system HF staff commited on
Commit
d7205d4
1 Parent(s): ec2bafb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-pqe
10
+
11
+ * source group: English
12
+ * target group: Eastern Malayo-Polynesian languages
13
+ * OPUS readme: [eng-pqe](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-pqe/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): fij gil haw lkt mah mri nau niu rap smo tah ton tvl
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-pqe/opus2m-2020-08-01.zip)
22
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-pqe/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-pqe/opus2m-2020-08-01.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.eng-fij.eng.fij | 22.1 | 0.396 |
30
+ | Tatoeba-test.eng-gil.eng.gil | 41.9 | 0.673 |
31
+ | Tatoeba-test.eng-haw.eng.haw | 0.6 | 0.114 |
32
+ | Tatoeba-test.eng-lkt.eng.lkt | 0.5 | 0.075 |
33
+ | Tatoeba-test.eng-mah.eng.mah | 9.7 | 0.386 |
34
+ | Tatoeba-test.eng-mri.eng.mri | 7.7 | 0.301 |
35
+ | Tatoeba-test.eng.multi | 11.3 | 0.306 |
36
+ | Tatoeba-test.eng-nau.eng.nau | 0.5 | 0.071 |
37
+ | Tatoeba-test.eng-niu.eng.niu | 42.5 | 0.560 |
38
+ | Tatoeba-test.eng-rap.eng.rap | 3.3 | 0.122 |
39
+ | Tatoeba-test.eng-smo.eng.smo | 27.0 | 0.462 |
40
+ | Tatoeba-test.eng-tah.eng.tah | 11.3 | 0.307 |
41
+ | Tatoeba-test.eng-ton.eng.ton | 27.0 | 0.528 |
42
+ | Tatoeba-test.eng-tvl.eng.tvl | 29.3 | 0.513 |
43
+
44
+
45
+ ### System Info:
46
+ - hf_name: eng-pqe
47
+
48
+ - source_languages: eng
49
+
50
+ - target_languages: pqe
51
+
52
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-pqe/README.md
53
+
54
+ - original_repo: Tatoeba-Challenge
55
+
56
+ - tags: ['translation']
57
+
58
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
59
+
60
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-pqe/opus2m-2020-08-01.zip
61
+
62
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-pqe/opus2m-2020-08-01.test.txt
63
+
64
+ - src_alpha3: eng
65
+
66
+ - tgt_alpha3: pqe
67
+
68
+ - short_pair: en-pqe
69
+
70
+ - chrF2_score: 0.306
71
+
72
+ - bleu: 11.3
73
+
74
+ - brevity_penalty: 1.0
75
+
76
+ - ref_len: 5786.0
77
+
78
+ - src_name: English
79
+
80
+ - tgt_name: Eastern Malayo-Polynesian languages
81
+
82
+ - train_date: 2020-08-01
83
+
84
+ - src_alpha2: en
85
+
86
+ - tgt_alpha2: pqe
87
+
88
+ - prefer_old: False
89
+
90
+ - long_pair: eng-pqe
91
+
92
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
93
+
94
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
95
+
96
+ - port_machine: brutasse
97
+
98
+ - port_time: 2020-08-18-01:48