system HF staff commited on
Commit
bbf610b
1 Parent(s): 1cc65b5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-cpf
10
+
11
+ * source group: English
12
+ * target group: Creoles and pidgins, French‑based
13
+ * OPUS readme: [eng-cpf](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-cpf/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): gcf_Latn hat mfe
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-2020-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpf/opus-2020-07-26.zip)
22
+ * test set translations: [opus-2020-07-26.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpf/opus-2020-07-26.test.txt)
23
+ * test set scores: [opus-2020-07-26.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpf/opus-2020-07-26.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.eng-gcf.eng.gcf | 6.2 | 0.262 |
30
+ | Tatoeba-test.eng-hat.eng.hat | 25.7 | 0.451 |
31
+ | Tatoeba-test.eng-mfe.eng.mfe | 80.1 | 0.900 |
32
+ | Tatoeba-test.eng.multi | 15.9 | 0.354 |
33
+
34
+
35
+ ### System Info:
36
+ - hf_name: eng-cpf
37
+
38
+ - source_languages: eng
39
+
40
+ - target_languages: cpf
41
+
42
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-cpf/README.md
43
+
44
+ - original_repo: Tatoeba-Challenge
45
+
46
+ - tags: ['translation']
47
+
48
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
49
+
50
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpf/opus-2020-07-26.zip
51
+
52
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-cpf/opus-2020-07-26.test.txt
53
+
54
+ - src_alpha3: eng
55
+
56
+ - tgt_alpha3: cpf
57
+
58
+ - short_pair: en-cpf
59
+
60
+ - chrF2_score: 0.354
61
+
62
+ - bleu: 15.9
63
+
64
+ - brevity_penalty: 1.0
65
+
66
+ - ref_len: 1012.0
67
+
68
+ - src_name: English
69
+
70
+ - tgt_name: Creoles and pidgins, French‑based
71
+
72
+ - train_date: 2020-07-26
73
+
74
+ - src_alpha2: en
75
+
76
+ - tgt_alpha2: cpf
77
+
78
+ - prefer_old: False
79
+
80
+ - long_pair: eng-cpf
81
+
82
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
83
+
84
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
85
+
86
+ - port_machine: brutasse
87
+
88
+ - port_time: 2020-08-18-01:48