system HF staff commited on
Commit
7545522
1 Parent(s): b632b23

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-map
10
+
11
+ * source group: English
12
+ * target group: Austronesian languages
13
+ * OPUS readme: [eng-map](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-map/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-map/opus-2020-07-27.zip)
22
+ * test set translations: [opus-2020-07-27.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-map/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-map/opus-2020-07-27.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.eng-akl.eng.akl | 2.2 | 0.103 |
30
+ | Tatoeba-test.eng-ceb.eng.ceb | 10.7 | 0.425 |
31
+ | Tatoeba-test.eng-cha.eng.cha | 3.2 | 0.201 |
32
+ | Tatoeba-test.eng-dtp.eng.dtp | 0.5 | 0.120 |
33
+ | Tatoeba-test.eng-fij.eng.fij | 26.8 | 0.453 |
34
+ | Tatoeba-test.eng-gil.eng.gil | 59.3 | 0.762 |
35
+ | Tatoeba-test.eng-haw.eng.haw | 1.0 | 0.116 |
36
+ | Tatoeba-test.eng-hil.eng.hil | 19.0 | 0.517 |
37
+ | Tatoeba-test.eng-iba.eng.iba | 15.5 | 0.400 |
38
+ | Tatoeba-test.eng-ilo.eng.ilo | 33.6 | 0.591 |
39
+ | Tatoeba-test.eng-jav.eng.jav | 7.8 | 0.301 |
40
+ | Tatoeba-test.eng-lkt.eng.lkt | 1.0 | 0.064 |
41
+ | Tatoeba-test.eng-mad.eng.mad | 1.1 | 0.142 |
42
+ | Tatoeba-test.eng-mah.eng.mah | 9.1 | 0.374 |
43
+ | Tatoeba-test.eng-mlg.eng.mlg | 35.4 | 0.526 |
44
+ | Tatoeba-test.eng-mri.eng.mri | 7.6 | 0.309 |
45
+ | Tatoeba-test.eng-msa.eng.msa | 31.1 | 0.565 |
46
+ | Tatoeba-test.eng.multi | 17.6 | 0.411 |
47
+ | Tatoeba-test.eng-nau.eng.nau | 1.4 | 0.098 |
48
+ | Tatoeba-test.eng-niu.eng.niu | 40.1 | 0.560 |
49
+ | Tatoeba-test.eng-pag.eng.pag | 16.8 | 0.526 |
50
+ | Tatoeba-test.eng-pau.eng.pau | 1.9 | 0.139 |
51
+ | Tatoeba-test.eng-rap.eng.rap | 2.7 | 0.090 |
52
+ | Tatoeba-test.eng-smo.eng.smo | 24.9 | 0.453 |
53
+ | Tatoeba-test.eng-sun.eng.sun | 33.2 | 0.439 |
54
+ | Tatoeba-test.eng-tah.eng.tah | 12.5 | 0.278 |
55
+ | Tatoeba-test.eng-tet.eng.tet | 1.6 | 0.140 |
56
+ | Tatoeba-test.eng-ton.eng.ton | 25.8 | 0.530 |
57
+ | Tatoeba-test.eng-tvl.eng.tvl | 31.1 | 0.523 |
58
+ | Tatoeba-test.eng-war.eng.war | 12.8 | 0.436 |
59
+
60
+
61
+ ### System Info:
62
+ - hf_name: eng-map
63
+
64
+ - source_languages: eng
65
+
66
+ - target_languages: map
67
+
68
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-map/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-map/opus-2020-07-27.zip
77
+
78
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-map/opus-2020-07-27.test.txt
79
+
80
+ - src_alpha3: eng
81
+
82
+ - tgt_alpha3: map
83
+
84
+ - short_pair: en-map
85
+
86
+ - chrF2_score: 0.41100000000000003
87
+
88
+ - bleu: 17.6
89
+
90
+ - brevity_penalty: 1.0
91
+
92
+ - ref_len: 66963.0
93
+
94
+ - src_name: English
95
+
96
+ - tgt_name: Austronesian languages
97
+
98
+ - train_date: 2020-07-27
99
+
100
+ - src_alpha2: en
101
+
102
+ - tgt_alpha2: map
103
+
104
+ - prefer_old: False
105
+
106
+ - long_pair: eng-map
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