VaishalBusiness commited on
Commit
5ee2d9e
·
verified ·
1 Parent(s): eda7448

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

Browse files
Files changed (1) hide show
  1. Helsinki-NLP-opus-mt-bat-en/README.md +107 -0
Helsinki-NLP-opus-mt-bat-en/README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - lt
4
+ - lv
5
+ - bat
6
+ - en
7
+
8
+ tags:
9
+ - translation
10
+
11
+ license: apache-2.0
12
+ ---
13
+
14
+ ### bat-eng
15
+
16
+ * source group: Baltic languages
17
+ * target group: English
18
+ * OPUS readme: [bat-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/bat-eng/README.md)
19
+
20
+ * model: transformer
21
+ * source language(s): lav lit ltg prg_Latn sgs
22
+ * target language(s): eng
23
+ * model: transformer
24
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
25
+ * download original weights: [opus2m-2020-07-31.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/bat-eng/opus2m-2020-07-31.zip)
26
+ * test set translations: [opus2m-2020-07-31.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/bat-eng/opus2m-2020-07-31.test.txt)
27
+ * test set scores: [opus2m-2020-07-31.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/bat-eng/opus2m-2020-07-31.eval.txt)
28
+
29
+ ## Benchmarks
30
+
31
+ | testset | BLEU | chr-F |
32
+ |-----------------------|-------|-------|
33
+ | newsdev2017-enlv-laveng.lav.eng | 27.5 | 0.566 |
34
+ | newsdev2019-enlt-liteng.lit.eng | 27.8 | 0.557 |
35
+ | newstest2017-enlv-laveng.lav.eng | 21.1 | 0.512 |
36
+ | newstest2019-lten-liteng.lit.eng | 30.2 | 0.592 |
37
+ | Tatoeba-test.lav-eng.lav.eng | 51.5 | 0.687 |
38
+ | Tatoeba-test.lit-eng.lit.eng | 55.1 | 0.703 |
39
+ | Tatoeba-test.multi.eng | 50.6 | 0.662 |
40
+ | Tatoeba-test.prg-eng.prg.eng | 1.0 | 0.159 |
41
+ | Tatoeba-test.sgs-eng.sgs.eng | 16.5 | 0.265 |
42
+
43
+
44
+ ### System Info:
45
+ - hf_name: bat-eng
46
+
47
+ - source_languages: bat
48
+
49
+ - target_languages: eng
50
+
51
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/bat-eng/README.md
52
+
53
+ - original_repo: Tatoeba-Challenge
54
+
55
+ - tags: ['translation']
56
+
57
+ - languages: ['lt', 'lv', 'bat', 'en']
58
+
59
+ - src_constituents: {'lit', 'lav', 'prg_Latn', 'ltg', 'sgs'}
60
+
61
+ - tgt_constituents: {'eng'}
62
+
63
+ - src_multilingual: True
64
+
65
+ - tgt_multilingual: False
66
+
67
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
68
+
69
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/bat-eng/opus2m-2020-07-31.zip
70
+
71
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/bat-eng/opus2m-2020-07-31.test.txt
72
+
73
+ - src_alpha3: bat
74
+
75
+ - tgt_alpha3: eng
76
+
77
+ - short_pair: bat-en
78
+
79
+ - chrF2_score: 0.662
80
+
81
+ - bleu: 50.6
82
+
83
+ - brevity_penalty: 0.9890000000000001
84
+
85
+ - ref_len: 30772.0
86
+
87
+ - src_name: Baltic languages
88
+
89
+ - tgt_name: English
90
+
91
+ - train_date: 2020-07-31
92
+
93
+ - src_alpha2: bat
94
+
95
+ - tgt_alpha2: en
96
+
97
+ - prefer_old: False
98
+
99
+ - long_pair: bat-eng
100
+
101
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
102
+
103
+ - transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
104
+
105
+ - port_machine: brutasse
106
+
107
+ - port_time: 2020-08-21-14:41