw
106
+
107
+ - prefer_old: False
108
+
109
+ - long_pair: eng-zlw
110
+
111
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
112
+
113
+ - transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
114
+
115
+ - port_machine: brutasse
116
+
117
+ - port_time: 2020-08-21-14:41