VaishalBusiness commited on
Commit
8bd1d9f
·
verified ·
1 Parent(s): 3c0801a

Add README.md for Helsinki-NLP-opus-mt-aav-en

Browse files
Files changed (1) hide show
  1. Helsinki-NLP-opus-mt-aav-en/README.md +104 -0
Helsinki-NLP-opus-mt-aav-en/README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - vi
4
+ - km
5
+ - aav
6
+ - en
7
+
8
+ tags:
9
+ - translation
10
+
11
+ license: apache-2.0
12
+ ---
13
+
14
+ ### aav-eng
15
+
16
+ * source group: Austro-Asiatic languages
17
+ * target group: English
18
+ * OPUS readme: [aav-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/aav-eng/README.md)
19
+
20
+ * model: transformer
21
+ * source language(s): hoc hoc_Latn kha khm khm_Latn mnw vie vie_Hani
22
+ * target language(s): eng
23
+ * model: transformer
24
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
25
+ * download original weights: [opus2m-2020-07-31.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/aav-eng/opus2m-2020-07-31.zip)
26
+ * test set translations: [opus2m-2020-07-31.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/aav-eng/opus2m-2020-07-31.test.txt)
27
+ * test set scores: [opus2m-2020-07-31.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/aav-eng/opus2m-2020-07-31.eval.txt)
28
+
29
+ ## Benchmarks
30
+
31
+ | testset | BLEU | chr-F |
32
+ |-----------------------|-------|-------|
33
+ | Tatoeba-test.hoc-eng.hoc.eng | 0.3 | 0.095 |
34
+ | Tatoeba-test.kha-eng.kha.eng | 1.0 | 0.115 |
35
+ | Tatoeba-test.khm-eng.khm.eng | 8.9 | 0.271 |
36
+ | Tatoeba-test.mnw-eng.mnw.eng | 0.8 | 0.118 |
37
+ | Tatoeba-test.multi.eng | 24.8 | 0.391 |
38
+ | Tatoeba-test.vie-eng.vie.eng | 38.7 | 0.567 |
39
+
40
+
41
+ ### System Info:
42
+ - hf_name: aav-eng
43
+
44
+ - source_languages: aav
45
+
46
+ - target_languages: eng
47
+
48
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/aav-eng/README.md
49
+
50
+ - original_repo: Tatoeba-Challenge
51
+
52
+ - tags: ['translation']
53
+
54
+ - languages: ['vi', 'km', 'aav', 'en']
55
+
56
+ - src_constituents: {'mnw', 'vie', 'kha', 'khm', 'vie_Hani', 'khm_Latn', 'hoc_Latn', 'hoc'}
57
+
58
+ - tgt_constituents: {'eng'}
59
+
60
+ - src_multilingual: True
61
+
62
+ - tgt_multilingual: False
63
+
64
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
65
+
66
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/aav-eng/opus2m-2020-07-31.zip
67
+
68
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/aav-eng/opus2m-2020-07-31.test.txt
69
+
70
+ - src_alpha3: aav
71
+
72
+ - tgt_alpha3: eng
73
+
74
+ - short_pair: aav-en
75
+
76
+ - chrF2_score: 0.391
77
+
78
+ - bleu: 24.8
79
+
80
+ - brevity_penalty: 0.968
81
+
82
+ - ref_len: 36693.0
83
+
84
+ - src_name: Austro-Asiatic languages
85
+
86
+ - tgt_name: English
87
+
88
+ - train_date: 2020-07-31
89
+
90
+ - src_alpha2: aav
91
+
92
+ - tgt_alpha2: en
93
+
94
+ - prefer_old: False
95
+
96
+ - long_pair: aav-eng
97
+
98
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
99
+
100
+ - transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
101
+
102
+ - port_machine: brutasse
103
+
104
+ - port_time: 2020-08-21-14:41