Joerg Tiedemann
|
ca2a249845
|
bugfixing in tatoeba MT model recipes
|
2021-02-18 13:49:16 +02:00 |
|
Joerg Tiedemann
|
53c5680268
|
fixed tatoeba group recipes
|
2021-02-16 20:36:00 +02:00 |
|
Joerg Tiedemann
|
f2eb32239b
|
memad tatoeba models
|
2021-02-15 20:36:26 +02:00 |
|
Joerg Tiedemann
|
3c6793045b
|
moved results table generation for tatoeba models
|
2021-02-15 20:35:29 +02:00 |
|
Joerg Tiedemann
|
c46eb49c26
|
memad models with tatoeba data and some cleanup in tatoeba langgroup language expansion
|
2021-02-03 20:49:14 +02:00 |
|
Joerg Tiedemann
|
4305ad01b9
|
tatoeba model result lists added
|
2021-01-18 14:53:54 +02:00 |
|
Joerg Tiedemann
|
b5fbc4a52a
|
Merge branch 'master' of github.com:Helsinki-NLP/OPUS-MT-train
|
2021-01-14 23:12:46 +02:00 |
|
Joerg Tiedemann
|
385e8298b2
|
more fixes with evaluation recipes of multilingual tatoeba models
|
2021-01-14 23:07:12 +02:00 |
|
tiedemann
|
f74531468e
|
Update README.md
|
2021-01-14 22:31:09 +02:00 |
|
Joerg Tiedemann
|
81ce0bf8c4
|
fixed a problem with fine-tuning Tatoeba multilingual models for specific language pairs
|
2021-01-09 00:29:04 +02:00 |
|
Joerg Tiedemann
|
71d49406eb
|
tutorial links added
|
2021-01-07 23:50:33 +02:00 |
|
Joerg Tiedemann
|
527ab54caa
|
subset result tables for Tatoeba now also with reverse translation direction
|
2021-01-07 23:19:24 +02:00 |
|
Joerg Tiedemann
|
c3be953980
|
recipe for finetuning multilingual models for specific language pairs (example Tatoeba models)
|
2021-01-07 21:45:59 +02:00 |
|
Joerg Tiedemann
|
359657a523
|
make it possible to update release list
|
2021-01-05 00:49:43 +02:00 |
|
Joerg Tiedemann
|
3413c8afe0
|
added file for released Tatoeba results
|
2021-01-05 00:44:52 +02:00 |
|
Joerg Tiedemann
|
f574427461
|
add recipe to release all unfinished Tatoeba models
|
2021-01-03 00:55:03 +02:00 |
|
Joerg Tiedemann
|
f196818110
|
renamed some recipes for tatoeba to be more flexible
|
2020-12-29 12:42:37 +02:00 |
|
Joerg Tiedemann
|
721527e8ef
|
Merge branch 'master' of github.com:Helsinki-NLP/OPUS-MT-train
|
2020-11-26 12:59:21 +02:00 |
|
Joerg Tiedemann
|
7bd502edcc
|
updated model list
|
2020-11-26 12:57:46 +02:00 |
|
tiedemann
|
474891563a
|
Update README.md
|
2020-11-19 12:02:06 +02:00 |
|
Joerg Tiedemann
|
3a66dc6fd4
|
Merge branch 'master' of github.com:Helsinki-NLP/OPUS-MT-train
|
2020-10-27 23:49:39 +02:00 |
|
Joerg Tiedemann
|
1186d9afd5
|
tico19 benchmark added
|
2020-10-27 23:48:09 +02:00 |
|
Joerg Tiedemann
|
40a6b5ab6b
|
fixed bug in release target
|
2020-10-04 00:10:11 +03:00 |
|
tiedemann
|
79a49e1b9e
|
Merge pull request #31 from Helsinki-NLP/sam-suppress-missing-perl-module-warnings-when-installing-fix
Sam suppress missing perl module warnings when installing fix
|
2020-10-01 23:26:45 +03:00 |
|
Joerg Tiedemann
|
4cc192da15
|
avoid error messages in data creation when no data files exist for some language pairs
|
2020-09-25 10:05:18 +03:00 |
|
Joerg Tiedemann
|
c6356d3a8a
|
back to yml vocab files as default
|
2020-09-25 09:58:25 +03:00 |
|
Traubert
|
9ee38fe355
|
Suppress warnings when testing for missing Perl modules
|
2020-09-24 13:25:14 +03:00 |
|
Traubert
|
ec69daa989
|
Some puhti modules needed for installing
|
2020-09-24 13:18:18 +03:00 |
|
Traubert
|
21433867ab
|
If we include lib/config.mk before prerequisites are made, make fails
Therefore, the install target needs to come first (though this is not
necessarily sufficient).
