system HF staff commited on
Commit
b914cbb
1 Parent(s): 647117d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-sem
10
+
11
+ * source group: English
12
+ * target group: Semitic languages
13
+ * OPUS readme: [eng-sem](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-sem/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): acm afb amh apc ara arq ary arz heb mlt tir
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-sem/opus2m-2020-08-01.zip)
22
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sem/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-sem/opus2m-2020-08-01.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.eng-amh.eng.amh | 11.2 | 0.480 |
30
+ | Tatoeba-test.eng-ara.eng.ara | 12.7 | 0.417 |
31
+ | Tatoeba-test.eng-heb.eng.heb | 33.8 | 0.564 |
32
+ | Tatoeba-test.eng-mlt.eng.mlt | 18.7 | 0.554 |
33
+ | Tatoeba-test.eng.multi | 23.5 | 0.486 |
34
+ | Tatoeba-test.eng-tir.eng.tir | 2.7 | 0.248 |
35
+
36
+
37
+ ### System Info:
38
+ - hf_name: eng-sem
39
+
40
+ - source_languages: eng
41
+
42
+ - target_languages: sem
43
+
44
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-sem/README.md
45
+
46
+ - original_repo: Tatoeba-Challenge
47
+
48
+ - tags: ['translation']
49
+
50
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
51
+
52
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sem/opus2m-2020-08-01.zip
53
+
54
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sem/opus2m-2020-08-01.test.txt
55
+
56
+ - src_alpha3: eng
57
+
58
+ - tgt_alpha3: sem
59
+
60
+ - short_pair: en-sem
61
+
62
+ - chrF2_score: 0.486
63
+
64
+ - bleu: 23.5
65
+
66
+ - brevity_penalty: 1.0
67
+
68
+ - ref_len: 59258.0
69
+
70
+ - src_name: English
71
+
72
+ - tgt_name: Semitic languages
73
+
74
+ - train_date: 2020-08-01
75
+
76
+ - src_alpha2: en
77
+
78
+ - tgt_alpha2: sem
79
+
80
+ - prefer_old: False
81
+
82
+ - long_pair: eng-sem
83
+
84
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
85
+
86
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
87
+
88
+ - port_machine: brutasse
89
+
90
+ - port_time: 2020-08-18-01:48