opus-mt-urj-en / README.md
system
Update README.md 9580445
1
---
2
language: 
3
- se
4
- fi
5
- hu
6
- et
7
- urj
8
- en
9
10
tags:
11
- translation
12
13
license: apache-2.0
14
---
15
16
### urj-eng
17
18
* source group: Uralic languages 
19
* target group: English 
20
*  OPUS readme: [urj-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/urj-eng/README.md)
21
22
*  model: transformer
23
* source language(s): est fin fkv_Latn hun izh kpv krl liv_Latn mdf mhr myv sma sme udm vro
24
* target language(s): eng
25
* model: transformer
26
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
27
* download original weights: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/urj-eng/opus2m-2020-08-01.zip)
28
* test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/urj-eng/opus2m-2020-08-01.test.txt)
29
* test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/urj-eng/opus2m-2020-08-01.eval.txt)
30
31
## Benchmarks
32
33
| testset               | BLEU  | chr-F |
34
|-----------------------|-------|-------|
35
| newsdev2015-enfi-fineng.fin.eng 	| 22.7 	| 0.511 |
36
| newsdev2018-enet-esteng.est.eng 	| 26.6 	| 0.545 |
37
| newssyscomb2009-huneng.hun.eng 	| 21.3 	| 0.493 |
38
| newstest2009-huneng.hun.eng 	| 20.1 	| 0.487 |
39
| newstest2015-enfi-fineng.fin.eng 	| 23.9 	| 0.521 |
40
| newstest2016-enfi-fineng.fin.eng 	| 25.8 	| 0.542 |
41
| newstest2017-enfi-fineng.fin.eng 	| 28.9 	| 0.562 |
42
| newstest2018-enet-esteng.est.eng 	| 27.0 	| 0.552 |
43
| newstest2018-enfi-fineng.fin.eng 	| 21.2 	| 0.492 |
44
| newstest2019-fien-fineng.fin.eng 	| 25.3 	| 0.531 |
45
| newstestB2016-enfi-fineng.fin.eng 	| 21.3 	| 0.500 |
46
| newstestB2017-enfi-fineng.fin.eng 	| 24.4 	| 0.528 |
47
| newstestB2017-fien-fineng.fin.eng 	| 24.4 	| 0.528 |
48
| Tatoeba-test.chm-eng.chm.eng 	| 0.8 	| 0.131 |
49
| Tatoeba-test.est-eng.est.eng 	| 34.5 	| 0.526 |
50
| Tatoeba-test.fin-eng.fin.eng 	| 28.1 	| 0.485 |
51
| Tatoeba-test.fkv-eng.fkv.eng 	| 6.8 	| 0.335 |
52
| Tatoeba-test.hun-eng.hun.eng 	| 25.1 	| 0.452 |
53
| Tatoeba-test.izh-eng.izh.eng 	| 11.6 	| 0.224 |
54
| Tatoeba-test.kom-eng.kom.eng 	| 2.4 	| 0.110 |
55
| Tatoeba-test.krl-eng.krl.eng 	| 18.6 	| 0.365 |
56
| Tatoeba-test.liv-eng.liv.eng 	| 0.5 	| 0.078 |
57
| Tatoeba-test.mdf-eng.mdf.eng 	| 1.5 	| 0.117 |
58
| Tatoeba-test.multi.eng 	| 47.8 	| 0.646 |
59
| Tatoeba-test.myv-eng.myv.eng 	| 0.5 	| 0.101 |
60
| Tatoeba-test.sma-eng.sma.eng 	| 1.2 	| 0.110 |
61
| Tatoeba-test.sme-eng.sme.eng 	| 1.5 	| 0.147 |
62
| Tatoeba-test.udm-eng.udm.eng 	| 1.0 	| 0.130 |
63
64
65
### System Info: 
66
- hf_name: urj-eng
67
68
- source_languages: urj
69
70
- target_languages: eng
71
72
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/urj-eng/README.md
73
74
- original_repo: Tatoeba-Challenge
75
76
- tags: ['translation']
77
78
- languages: ['se', 'fi', 'hu', 'et', 'urj', 'en']
79
80
- src_constituents: {'izh', 'mdf', 'vep', 'vro', 'sme', 'myv', 'fkv_Latn', 'krl', 'fin', 'hun', 'kpv', 'udm', 'liv_Latn', 'est', 'mhr', 'sma'}
81
82
- tgt_constituents: {'eng'}
83
84
- src_multilingual: True
85
86
- tgt_multilingual: False
87
88
- prepro:  normalization + SentencePiece (spm32k,spm32k)
89
90
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/urj-eng/opus2m-2020-08-01.zip
91
92
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/urj-eng/opus2m-2020-08-01.test.txt
93
94
- src_alpha3: urj
95
96
- tgt_alpha3: eng
97
98
- short_pair: urj-en
99
100
- chrF2_score: 0.6459999999999999
101
102
- bleu: 47.8
103
104
- brevity_penalty: 0.993
105
106
- ref_len: 70882.0
107
108
- src_name: Uralic languages
109
110
- tgt_name: English
111
112
- train_date: 2020-08-01
113
114
- src_alpha2: urj
115
116
- tgt_alpha2: en
117
118
- prefer_old: False
119
120
- long_pair: urj-eng
121
122
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
123
124
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
125
126
- port_machine: brutasse
127
128
- port_time: 2020-08-21-14:41