Hugging Face's logo

Helsinki-NLP
/
opus-mt-en-roa

Translation
Transformers
PyTorch
TensorFlow
Rust
marian
text2text-generation
Inference Endpoints
Model card Files Community
3
system HF staff commited on
Commit
5a844b9
·
1 Parent(s): 4d97940

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +119 -10
README.md CHANGED
@@ -1,25 +1,134 @@
1
  ---
 
2
  tags:
3
  - translation
 
 
4
  ---
5
 
6
- ### opus-mt-en-ROMANCE
7
 
8
- * source languages: en
9
- * target languages: fr,fr_BE,fr_CA,fr_FR,wa,frp,oc,ca,rm,lld,fur,lij,lmo,es,es_AR,es_CL,es_CO,es_CR,es_DO,es_EC,es_ES,es_GT,es_HN,es_MX,es_NI,es_PA,es_PE,es_PR,es_SV,es_UY,es_VE,pt,pt_br,pt_BR,pt_PT,gl,lad,an,mwl,it,it_IT,co,nap,scn,vec,sc,ro,la
10
- * OPUS readme: [en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la/README.md)
11
 
12
- * dataset: opus
 
 
13
  * model: transformer
14
- * pre-processing: normalization + SentencePiece
15
  * a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
16
- * download original weights: [opus-2020-04-21.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la/opus-2020-04-21.zip)
17
- * test set translations: [opus-2020-04-21.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la/opus-2020-04-21.test.txt)
18
- * test set scores: [opus-2020-04-21.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la/opus-2020-04-21.eval.txt)
19
 
20
  ## Benchmarks
21
 
22
  | testset | BLEU | chr-F |
23
  |-----------------------|-------|-------|
24
- | Tatoeba.en.la | 50.1 | 0.693 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
 
 
 
1
  ---
2
+ language: en
3
  tags:
4
  - translation
5
+
6
+ license: apache-2.0
7
  ---
8
 
9
+ ### eng-roa
10
 
11
+ * source group: English
12
+ * target group: Romance languages
13
+ * OPUS readme: [eng-roa](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-roa/README.md)
14
 
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): arg ast cat cos egl ext fra frm_Latn gcf_Latn glg hat ind ita lad lad_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
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-roa/opus2m-2020-08-01.zip)
22
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-roa/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-roa/opus2m-2020-08-01.eval.txt)
24
 
