Update README.md
Browse files
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: urj
|
3 |
+
tags:
|
4 |
+
- translation
|
5 |
+
|
6 |
+
license: apache-2.0
|
7 |
+
---
|
8 |
+
|
9 |
+
### urj-eng
|
10 |
+
|
11 |
+
* source group: Uralic languages
|
12 |
+
* target group: English
|
13 |
+
* OPUS readme: [urj-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/urj-eng/README.md)
|
14 |
+
|
15 |
+
* model: transformer
|
16 |
+
* source language(s): est fin fkv_Latn hun izh kpv krl liv_Latn mdf mhr myv sma sme udm vro
|
17 |
+
* target language(s): eng
|
18 |
+
* model: transformer
|
19 |
+
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
|
20 |
+
* download original weights: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/urj-eng/opus2m-2020-08-01.zip)
|
21 |
+
* 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)
|
22 |
+
* 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)
|
23 |
+
|
24 |
+
## Benchmarks
|
25 |
+
|
26 |
+
| testset | BLEU | chr-F |
|
27 |
+
|-----------------------|-------|-------|
|
28 |
+
| newsdev2015-enfi-fineng.fin.eng | 22.7 | 0.511 |
|
29 |
+
| newsdev2018-enet-esteng.est.eng | 26.6 | 0.545 |
|
30 |
+
| newssyscomb2009-huneng.hun.eng | 21.3 | 0.493 |
|
31 |
+
| newstest2009-huneng.hun.eng | 20.1 | 0.487 |
|
32 |
+
| newstest2015-enfi-fineng.fin.eng | 23.9 | 0.521 |
|
33 |
+
| newstest2016-enfi-fineng.fin.eng | 25.8 | 0.542 |
|
34 |
+
| newstest2017-enfi-fineng.fin.eng | 28.9 | 0.562 |
|
35 |
+
| newstest2018-enet-esteng.est.eng | 27.0 | 0.552 |
|
36 |
+
| newstest2018-enfi-fineng.fin.eng | 21.2 | 0.492 |
|
37 |
+
| newstest2019-fien-fineng.fin.eng | 25.3 | 0.531 |
|
38 |
+
| newstestB2016-enfi-fineng.fin.eng | 21.3 | 0.500 |
|
39 |
+
| newstestB2017-enfi-fineng.fin.eng | 24.4 | 0.528 |
|
40 |
+
| newstestB2017-fien-fineng.fin.eng | 24.4 | 0.528 |
|
41 |
+
| Tatoeba-test.chm-eng.chm.eng | 0.8 | 0.131 |
|
42 |
+
| Tatoeba-test.est-eng.est.eng | 34.5 | 0.526 |
|
43 |
+
| Tatoeba-test.fin-eng.fin.eng | 28.1 | 0.485 |
|
44 |
+
| Tatoeba-test.fkv-eng.fkv.eng | 6.8 | 0.335 |
|
45 |
+
| Tatoeba-test.hun-eng.hun.eng | 25.1 | 0.452 |
|
46 |
+
| Tatoeba-test.izh-eng.izh.eng | 11.6 | 0.224 |
|
47 |
+
| Tatoeba-test.kom-eng.kom.eng | 2.4 | 0.110 |
|
48 |
+
| Tatoeba-test.krl-eng.krl.eng | 18.6 | 0.365 |
|
49 |
+
| Tatoeba-test.liv-eng.liv.eng | 0.5 | 0.078 |
|
50 |
+
| Tatoeba-test.mdf-eng.mdf.eng | 1.5 | 0.117 |
|
51 |
+
| Tatoeba-test.multi.eng | 47.8 | 0.646 |
|
52 |
+
| Tatoeba-test.myv-eng.myv.eng | 0.5 | 0.101 |
|
53 |
+
| Tatoeba-test.sma-eng.sma.eng | 1.2 | 0.110 |
|
54 |
+
| Tatoeba-test.sme-eng.sme.eng | 1.5 | 0.147 |
|
55 |
+
| Tatoeba-test.udm-eng.udm.eng | 1.0 | 0.130 |
|
56 |
+
|
57 |
+
|
58 |
+
### System Info:
|
59 |
+
- hf_name: urj-eng
|
60 |
+
|
61 |
+
- source_languages: urj
|
62 |
+
|
63 |
+
- target_languages: eng
|
64 |
+
|
65 |
+
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/urj-eng/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/urj-eng/opus2m-2020-08-01.zip
|
74 |
+
|
75 |
+
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/urj-eng/opus2m-2020-08-01.test.txt
|
76 |
+
|
77 |
+
- src_alpha3: urj
|
78 |
+
|
79 |
+
- tgt_alpha3: eng
|
80 |
+
|
81 |
+
- short_pair: urj-en
|
82 |
+
|
83 |
+
- chrF2_score: 0.6459999999999999
|
84 |
+
|
85 |
+
- bleu: 47.8
|
86 |
+
|
87 |
+
- brevity_penalty: 0.993
|
88 |
+
|
89 |
+
- ref_len: 70882.0
|
90 |
+
|
91 |
+
- src_name: Uralic languages
|
92 |
+
|
93 |
+
- tgt_name: English
|
94 |
+
|
95 |
+
- train_date: 2020-08-01
|
96 |
+
|
97 |
+
- src_alpha2: urj
|
98 |
+
|
99 |
+
- tgt_alpha2: en
|
100 |
+
|
101 |
+
- prefer_old: False
|
102 |
+
|
103 |
+
- long_pair: urj-eng
|
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
|