Hugging Face's logo

Helsinki-NLP
/
opus-mt-itc-en

Translation
Transformers
PyTorch
TensorFlow
17 languages
marian
text2text-generation
Inference Endpoints
Model card Files Community
2
system HF staff commited on
Commit
4899287
•
1 Parent(s): 80aa9bb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +135 -0
README.md ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: itc
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### itc-eng
10
+
11
+ * source group: Italic languages
12
+ * target group: English
13
+ * OPUS readme: [itc-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/itc-eng/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): arg ast cat cos egl ext fra frm_Latn gcf_Latn glg hat ind ita lad lad_Latn lat_Latn lij lld_Latn lmo max_Latn mfe min mwl oci pap pms por roh ron scn spa tmw_Latn vec wln zlm_Latn zsm_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/itc-eng/opus2m-2020-08-01.zip)
21
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/itc-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/itc-eng/opus2m-2020-08-01.eval.txt)
23
+
24
+ ## Benchmarks
25
+
26
+ | testset | BLEU | chr-F |
27
+ |-----------------------|-------|-------|
28
+ | newsdev2016-enro-roneng.ron.eng | 36.5 | 0.628 |
29
+ | newsdiscussdev2015-enfr-fraeng.fra.eng | 30.9 | 0.561 |
30
+ | newsdiscusstest2015-enfr-fraeng.fra.eng | 35.5 | 0.590 |
31
+ | newssyscomb2009-fraeng.fra.eng | 29.2 | 0.560 |
32
+ | newssyscomb2009-itaeng.ita.eng | 32.2 | 0.583 |
33
+ | newssyscomb2009-spaeng.spa.eng | 29.3 | 0.563 |
34
+ | news-test2008-fraeng.fra.eng | 25.2 | 0.531 |
35
+ | news-test2008-spaeng.spa.eng | 26.3 | 0.539 |
36
+ | newstest2009-fraeng.fra.eng | 28.5 | 0.555 |
37
+ | newstest2009-itaeng.ita.eng | 31.6 | 0.578 |
38
+ | newstest2009-spaeng.spa.eng | 28.7 | 0.558 |
39
+ | newstest2010-fraeng.fra.eng | 29.7 | 0.571 |
40
+ | newstest2010-spaeng.spa.eng | 32.8 | 0.593 |
41
+ | newstest2011-fraeng.fra.eng | 30.9 | 0.580 |
42
+ | newstest2011-spaeng.spa.eng | 31.8 | 0.582 |
43
+ | newstest2012-fraeng.fra.eng | 31.1 | 0.576 |
44
+ | newstest2012-spaeng.spa.eng | 35.0 | 0.604 |
45
+ | newstest2013-fraeng.fra.eng | 31.7 | 0.573 |
46
+ | newstest2013-spaeng.spa.eng | 32.4 | 0.589 |
47
+ | newstest2014-fren-fraeng.fra.eng | 34.0 | 0.606 |
48
+ | newstest2016-enro-roneng.ron.eng | 34.8 | 0.608 |
49
+ | Tatoeba-test.arg-eng.arg.eng | 41.5 | 0.528 |
50
+ | Tatoeba-test.ast-eng.ast.eng | 36.0 | 0.519 |
51
+ | Tatoeba-test.cat-eng.cat.eng | 53.7 | 0.696 |
52
+ | Tatoeba-test.cos-eng.cos.eng | 56.5 | 0.640 |
53
+ | Tatoeba-test.egl-eng.egl.eng | 4.6 | 0.217 |
54
+ | Tatoeba-test.ext-eng.ext.eng | 39.1 | 0.547 |
55
+ | Tatoeba-test.fra-eng.fra.eng | 53.4 | 0.688 |
56
+ | Tatoeba-test.frm-eng.frm.eng | 22.3 | 0.409 |
57
+ | Tatoeba-test.gcf-eng.gcf.eng | 18.7 | 0.308 |
58
+ | Tatoeba-test.glg-eng.glg.eng | 54.8 | 0.701 |
59
+ | Tatoeba-test.hat-eng.hat.eng | 42.6 | 0.583 |
60
+ | Tatoeba-test.ita-eng.ita.eng | 64.8 | 0.767 |
61
+ | Tatoeba-test.lad-eng.lad.eng | 14.4 | 0.433 |
62
+ | Tatoeba-test.lat-eng.lat.eng | 19.5 | 0.390 |
63
+ | Tatoeba-test.lij-eng.lij.eng | 8.9 | 0.280 |
64
+ | Tatoeba-test.lld-eng.lld.eng | 17.4 | 0.331 |
65
+ | Tatoeba-test.lmo-eng.lmo.eng | 10.8 | 0.306 |
66
+ | Tatoeba-test.mfe-eng.mfe.eng | 66.0 | 0.820 |
67
+ | Tatoeba-test.msa-eng.msa.eng | 40.8 | 0.590 |
68
+ | Tatoeba-test.multi.eng | 47.6 | 0.634 |
69
+ | Tatoeba-test.mwl-eng.mwl.eng | 41.3 | 0.707 |
70
+ | Tatoeba-test.oci-eng.oci.eng | 20.3 | 0.401 |
71
+ | Tatoeba-test.pap-eng.pap.eng | 53.9 | 0.642 |
72
+ | Tatoeba-test.pms-eng.pms.eng | 12.2 | 0.334 |
73
+ | Tatoeba-test.por-eng.por.eng | 59.3 | 0.734 |
74
+ | Tatoeba-test.roh-eng.roh.eng | 17.7 | 0.420 |
75
+ | Tatoeba-test.ron-eng.ron.eng | 54.5 | 0.697 |
76
+ | Tatoeba-test.scn-eng.scn.eng | 40.0 | 0.443 |
77
+ | Tatoeba-test.spa-eng.spa.eng | 55.9 | 0.712 |
78
+ | Tatoeba-test.vec-eng.vec.eng | 11.2 | 0.304 |
79
+ | Tatoeba-test.wln-eng.wln.eng | 20.9 | 0.360 |
80
+
81
+
82
+ ### System Info:
83
+ - hf_name: itc-eng
84
+
85
+ - source_languages: itc
86
+
87
+ - target_languages: eng
88
+
89
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/itc-eng/README.md
90
+
91
+ - original_repo: Tatoeba-Challenge
92
+
93
+ - tags: ['translation']
94
+
95
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
96
+
97
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/itc-eng/opus2m-2020-08-01.zip
98
+
99
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/itc-eng/opus2m-2020-08-01.test.txt
100
+
101
+ - src_alpha3: itc
102
+
103
+ - tgt_alpha3: eng
104
+
105
+ - short_pair: itc-en
106
+
107
+ - chrF2_score: 0.634
108
+
109
+ - bleu: 47.6
110
+
111
+ - brevity_penalty: 0.981
112
+
113
+ - ref_len: 77633.0
114
+
115
+ - src_name: Italic languages
116
+
117
+ - tgt_name: English
118
+
119
+ - train_date: 2020-08-01
120
+
121
+ - src_alpha2: itc
122
+
123
+ - tgt_alpha2: en
124
+
125
+ - prefer_old: False
126
+
127
+ - long_pair: itc-eng
128
+
129
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
130
+
131
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
132
+
133
+ - port_machine: brutasse
134
+
135
+ - port_time: 2020-08-18-01:48