system HF staff commited on
Commit
c8149ef
1 Parent(s): 79417e3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-alv
10
+
11
+ * source group: English
12
+ * target group: Atlantic-Congo languages
13
+ * OPUS readme: [eng-alv](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-alv/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): ewe fuc fuv ibo kin lin lug nya run sag sna swh toi_Latn tso umb wol xho yor zul
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-alv/opus2m-2020-08-01.zip)
22
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-alv/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-alv/opus2m-2020-08-01.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.eng-ewe.eng.ewe | 4.9 | 0.212 |
30
+ | Tatoeba-test.eng-ful.eng.ful | 0.6 | 0.079 |
31
+ | Tatoeba-test.eng-ibo.eng.ibo | 3.5 | 0.255 |
32
+ | Tatoeba-test.eng-kin.eng.kin | 10.5 | 0.510 |
33
+ | Tatoeba-test.eng-lin.eng.lin | 1.1 | 0.273 |
34
+ | Tatoeba-test.eng-lug.eng.lug | 5.3 | 0.340 |
35
+ | Tatoeba-test.eng.multi | 11.4 | 0.429 |
36
+ | Tatoeba-test.eng-nya.eng.nya | 18.1 | 0.595 |
37
+ | Tatoeba-test.eng-run.eng.run | 13.9 | 0.484 |
38
+ | Tatoeba-test.eng-sag.eng.sag | 5.3 | 0.194 |
39
+ | Tatoeba-test.eng-sna.eng.sna | 26.2 | 0.623 |
40
+ | Tatoeba-test.eng-swa.eng.swa | 1.0 | 0.141 |
41
+ | Tatoeba-test.eng-toi.eng.toi | 7.0 | 0.224 |
42
+ | Tatoeba-test.eng-tso.eng.tso | 46.7 | 0.643 |
43
+ | Tatoeba-test.eng-umb.eng.umb | 7.8 | 0.359 |
44
+ | Tatoeba-test.eng-wol.eng.wol | 6.8 | 0.191 |
45
+ | Tatoeba-test.eng-xho.eng.xho | 27.1 | 0.629 |
46
+ | Tatoeba-test.eng-yor.eng.yor | 17.4 | 0.356 |
47
+ | Tatoeba-test.eng-zul.eng.zul | 34.1 | 0.729 |
48
+
49
+
50
+ ### System Info:
51
+ - hf_name: eng-alv
52
+
53
+ - source_languages: eng
54
+
55
+ - target_languages: alv
56
+
57
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-alv/README.md
58
+
59
+ - original_repo: Tatoeba-Challenge
60
+
61
+ - tags: ['translation']
62
+
63
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
64
+
65
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-alv/opus2m-2020-08-01.zip
66
+
67
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-alv/opus2m-2020-08-01.test.txt
68
+
69
+ - src_alpha3: eng
70
+
71
+ - tgt_alpha3: alv
72
+
73
+ - short_pair: en-alv
74
+
75
+ - chrF2_score: 0.429
76
+
77
+ - bleu: 11.4
78
+
79
+ - brevity_penalty: 1.0
80
+
81
+ - ref_len: 10603.0
82
+
83
+ - src_name: English
84
+
85
+ - tgt_name: Atlantic-Congo languages
86
+
87
+ - train_date: 2020-08-01
88
+
89
+ - src_alpha2: en
90
+
91
+ - tgt_alpha2: alv
92
+
93
+ - prefer_old: False
94
+
95
+ - long_pair: eng-alv
96
+
97
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
98
+
99
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
100
+
101
+ - port_machine: brutasse
102
+
103
+ - port_time: 2020-08-18-01:48