system HF staff commited on
Commit
eec33bd
1 Parent(s): 0aec6e2

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: trk
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### trk-eng
10
+
11
+ * source group: Turkic languages
12
+ * target group: English
13
+ * OPUS readme: [trk-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/trk-eng/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): aze_Latn bak chv crh crh_Latn kaz_Cyrl kaz_Latn kir_Cyrl kjh kum ota_Arab ota_Latn sah tat tat_Arab tat_Latn tuk tuk_Latn tur tyv uig_Arab uig_Cyrl uzb_Cyrl uzb_Latn
17
+ * target language(s): eng
18
+ * model: transformer
19
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
20
+ * download original weights: [opus2m-2020-08-01.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/trk-eng/opus2m-2020-08-01.zip)
21
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/trk-eng/opus2m-2020-08-01.test.txt)
22
+ * test set scores: [opus2m-2020-08-01.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/trk-eng/opus2m-2020-08-01.eval.txt)
23
+
24
+ ## Benchmarks
25
+
26
+ | testset | BLEU | chr-F |
27
+ |-----------------------|-------|-------|
28
+ | newsdev2016-entr-tureng.tur.eng | 5.0 | 0.242 |
29
+ | newstest2016-entr-tureng.tur.eng | 3.7 | 0.231 |
30
+ | newstest2017-entr-tureng.tur.eng | 3.7 | 0.229 |
31
+ | newstest2018-entr-tureng.tur.eng | 4.1 | 0.230 |
32
+ | Tatoeba-test.aze-eng.aze.eng | 15.1 | 0.330 |
33
+ | Tatoeba-test.bak-eng.bak.eng | 3.3 | 0.185 |
34
+ | Tatoeba-test.chv-eng.chv.eng | 1.3 | 0.161 |
35
+ | Tatoeba-test.crh-eng.crh.eng | 10.8 | 0.325 |
36
+ | Tatoeba-test.kaz-eng.kaz.eng | 9.6 | 0.264 |
37
+ | Tatoeba-test.kir-eng.kir.eng | 15.3 | 0.328 |
38
+ | Tatoeba-test.kjh-eng.kjh.eng | 1.8 | 0.121 |
39
+ | Tatoeba-test.kum-eng.kum.eng | 16.1 | 0.277 |
40
+ | Tatoeba-test.multi.eng | 12.0 | 0.304 |
41
+ | Tatoeba-test.ota-eng.ota.eng | 2.0 | 0.149 |
42
+ | Tatoeba-test.sah-eng.sah.eng | 0.7 | 0.140 |
43
+ | Tatoeba-test.tat-eng.tat.eng | 4.0 | 0.215 |
44
+ | Tatoeba-test.tuk-eng.tuk.eng | 5.5 | 0.243 |
45
+ | Tatoeba-test.tur-eng.tur.eng | 26.8 | 0.443 |
46
+ | Tatoeba-test.tyv-eng.tyv.eng | 1.3 | 0.111 |
47
+ | Tatoeba-test.uig-eng.uig.eng | 0.2 | 0.111 |
48
+ | Tatoeba-test.uzb-eng.uzb.eng | 4.6 | 0.195 |
49
+
50
+
51
+ ### System Info:
52
+ - hf_name: trk-eng
53
+
54
+ - source_languages: trk
55
+
56
+ - target_languages: eng
57
+
58
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/trk-eng/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/trk-eng/opus2m-2020-08-01.zip
67
+
68
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/trk-eng/opus2m-2020-08-01.test.txt
69
+
70
+ - src_alpha3: trk
71
+
72
+ - tgt_alpha3: eng
73
+
74
+ - short_pair: trk-en
75
+
76
+ - chrF2_score: 0.304
77
+
78
+ - bleu: 12.0
79
+
80
+ - brevity_penalty: 1.0
81
+
82
+ - ref_len: 18733.0
83
+
84
+ - src_name: Turkic languages
85
+
86
+ - tgt_name: English
87
+
88
+ - train_date: 2020-08-01
89
+
90
+ - src_alpha2: trk
91
+
92
+ - tgt_alpha2: en
93
+
94
+ - prefer_old: False
95
+
96
+ - long_pair: trk-eng
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