system HF staff commited on
Commit
cdb0131
1 Parent(s): 09e3c71

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +114 -0
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-poz
10
+
11
+ * source group: English
12
+ * target group: Malayo-Polynesian languages
13
+ * OPUS readme: [eng-poz](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-poz/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): akl_Latn ceb cha dtp fij gil haw hil iba ilo ind jav jav_Java lkt mad mah max_Latn min mlg mri nau niu pag pau rap smo sun tah tet tmw_Latn ton tvl war zlm_Latn zsm_Latn
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: [opus-2020-07-27.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-poz/opus-2020-07-27.zip)
22
+ * test set translations: [opus-2020-07-27.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-poz/opus-2020-07-27.test.txt)
23
+ * test set scores: [opus-2020-07-27.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-poz/opus-2020-07-27.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.eng-akl.eng.akl | 1.3 | 0.086 |
30
+ | Tatoeba-test.eng-ceb.eng.ceb | 10.2 | 0.426 |
31
+ | Tatoeba-test.eng-cha.eng.cha | 1.9 | 0.196 |
32
+ | Tatoeba-test.eng-dtp.eng.dtp | 0.4 | 0.121 |
33
+ | Tatoeba-test.eng-fij.eng.fij | 31.0 | 0.463 |
34
+ | Tatoeba-test.eng-gil.eng.gil | 45.4 | 0.635 |
35
+ | Tatoeba-test.eng-haw.eng.haw | 0.6 | 0.104 |
36
+ | Tatoeba-test.eng-hil.eng.hil | 14.4 | 0.498 |
37
+ | Tatoeba-test.eng-iba.eng.iba | 17.4 | 0.414 |
38
+ | Tatoeba-test.eng-ilo.eng.ilo | 33.1 | 0.585 |
39
+ | Tatoeba-test.eng-jav.eng.jav | 6.5 | 0.309 |
40
+ | Tatoeba-test.eng-lkt.eng.lkt | 0.5 | 0.065 |
41
+ | Tatoeba-test.eng-mad.eng.mad | 1.7 | 0.156 |
42
+ | Tatoeba-test.eng-mah.eng.mah | 12.7 | 0.391 |
43
+ | Tatoeba-test.eng-mlg.eng.mlg | 30.3 | 0.504 |
44
+ | Tatoeba-test.eng-mri.eng.mri | 8.2 | 0.316 |
45
+ | Tatoeba-test.eng-msa.eng.msa | 30.4 | 0.561 |
46
+ | Tatoeba-test.eng.multi | 16.2 | 0.410 |
47
+ | Tatoeba-test.eng-nau.eng.nau | 0.6 | 0.087 |
48
+ | Tatoeba-test.eng-niu.eng.niu | 33.2 | 0.482 |
49
+ | Tatoeba-test.eng-pag.eng.pag | 19.4 | 0.555 |
50
+ | Tatoeba-test.eng-pau.eng.pau | 1.0 | 0.124 |
51
+ | Tatoeba-test.eng-rap.eng.rap | 1.4 | 0.090 |
52
+ | Tatoeba-test.eng-smo.eng.smo | 12.9 | 0.407 |
53
+ | Tatoeba-test.eng-sun.eng.sun | 15.5 | 0.364 |
54
+ | Tatoeba-test.eng-tah.eng.tah | 9.5 | 0.295 |
55
+ | Tatoeba-test.eng-tet.eng.tet | 1.2 | 0.146 |
56
+ | Tatoeba-test.eng-ton.eng.ton | 23.7 | 0.484 |
57
+ | Tatoeba-test.eng-tvl.eng.tvl | 32.5 | 0.549 |
58
+ | Tatoeba-test.eng-war.eng.war | 12.6 | 0.432 |
59
+
60
+
61
+ ### System Info:
62
+ - hf_name: eng-poz
63
+
64
+ - source_languages: eng
65
+
66
+ - target_languages: poz
67
+
68
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-poz/README.md
69
+
70
+ - original_repo: Tatoeba-Challenge
71
+
72
+ - tags: ['translation']
73
+
74
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
75
+
76
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-poz/opus-2020-07-27.zip
77
+
78
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-poz/opus-2020-07-27.test.txt
79
+
80
+ - src_alpha3: eng
81
+
82
+ - tgt_alpha3: poz
83
+
84
+ - short_pair: en-poz
85
+
86
+ - chrF2_score: 0.41
87
+
88
+ - bleu: 16.2
89
+
90
+ - brevity_penalty: 1.0
91
+
92
+ - ref_len: 66803.0
93
+
94
+ - src_name: English
95
+
96
+ - tgt_name: Malayo-Polynesian languages
97
+
98
+ - train_date: 2020-07-27
99
+
100
+ - src_alpha2: en
101
+
102
+ - tgt_alpha2: poz
103
+
104
+ - prefer_old: False
105
+
106
+ - long_pair: eng-poz
107
+
108
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
109
+
110
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
111
+
112
+ - port_machine: brutasse
113
+
114
+ - port_time: 2020-08-18-01:48