Update 2024-08-30 model

README.md

@@ -50,8 +50,8 @@ print(tokenizer.detokenize(translated[0][0]['tokens']))
 
 | testset                               | BLEU  |
 |---------------------------------------|-------|
-| test dataset (from train/dev/test)   	| 36.2	|
-| Flores200 dataset                     | 24.5	|
+| test dataset (from train/dev/test)   	| 38.3	|
+| Flores200 dataset                     | 25.1	|
 
 ## Additional information
 * https://github.com/Softcatala/nmt-models

config.json

@@ -1,2 +1,9 @@
 {
-}
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<s>",
+  "decoder_start_token": "<s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": null,
+  "unk_token": "<unk>"
+}

model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3f0990763e7f2e6f41896c9c3cfcc20f14c8a613be41f34c5b9cead48fa6eb
-size 70727761
+oid sha256:b2d178173374dfacc0f7ea160371f2f5ac612a481779d8e4d6fc5ef6f0c91e0b
+size 70727741

model_description.txt

@@ -1,9 +1,9 @@
 Model description: cat-ita
-Date: 2022-11-15
-TF version 2.10.0, OpenNMT version 2.29.1, CTranslate2 version 2.24.0
+Date: 2024-08-30
+TF version 2.10.0, OpenNMT version 2.29.1, CTranslate2 version 3.22.0
 Test data set
-  BLEU|nrefs:1|case:mixed|eff:no|tok:13a|smooth:exp|version:2.1.0 = 36.2 64.1/42.4/30.7/22.7 (BP = 0.974 ratio = 0.975 hyp_len = 139207 ref_len = 142832)
-chrF2|nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.1.0 = 62.9
+  BLEU|nrefs:1|bs:1000|seed:12345|case:mixed|eff:no|tok:13a|smooth:exp|version:2.1.0 = 38.3 (μ = 38.3 ± 0.6) 66.0/44.9/33.0/24.7 (BP = 0.972 ratio = 0.972 hyp_len = 171543 ref_len = 176440)
+chrF2|nrefs:1|bs:1000|seed:12345|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.1.0 = 64.2 (μ = 64.2 ± 0.5)
 Flores data set
-  BLEU|nrefs:1|case:mixed|eff:no|tok:13a|smooth:exp|version:2.1.0 = 24.5 58.1/32.3/19.4/12.0 (BP = 0.952 ratio = 0.953 hyp_len = 26034 ref_len = 27306)
-chrF2|nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.1.0 = 54.6
+  BLEU|nrefs:1|bs:1000|seed:12345|case:mixed|eff:no|tok:13a|smooth:exp|version:2.1.0 = 25.1 (μ = 25.1 ± 0.9) 58.5/32.8/20.0/12.3 (BP = 0.957 ratio = 0.958 hyp_len = 26150 ref_len = 27306)
+chrF2|nrefs:1|bs:1000|seed:12345|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.1.0 = 55.2 (μ = 55.2 ± 0.6)

sp_m.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17adbdc0d9f2593177a7274e1d928828fff2ebb17d488355b328d4e707a47d47
-size 1167983
+oid sha256:02ceeec9cb66dcd10292dfcf80c2dbedf25fe427722b84845a6b2a58032254da
+size 1161765