|
2020-09-24 12:25:24 +03:00 |
|
Traubert
|
1e349f269c
|
Fix type
|
2020-09-24 12:15:08 +03:00 |
|
Joerg Tiedemann
|
f9a44bdb99
|
merged
|
2020-09-18 23:08:56 +03:00 |
|
Joerg Tiedemann
|
87a5354de5
|
changes to tatoeba recipes
|
2020-09-18 23:05:46 +03:00 |
|
Jörg Tiedemann
|
a61cf48443
|
add option to skip sentence piecce vocabs but use marian_vocab instead
|
2020-09-16 19:33:19 +03:00 |
|
tiedemann
|
913d31472e
|
Merge pull request #25 from Helsinki-NLP/sam-fixes
Fix typo
|
2020-09-16 09:28:46 +03:00 |
|
Joerg Tiedemann
|
c564bd1f56
|
fix in fetching data for Sami languages
|
2020-09-16 09:25:36 +03:00 |
|
Traubert
|
1da54c4155
|
Fix typo
|
2020-09-15 15:02:20 +03:00 |
|
Jörg Tiedemann
|
58fbf0bdd8
|
back to old subword model names
|
2020-09-14 08:53:57 +03:00 |
|
Jörg Tiedemann
|
c2798e9758
|
plain text vocab files from spm models
|
2020-09-13 22:17:21 +03:00 |
|
Jörg Tiedemann
|
24e92de56a
|
proper release packages for models with internal sentence piece vocabs
|
2020-09-13 00:00:15 +03:00 |
|
Jörg Tiedemann
|
666b2b8462
|
internal sentence piece models in transformers
|
2020-09-12 16:16:01 +03:00 |
|
Jörg Tiedemann
|
ddafb43d66
|
removed dependence on moses tools in preprocessing script for released spm packages
|
2020-09-12 14:42:10 +03:00 |
|
Jörg Tiedemann
|
c0cb356417
|
added acknowledgements
|
2020-09-12 12:01:02 +03:00 |
|
Jörg Tiedemann
|
16eef8e45d
|
moved project makefiles to lib/projects
|
2020-09-10 12:12:44 +03:00 |
|
Jörg Tiedemann
|
1a6e29275d
|
dev data is now uniq to avoid overlaps with test data
|
2020-09-09 23:21:07 +03:00 |
|
Jörg Tiedemann
|
3735af4ec1
|
more documentation
|
2020-09-07 23:00:01 +03:00 |
|
Jörg Tiedemann
|
3367ad2e34
|
documentation of low-resource languages
|
2020-09-06 23:56:16 +03:00 |
|
Jörg Tiedemann
|
909e525a2d
|
keep translations even if uncomplete in pivoting
|
2020-09-06 00:22:48 +03:00 |
|
Jörg Tiedemann
|
a47c292152
|
pivoting and documentation
|
2020-09-05 22:19:00 +03:00 |
|
Jörg Tiedemann
|
ad828c3124
|
started tutorial and fixes to backtranslate makefile
|
2020-09-05 00:16:22 +03:00 |
|
Tiedemann Jörg
|
d11f74ce41
|
added bpe submodule
|
2020-09-04 15:34:20 +03:00 |
|