system HF staff commited on
Commit
4b8956f
1 Parent(s): 7cf63ea

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: ja
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### jpn-msa
10
+
11
+ * source group: Japanese
12
+ * target group: Malay (macrolanguage)
13
+ * OPUS readme: [jpn-msa](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/jpn-msa/README.md)
14
+
15
+ * model: transformer-align
16
+ * source language(s): jpn jpn_Hani jpn_Hira jpn_Kana
17
+ * target language(s): ind zlm_Latn zsm_Latn
18
+ * model: transformer-align
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: [opus-2020-06-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/jpn-msa/opus-2020-06-17.zip)
22
+ * test set translations: [opus-2020-06-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/jpn-msa/opus-2020-06-17.test.txt)
23
+ * test set scores: [opus-2020-06-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/jpn-msa/opus-2020-06-17.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.jpn.msa | 21.5 | 0.469 |
30
+
31
+
32
+ ### System Info:
33
+ - hf_name: jpn-msa
34
+
35
+ - source_languages: jpn
36
+
37
+ - target_languages: msa
38
+
39
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/jpn-msa/README.md
40
+
41
+ - original_repo: Tatoeba-Challenge
42
+
43
+ - tags: ['translation']
44
+
45
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
46
+
47
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/jpn-msa/opus-2020-06-17.zip
48
+
49
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/jpn-msa/opus-2020-06-17.test.txt
50
+
51
+ - src_alpha3: jpn
52
+
53
+ - tgt_alpha3: msa
54
+
55
+ - short_pair: ja-ms
56
+
57
+ - chrF2_score: 0.469
58
+
59
+ - bleu: 21.5
60
+
61
+ - brevity_penalty: 0.9259999999999999
62
+
63
+ - ref_len: 17028.0
64
+
65
+ - src_name: Japanese
66
+
67
+ - tgt_name: Malay (macrolanguage)
68
+
69
+ - train_date: 2020-06-17
70
+
71
+ - src_alpha2: ja
72
+
73
+ - tgt_alpha2: ms
74
+
75
+ - prefer_old: False
76
+
77
+ - long_pair: jpn-msa
78
+
79
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
80
+
81
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
82
+
83
+ - port_machine: brutasse
84
+
85
+ - port_time: 2020-08-18-01:48