Hugging Face's logo

softcatala
/
translate-cat-glg

Translation
Catalan
Galician
opennmt
Model card Files Community
jordimas commited on
Commit
3b3b9a9
·
1 Parent(s): 61b8a8d

Update 2024-09-04 model

Browse files
Files changed (7) hide show
  1. README.md +2 -2
  2. config.json +8 -1
  3. model.bin +2 -2
  4. model_description.txt +6 -6
  5. shared_vocabulary.json +0 -0
  6. shared_vocabulary.txt +0 -0
  7. sp_m.model +2 -2
README.md CHANGED
@@ -50,8 +50,8 @@ print(tokenizer.detokenize(translated[0][0]['tokens']))
50
 
51
  | testset | BLEU |
52
  |---------------------------------------|-------|
53
- | test dataset (from train/dev/test) | 80.7 |
54
- | Flores200 dataset | 31.9 |
55
 
56
  ## Additional information
57
  * https://github.com/Softcatala/nmt-models
 
50
 
51
  | testset | BLEU |
52
  |---------------------------------------|-------|
53
+ | test dataset (from train/dev/test) | 69.4 |
54
+ | Flores200 dataset | 32.2 |
55
 
56
  ## Additional information
57
  * https://github.com/Softcatala/nmt-models
config.json CHANGED
@@ -1,2 +1,9 @@
1
  {
2
- }
 
 
 
 
 
 
 
 
1
  {
2
+ "add_source_bos": false,
3
+ "add_source_eos": false,
4
+ "bos_token": "<s>",
5
+ "decoder_start_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "layer_norm_epsilon": null,
8
+ "unk_token": "<unk>"
9
+ }
model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc94a4caa3a7ad9087943e83f71619b016ca53cde820c52ea062cb22e6094c26
3
- size 70727761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b60ebb2e25d7841fda4ada9ff395ec7a44a2cd2658862a5c79cd006e26e1bd
3
+ size 70727741
model_description.txt CHANGED
@@ -1,9 +1,9 @@
1
  Model description: cat-glg
2
- Date: 2022-11-21
3
- TF version 2.10.0, OpenNMT version 2.29.1, CTranslate2 version 2.24.0
4
  Test data set
5
- BLEU|nrefs:1|case:mixed|eff:no|tok:13a|smooth:exp|version:2.1.0 = 80.7 92.3/85.6/80.3/75.6 (BP = 0.970 ratio = 0.970 hyp_len = 96933 ref_len = 99928)
6
- chrF2|nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.1.0 = 89.7
7
  Flores data set
8
- BLEU|nrefs:1|case:mixed|eff:no|tok:13a|smooth:exp|version:2.1.0 = 31.9 63.7/39.4/26.2/17.5 (BP = 0.974 ratio = 0.974 hyp_len = 25893 ref_len = 26582)
9
- chrF2|nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.1.0 = 59.5
 
1
  Model description: cat-glg
2
+ Date: 2024-09-04
3
+ TF version 2.10.0, OpenNMT version 2.29.1, CTranslate2 version 3.22.0
4
  Test data set
5
+ BLEU|nrefs:1|bs:1000|seed:12345|case:mixed|eff:no|tok:13a|smooth:exp|version:2.1.0 = 69.4 (μ = 69.4 ± 0.9) 84.0/73.4/66.3/60.6 (BP = 0.984 ratio = 0.984 hyp_len = 194271 ref_len = 197468)
6
+ chrF2|nrefs:1|bs:1000|seed:12345|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.1.0 = 82.6 (μ = 82.5 ± 0.7)
7
  Flores data set
8
+ BLEU|nrefs:1|bs:1000|seed:12345|case:mixed|eff:no|tok:13a|smooth:exp|version:2.1.0 = 32.2 (μ = 32.1 ± 0.9) 63.7/39.5/26.3/17.7 (BP = 0.977 ratio = 0.977 hyp_len = 25983 ref_len = 26582)
9
+ chrF2|nrefs:1|bs:1000|seed:12345|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.1.0 = 59.7 (μ = 59.7 ± 0.7)
shared_vocabulary.json ADDED
The diff for this file is too large to render. See raw diff
 
shared_vocabulary.txt DELETED
The diff for this file is too large to render. See raw diff
 
sp_m.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:096530f4aa45e25d8b626549b7d23615656bcc77e996b3fe62f5c969e4d28789
3
- size 1136059
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af48717d42260723d8218a562a83cf22af67e3ab816bcb8ba4785ab8c06990a
3
+ size 1144913