25
  ## Benchmarks
26
 
27
  | testset | BLEU | chr-F |
28
  |-----------------------|-------|-------|
29
+ | newsdev2016-enro-engron.eng.ron | 27.6 | 0.567 |
30
+ | newsdiscussdev2015-enfr-engfra.eng.fra | 30.2 | 0.575 |
31
+ | newsdiscusstest2015-enfr-engfra.eng.fra | 35.5 | 0.612 |
32
+ | newssyscomb2009-engfra.eng.fra | 27.9 | 0.570 |
33
+ | newssyscomb2009-engita.eng.ita | 29.3 | 0.590 |
34
+ | newssyscomb2009-engspa.eng.spa | 29.6 | 0.570 |
35
+ | news-test2008-engfra.eng.fra | 25.2 | 0.538 |
36
+ | news-test2008-engspa.eng.spa | 27.3 | 0.548 |
37
+ | newstest2009-engfra.eng.fra | 26.9 | 0.560 |
38
+ | newstest2009-engita.eng.ita | 28.7 | 0.583 |
39
+ | newstest2009-engspa.eng.spa | 29.0 | 0.568 |
40
+ | newstest2010-engfra.eng.fra | 29.3 | 0.574 |
41
+ | newstest2010-engspa.eng.spa | 34.2 | 0.601 |
42
+ | newstest2011-engfra.eng.fra | 31.4 | 0.592 |
43
+ | newstest2011-engspa.eng.spa | 35.0 | 0.599 |
44
+ | newstest2012-engfra.eng.fra | 29.5 | 0.576 |
45
+ | newstest2012-engspa.eng.spa | 35.5 | 0.603 |
46
+ | newstest2013-engfra.eng.fra | 29.9 | 0.567 |
47
+ | newstest2013-engspa.eng.spa | 32.1 | 0.578 |
48
+ | newstest2016-enro-engron.eng.ron | 26.1 | 0.551 |
49
+ | Tatoeba-test.eng-arg.eng.arg | 1.4 | 0.125 |
50
+ | Tatoeba-test.eng-ast.eng.ast | 17.8 | 0.406 |
51
+ | Tatoeba-test.eng-cat.eng.cat | 48.3 | 0.676 |
52
+ | Tatoeba-test.eng-cos.eng.cos | 3.2 | 0.275 |
53
+ | Tatoeba-test.eng-egl.eng.egl | 0.2 | 0.084 |
54
+ | Tatoeba-test.eng-ext.eng.ext | 11.2 | 0.344 |
55
+ | Tatoeba-test.eng-fra.eng.fra | 45.3 | 0.637 |
56
+ | Tatoeba-test.eng-frm.eng.frm | 1.1 | 0.221 |
57
+ | Tatoeba-test.eng-gcf.eng.gcf | 0.6 | 0.118 |
58
+ | Tatoeba-test.eng-glg.eng.glg | 44.2 | 0.645 |
59
+ | Tatoeba-test.eng-hat.eng.hat | 28.0 | 0.502 |
60
+ | Tatoeba-test.eng-ita.eng.ita | 45.6 | 0.674 |
61
+ | Tatoeba-test.eng-lad.eng.lad | 8.2 | 0.322 |
62
+ | Tatoeba-test.eng-lij.eng.lij | 1.4 | 0.182 |
63
+ | Tatoeba-test.eng-lld.eng.lld | 0.8 | 0.217 |
64
+ | Tatoeba-test.eng-lmo.eng.lmo | 0.7 | 0.190 |
65
+ | Tatoeba-test.eng-mfe.eng.mfe | 91.9 | 0.956 |
66
+ | Tatoeba-test.eng-msa.eng.msa | 31.1 | 0.548 |
67
+ | Tatoeba-test.eng.multi | 42.9 | 0.636 |
68
+ | Tatoeba-test.eng-mwl.eng.mwl | 2.1 | 0.234 |
69
+ | Tatoeba-test.eng-oci.eng.oci | 7.9 | 0.297 |
70
+ | Tatoeba-test.eng-pap.eng.pap | 44.1 | 0.648 |
71
+ | Tatoeba-test.eng-pms.eng.pms | 2.1 | 0.190 |
72
+ | Tatoeba-test.eng-por.eng.por | 41.8 | 0.639 |
73
+ | Tatoeba-test.eng-roh.eng.roh | 3.5 | 0.261 |
74
+ | Tatoeba-test.eng-ron.eng.ron | 41.0 | 0.635 |
75
+ | Tatoeba-test.eng-scn.eng.scn | 1.7 | 0.184 |
76
+ | Tatoeba-test.eng-spa.eng.spa | 50.1 | 0.689 |
77
+ | Tatoeba-test.eng-vec.eng.vec | 3.2 | 0.248 |
78
+ | Tatoeba-test.eng-wln.eng.wln | 7.2 | 0.220 |
79
+
80
+
81
+ ### System Info:
82
+ - hf_name: eng-roa
83
+
84
+ - source_languages: eng
85
+
86
+ - target_languages: roa
87
+
88
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-roa/README.md
89
+
90
+ - original_repo: Tatoeba-Challenge
91
+
92
+ - tags: ['translation']
93
+
94
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
95
+
96
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-roa/opus2m-2020-08-01.zip
97
+
98
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-roa/opus2m-2020-08-01.test.txt
99
+
100
+ - src_alpha3: eng
101
+
102
+ - tgt_alpha3: roa
103
+
104
+ - short_pair: en-roa
105
+
106
+ - chrF2_score: 0.636
107
+
108
+ - bleu: 42.9
109
+
110
+ - brevity_penalty: 0.978
111
+
112
+ - ref_len: 72751.0
113
+
114
+ - src_name: English
115
+
116
+ - tgt_name: Romance languages
117
+
118
+ - train_date: 2020-08-01
119
+
120
+ - src_alpha2: en
121
+
122
+ - tgt_alpha2: roa
123
+
124
+ - prefer_old: False
125
+
126
+ - long_pair: eng-roa
127
+
128
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
129
+
130
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
131
+
132
+ - port_machine: brutasse
133
 
134
+ - port_time: 2020-08-18-01:48