Hugging Face's logo

Helsinki-NLP
/
opus-mt-ar-de

Translation
Transformers
PyTorch
TensorFlow
Arabic
German
marian
text2text-generation
Inference Endpoints
Model card Files Community
4
system HF staff commited on
Commit
a48cad6
โ€ข
1 Parent(s): 622bbc2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -10
README.md CHANGED
@@ -1,24 +1,84 @@
1
  ---
 
2
  tags:
3
  - translation
 
 
4
  ---
5
 
6
- ### opus-mt-ar-de
7
 
8
- * source languages: ar
9
- * target languages: de
10
- * OPUS readme: [ar-de](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/ar-de/README.md)
11
 
12
- * dataset: opus
 
 
13
  * model: transformer-align
14
- * pre-processing: normalization + SentencePiece
15
- * download original weights: [opus-2020-01-20.zip](https://object.pouta.csc.fi/OPUS-MT-models/ar-de/opus-2020-01-20.zip)
16
- * test set translations: [opus-2020-01-20.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/ar-de/opus-2020-01-20.test.txt)
17
- * test set scores: [opus-2020-01-20.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/ar-de/opus-2020-01-20.eval.txt)
18
 
19
  ## Benchmarks
20
 
21
  | testset | BLEU | chr-F |
22
  |-----------------------|-------|-------|
23
- | Tatoeba.ar.de | 43.0 | 0.614 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
 
 
 
1
  ---
2
+ language: ar
3
  tags:
4
  - translation
5
+
6
+ license: apache-2.0
7
  ---
8
 
9
+ ### ara-deu
10
 
11
+ * source group: Arabic
12
+ * target group: German
13
+ * OPUS readme: [ara-deu](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-deu/README.md)
14
 
15
+ * model: transformer-align
16
+ * source language(s): afb apc ara ara_Latn arq arz
17
+ * target language(s): deu
18
  * model: transformer-align
19
+ * pre-processing: normalization + SentencePiece (spm32k,spm32k)
20
+ * download original weights: [opus-2020-07-03.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-deu/opus-2020-07-03.zip)
21
+ * test set translations: [opus-2020-07-03.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-deu/opus-2020-07-03.test.txt)
22
+ * test set scores: [opus-2020-07-03.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/ara-deu/opus-2020-07-03.eval.txt)
23
 
24
  ## Benchmarks
25
 
26
  | testset | BLEU | chr-F |
27
  |-----------------------|-------|-------|
28
+ | Tatoeba-test.ara.deu | 44.7 | 0.629 |
29
+
30
+
31
+ ### System Info:
32
+ - hf_name: ara-deu
33
+
34
+ - source_languages: ara
35
+
36
+ - target_languages: deu
37
+
38
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/ara-deu/README.md
39
+
40
+ - original_repo: Tatoeba-Challenge
41
+
42
+ - tags: ['translation']
43
+
44
+ - prepro: normalization + SentencePiece (spm32k,spm32k)
45
+
46
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-deu/opus-2020-07-03.zip
47
+
48
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/ara-deu/opus-2020-07-03.test.txt
49
+
50
+ - src_alpha3: ara
51
+
52
+ - tgt_alpha3: deu
53
+
54
+ - short_pair: ar-de
55
+
56
+ - chrF2_score: 0.629
57
+
58
+ - bleu: 44.7
59
+
60
+ - brevity_penalty: 0.986
61
+
62
+ - ref_len: 8371.0
63
+
64
+ - src_name: Arabic
65
+
66
+ - tgt_name: German
67
+
68
+ - train_date: 2020-07-03
69
+
70
+ - src_alpha2: ar
71
+
72
+ - tgt_alpha2: de
73
+
74
+ - prefer_old: False
75
+
76
+ - long_pair: ara-deu
77
+
78
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
79
+
80
+ - transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
81
+
82
+ - port_machine: brutasse
83
 
84
+ - port_time: 2020-08-18-01:48