README.md
2.4 KB · 104 lines · markdown Raw
1 ---
2 language:
3 - es
4 - en
5
6 tags:
7 - translation
8
9 license: apache-2.0
10 ---
11
12 ### spa-eng
13
14 * source group: Spanish
15 * target group: English
16 * OPUS readme: [spa-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/spa-eng/README.md)
17
18 * model: transformer
19 * source language(s): spa
20 * target language(s): eng
21 * model: transformer
22 * pre-processing: normalization + SentencePiece (spm32k,spm32k)
23 * download original weights: [opus-2020-08-18.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.zip)
24 * test set translations: [opus-2020-08-18.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.test.txt)
25 * test set scores: [opus-2020-08-18.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.eval.txt)
26
27 ## Benchmarks
28
29 | testset | BLEU | chr-F |
30 |-----------------------|-------|-------|
31 | newssyscomb2009-spaeng.spa.eng | 30.6 | 0.570 |
32 | news-test2008-spaeng.spa.eng | 27.9 | 0.553 |
33 | newstest2009-spaeng.spa.eng | 30.4 | 0.572 |
34 | newstest2010-spaeng.spa.eng | 36.1 | 0.614 |
35 | newstest2011-spaeng.spa.eng | 34.2 | 0.599 |
36 | newstest2012-spaeng.spa.eng | 37.9 | 0.624 |
37 | newstest2013-spaeng.spa.eng | 35.3 | 0.609 |
38 | Tatoeba-test.spa.eng | 59.6 | 0.739 |
39
40
41 ### System Info:
42 - hf_name: spa-eng
43
44 - source_languages: spa
45
46 - target_languages: eng
47
48 - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/spa-eng/README.md
49
50 - original_repo: Tatoeba-Challenge
51
52 - tags: ['translation']
53
54 - languages: ['es', 'en']
55
56 - src_constituents: {'spa'}
57
58 - tgt_constituents: {'eng'}
59
60 - src_multilingual: False
61
62 - tgt_multilingual: False
63
64 - prepro: normalization + SentencePiece (spm32k,spm32k)
65
66 - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.zip
67
68 - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/spa-eng/opus-2020-08-18.test.txt
69
70 - src_alpha3: spa
71
72 - tgt_alpha3: eng
73
74 - short_pair: es-en
75
76 - chrF2_score: 0.7390000000000001
77
78 - bleu: 59.6
79
80 - brevity_penalty: 0.9740000000000001
81
82 - ref_len: 79376.0
83
84 - src_name: Spanish
85
86 - tgt_name: English
87
88 - train_date: 2020-08-18 00:00:00
89
90 - src_alpha2: es
91
92 - tgt_alpha2: en
93
94 - prefer_old: False
95
96 - long_pair: spa-eng
97
98 - helsinki_git_sha: d2f0910c89026c34a44e331e785dec1e0faa7b82
99
100 - transformers_git_sha: f7af09b4524b784d67ae8526f0e2fcc6f5ed0de9
101
102 - port_machine: brutasse
103
104 - port_time: 2020-08-24-18:20