system HF staff commited on
Commit
89e4668
·
1 Parent(s): fb8838f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +104 -0
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-nic
10
+
11
+ * source group: English
12
+ * target group: Niger-Kordofanian languages
13
+ * OPUS readme: [eng-nic](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-nic/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): bam_Latn 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: [opus-2020-07-27.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nic/opus-2020-07-27.zip)
22
+ * test set translations: [opus-2020-07-27.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nic/opus-2020-07-27.test.txt)
23
+ * test set scores: [opus-2020-07-27.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nic/opus-2020-07-27.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | Tatoeba-test.eng-bam.eng.bam | 6.2 | 0.029 |
30
+ | Tatoeba-test.eng-ewe.eng.ewe | 4.5 | 0.258 |
31
+ | Tatoeba-test.eng-ful.eng.ful | 0.5 | 0.073 |
32
+ | Tatoeba-test.eng-ibo.eng.ibo | 3.9 | 0.267 |
33
+ | Tatoeba-test.eng-kin.eng.kin | 6.4 | 0.475 |
34
+ | Tatoeba-test.eng-lin.eng.lin | 1.2 | 0.308 |
35
+ | Tatoeba-test.eng-lug.eng.lug | 3.9 | 0.405 |
36
+ | Tatoeba-test.eng.multi | 11.1 | 0.427 |
37
+ | Tatoeba-test.eng-nya.eng.nya | 14.0 | 0.622 |
38
+ | Tatoeba-test.eng-run.eng.run | 13.6 | 0.477 |
39
+ | Tatoeba-test.eng-sag.eng.sag | 5.5 | 0.199 |
40
+ | Tatoeba-test.eng-sna.eng.sna | 19.6 | 0.557 |
41
+ | Tatoeba-test.eng-swa.eng.swa | 1.8 | 0.163 |
42
+ | Tatoeba-test.eng-toi.eng.toi | 8.3 | 0.231 |
43
+ | Tatoeba-test.eng-tso.eng.tso | 50.0 | 0.789 |
44
+ | Tatoeba-test.eng-umb.eng.umb | 7.8 | 0.342 |
45
+ | Tatoeba-test.eng-wol.eng.wol | 6.7 | 0.143 |
46
+ | Tatoeba-test.eng-xho.eng.xho | 26.4 | 0.620 |
47
+ | Tatoeba-test.eng-yor.eng.yor | 15.5 | 0.342 |
48
+ | Tatoeba-test.eng-zul.eng.zul | 35.9 | 0.750 |
49
+
50
+
51
+ ### System Info:
52
+ - hf_name: eng-nic
53
+
54
+ - source_languages: eng
55
+
56
+ - target_languages: nic
57
+
58
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-nic/README.md
59
+
60
+ - original_repo: Tatoeba-Challenge
61
+
62
+ - tags: ['translation']
63
+
64
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
65
+
66
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nic/opus-2020-07-27.zip
67
+
68
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-nic/opus-2020-07-27.test.txt
69
+
70
+ - src_alpha3: eng
71
+
72
+ - tgt_alpha3: nic
73
+
74
+ - short_pair: en-nic
75
+
76
+ - chrF2_score: 0.42700000000000005
77
+
78
+ - bleu: 11.1
79
+
80
+ - brevity_penalty: 1.0
81
+
82
+ - ref_len: 10625.0
83
+
84
+ - src_name: English
85
+
86
+ - tgt_name: Niger-Kordofanian languages
87
+
88
+ - train_date: 2020-07-27
89
+
90
+ - src_alpha2: en
91
+
92
+ - tgt_alpha2: nic
93
+
94
+ - prefer_old: False
95
+
96
+ - long_pair: eng-nic
97
+
98
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
99
+
100
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
101
+
102
+ - port_machine: brutasse
103
+
104
+ - port_time: 2020-08-18-01:48