system HF staff commited on
Commit
4642b80
1 Parent(s): 9148bcf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +108 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - translation
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ ### eng-inc
10
+
11
+ * source group: English
12
+ * target group: Indic languages
13
+ * OPUS readme: [eng-inc](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-inc/README.md)
14
+
15
+ * model: transformer
16
+ * source language(s): eng
17
+ * target language(s): asm awa ben bho gom guj hif_Latn hin mai mar npi ori pan_Guru pnb rom san_Deva sin snd_Arab urd
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-inc/opus2m-2020-08-01.zip)
22
+ * test set translations: [opus2m-2020-08-01.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-inc/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-inc/opus2m-2020-08-01.eval.txt)
24
+
25
+ ## Benchmarks
26
+
27
+ | testset | BLEU | chr-F |
28
+ |-----------------------|-------|-------|
29
+ | newsdev2014-enghin.eng.hin | 8.2 | 0.342 |
30
+ | newsdev2019-engu-engguj.eng.guj | 6.5 | 0.293 |
31
+ | newstest2014-hien-enghin.eng.hin | 11.4 | 0.364 |
32
+ | newstest2019-engu-engguj.eng.guj | 7.2 | 0.296 |
33
+ | Tatoeba-test.eng-asm.eng.asm | 2.7 | 0.277 |
34
+ | Tatoeba-test.eng-awa.eng.awa | 0.5 | 0.132 |
35
+ | Tatoeba-test.eng-ben.eng.ben | 16.7 | 0.470 |
36
+ | Tatoeba-test.eng-bho.eng.bho | 4.3 | 0.227 |
37
+ | Tatoeba-test.eng-guj.eng.guj | 17.5 | 0.373 |
38
+ | Tatoeba-test.eng-hif.eng.hif | 0.6 | 0.028 |
39
+ | Tatoeba-test.eng-hin.eng.hin | 17.7 | 0.469 |
40
+ | Tatoeba-test.eng-kok.eng.kok | 1.7 | 0.000 |
41
+ | Tatoeba-test.eng-lah.eng.lah | 0.3 | 0.028 |
42
+ | Tatoeba-test.eng-mai.eng.mai | 15.6 | 0.429 |
43
+ | Tatoeba-test.eng-mar.eng.mar | 21.3 | 0.477 |
44
+ | Tatoeba-test.eng.multi | 17.3 | 0.448 |
45
+ | Tatoeba-test.eng-nep.eng.nep | 0.8 | 0.081 |
46
+ | Tatoeba-test.eng-ori.eng.ori | 2.2 | 0.208 |
47
+ | Tatoeba-test.eng-pan.eng.pan | 8.0 | 0.347 |
48
+ | Tatoeba-test.eng-rom.eng.rom | 0.4 | 0.197 |
49
+ | Tatoeba-test.eng-san.eng.san | 0.5 | 0.108 |
50
+ | Tatoeba-test.eng-sin.eng.sin | 9.1 | 0.364 |
51
+ | Tatoeba-test.eng-snd.eng.snd | 4.4 | 0.284 |
52
+ | Tatoeba-test.eng-urd.eng.urd | 13.3 | 0.423 |
53
+
54
+
55
+ ### System Info:
56
+ - hf_name: eng-inc
57
+
58
+ - source_languages: eng
59
+
60
+ - target_languages: inc
61
+
62
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-inc/README.md
63
+
64
+ - original_repo: Tatoeba-Challenge
65
+
66
+ - tags: ['translation']
67
+
68
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
69
+
70
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-inc/opus2m-2020-08-01.zip
71
+
72
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-inc/opus2m-2020-08-01.test.txt
73
+
74
+ - src_alpha3: eng
75
+
76
+ - tgt_alpha3: inc
77
+
78
+ - short_pair: en-inc
79
+
80
+ - chrF2_score: 0.44799999999999995
81
+
82
+ - bleu: 17.3
83
+
84
+ - brevity_penalty: 1.0
85
+
86
+ - ref_len: 59917.0
87
+
88
+ - src_name: English
89
+
90
+ - tgt_name: Indic languages
91
+
92
+ - train_date: 2020-08-01
93
+
94
+ - src_alpha2: en
95
+
96
+ - tgt_alpha2: inc
97
+
98
+ - prefer_old: False
99
+
100
+ - long_pair: eng-inc
101
+
102
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
103
+
104
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
105
+
106
+ - port_machine: brutasse
107
+
108
+ - port_time: 2020-08-18-01:48