system HF staff commited on
Commit
29990a6
1 Parent(s): ab791a9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +111 -0
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-urj
10
+
11
+ * source group: English
12
+ * target group: Uralic languages
13
+ * OPUS readme: [eng-urj](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-urj/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): est fin fkv_Latn hun izh kpv krl liv_Latn mdf mhr myv sma sme udm vro
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-2020-08-02.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urj/opus2m-2020-08-02.zip)
22
+ * test set translations: [opus2m-2020-08-02.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urj/opus2m-2020-08-02.test.txt)
23
+ * test set scores: [opus2m-2020-08-02.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urj/opus2m-2020-08-02.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | newsdev2015-enfi-engfin.eng.fin | 18.3 | 0.519 |
30
+ | newsdev2018-enet-engest.eng.est | 19.3 | 0.520 |
31
+ | newssyscomb2009-enghun.eng.hun | 15.4 | 0.471 |
32
+ | newstest2009-enghun.eng.hun | 15.7 | 0.468 |
33
+ | newstest2015-enfi-engfin.eng.fin | 20.2 | 0.534 |
34
+ | newstest2016-enfi-engfin.eng.fin | 20.7 | 0.541 |
35
+ | newstest2017-enfi-engfin.eng.fin | 23.6 | 0.566 |
36
+ | newstest2018-enet-engest.eng.est | 20.8 | 0.535 |
37
+ | newstest2018-enfi-engfin.eng.fin | 15.8 | 0.499 |
38
+ | newstest2019-enfi-engfin.eng.fin | 19.9 | 0.518 |
39
+ | newstestB2016-enfi-engfin.eng.fin | 16.6 | 0.509 |
40
+ | newstestB2017-enfi-engfin.eng.fin | 19.4 | 0.529 |
41
+ | Tatoeba-test.eng-chm.eng.chm | 1.3 | 0.127 |
42
+ | Tatoeba-test.eng-est.eng.est | 51.0 | 0.692 |
43
+ | Tatoeba-test.eng-fin.eng.fin | 34.6 | 0.597 |
44
+ | Tatoeba-test.eng-fkv.eng.fkv | 2.2 | 0.302 |
45
+ | Tatoeba-test.eng-hun.eng.hun | 35.6 | 0.591 |
46
+ | Tatoeba-test.eng-izh.eng.izh | 5.7 | 0.211 |
47
+ | Tatoeba-test.eng-kom.eng.kom | 3.0 | 0.012 |
48
+ | Tatoeba-test.eng-krl.eng.krl | 8.5 | 0.230 |
49
+ | Tatoeba-test.eng-liv.eng.liv | 2.7 | 0.077 |
50
+ | Tatoeba-test.eng-mdf.eng.mdf | 2.8 | 0.007 |
51
+ | Tatoeba-test.eng.multi | 35.1 | 0.588 |
52
+ | Tatoeba-test.eng-myv.eng.myv | 1.3 | 0.014 |
53
+ | Tatoeba-test.eng-sma.eng.sma | 1.8 | 0.095 |
54
+ | Tatoeba-test.eng-sme.eng.sme | 6.8 | 0.204 |
55
+ | Tatoeba-test.eng-udm.eng.udm | 1.1 | 0.121 |
56
+
57
+
58
+ ### System Info:
59
+ - hf_name: eng-urj
60
+
61
+ - source_languages: eng
62
+
63
+ - target_languages: urj
64
+
65
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-urj/README.md
66
+
67
+ - original_repo: Tatoeba-Challenge
68
+
69
+ - tags: ['translation']
70
+
71
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
72
+
73
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urj/opus2m-2020-08-02.zip
74
+
75
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urj/opus2m-2020-08-02.test.txt
76
+
77
+ - src_alpha3: eng
78
+
79
+ - tgt_alpha3: urj
80
+
81
+ - short_pair: en-urj
82
+
83
+ - chrF2_score: 0.588
84
+
85
+ - bleu: 35.1
86
+
87
+ - brevity_penalty: 0.943
88
+
89
+ - ref_len: 59664.0
90
+
91
+ - src_name: English
92
+
93
+ - tgt_name: Uralic languages
94
+
95
+ - train_date: 2020-08-02
96
+
97
+ - src_alpha2: en
98
+
99
+ - tgt_alpha2: urj
100
+
101
+ - prefer_old: False
102
+
103
+ - long_pair: eng-urj
104
+
105
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
106
+
107
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
108
+
109
+ - port_machine: brutasse
110
+
111
+ - port_time: 2020-08-18-01:48