system HF staff commited on
Commit
b94bce1
1 Parent(s): aabe87a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: cpp
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### cpp-eng
10
+
11
+ * source group: Creoles and pidgins, Portuguese-based
12
+ * target group: English
13
+ * OPUS readme: [cpp-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cpp-eng/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): ind max_Latn min pap tmw_Latn zlm_Latn zsm_Latn
17
+ * target language(s): eng
18
+ * model: transformer
19
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
20
+ * download original weights: [opus2m-2020-07-31.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-eng/opus2m-2020-07-31.zip)
21
+ * test set translations: [opus2m-2020-07-31.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-eng/opus2m-2020-07-31.test.txt)
22
+ * test set scores: [opus2m-2020-07-31.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-eng/opus2m-2020-07-31.eval.txt)
23
+
24
+ ## Benchmarks
25
+
26
+ | testset | BLEU | chr-F |
27
+ |-----------------------|-------|-------|
28
+ | Tatoeba-test.msa-eng.msa.eng | 39.6 | 0.580 |
29
+ | Tatoeba-test.multi.eng | 39.7 | 0.580 |
30
+ | Tatoeba-test.pap-eng.pap.eng | 49.1 | 0.579 |
31
+
32
+
33
+ ### System Info:
34
+ - hf_name: cpp-eng
35
+
36
+ - source_languages: cpp
37
+
38
+ - target_languages: eng
39
+
40
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cpp-eng/README.md
41
+
42
+ - original_repo: Tatoeba-Challenge
43
+
44
+ - tags: ['translation']
45
+
46
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
47
+
48
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-eng/opus2m-2020-07-31.zip
49
+
50
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-eng/opus2m-2020-07-31.test.txt
51
+
52
+ - src_alpha3: cpp
53
+
54
+ - tgt_alpha3: eng
55
+
56
+ - short_pair: cpp-en
57
+
58
+ - chrF2_score: 0.58
59
+
60
+ - bleu: 39.7
61
+
62
+ - brevity_penalty: 0.972
63
+
64
+ - ref_len: 37399.0
65
+
66
+ - src_name: Creoles and pidgins, Portuguese-based
67
+
68
+ - tgt_name: English
69
+
70
+ - train_date: 2020-07-31
71
+
72
+ - src_alpha2: cpp
73
+
74
+ - tgt_alpha2: en
75
+
76
+ - prefer_old: False
77
+
78
+ - long_pair: cpp-eng
79
+
80
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
81
+
82
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
83
+
84
+ - port_machine: brutasse
85
+
86
+ - port_time: 2020-08-18-01:48