system HF staff commited on
Commit
6dab5a7
1 Parent(s): 2853742

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-bat
10
+
11
+ * source group: English
12
+ * target group: Baltic languages
13
+ * OPUS readme: [eng-bat](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-bat/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): lav lit ltg prg_Latn sgs
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-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-bat/opus2m-2020-08-01.zip)
22
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-bat/opus2m-2020-08-01.test.txt)
23
+ * test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-bat/opus2m-2020-08-01.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | newsdev2017-enlv-englav.eng.lav | 24.0 | 0.546 |
30
+ | newsdev2019-enlt-englit.eng.lit | 20.9 | 0.533 |
31
+ | newstest2017-enlv-englav.eng.lav | 18.3 | 0.506 |
32
+ | newstest2019-enlt-englit.eng.lit | 13.6 | 0.466 |
33
+ | Tatoeba-test.eng-lav.eng.lav | 42.8 | 0.652 |
34
+ | Tatoeba-test.eng-lit.eng.lit | 37.1 | 0.650 |
35
+ | Tatoeba-test.eng.multi | 37.0 | 0.616 |
36
+ | Tatoeba-test.eng-prg.eng.prg | 0.5 | 0.130 |
37
+ | Tatoeba-test.eng-sgs.eng.sgs | 4.1 | 0.178 |
38
+
39
+
40
+ ### System Info:
41
+ - hf_name: eng-bat
42
+
43
+ - source_languages: eng
44
+
45
+ - target_languages: bat
46
+
47
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-bat/README.md
48
+
49
+ - original_repo: Tatoeba-Challenge
50
+
51
+ - tags: ['translation']
52
+
53
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
54
+
55
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-bat/opus2m-2020-08-01.zip
56
+
57
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-bat/opus2m-2020-08-01.test.txt
58
+
59
+ - src_alpha3: eng
60
+
61
+ - tgt_alpha3: bat
62
+
63
+ - short_pair: en-bat
64
+
65
+ - chrF2_score: 0.616
66
+
67
+ - bleu: 37.0
68
+
69
+ - brevity_penalty: 0.956
70
+
71
+ - ref_len: 26417.0
72
+
73
+ - src_name: English
74
+
75
+ - tgt_name: Baltic languages
76
+
77
+ - train_date: 2020-08-01
78
+
79
+ - src_alpha2: en
80
+
81
+ - tgt_alpha2: bat
82
+
83
+ - prefer_old: False
84
+
85
+ - long_pair: eng-bat
86
+
87
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
88
+
89
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
90
+
91
+ - port_machine: brutasse
92
+
93
+ - port_time: 2020-08-18-01:48