tiedeman's picture
Initial commit
3e7352a
|
raw
history blame
45.9 kB
---
library_name: transformers
language:
- da
- de
- en
- es
- fo
- fr
- is
- nb
- nn
- no
- non
- pt
- sv
tags:
- translation
- opus-mt-tc-bible
license: apache-2.0
model-index:
- name: opus-mt-tc-bible-big-gmq-deu_eng_fra_por_spa
results:
- task:
name: Translation dan-deu
type: translation
args: dan-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: dan-deu
metrics:
- name: BLEU
type: bleu
value: 32.3
- name: chr-F
type: chrf
value: 0.60897
- task:
name: Translation dan-eng
type: translation
args: dan-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: dan-eng
metrics:
- name: BLEU
type: bleu
value: 48.2
- name: chr-F
type: chrf
value: 0.71641
- task:
name: Translation dan-fra
type: translation
args: dan-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: dan-fra
metrics:
- name: BLEU
type: bleu
value: 38.9
- name: chr-F
type: chrf
value: 0.63777
- task:
name: Translation dan-por
type: translation
args: dan-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: dan-por
metrics:
- name: BLEU
type: bleu
value: 36.7
- name: chr-F
type: chrf
value: 0.62302
- task:
name: Translation dan-spa
type: translation
args: dan-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: dan-spa
metrics:
- name: BLEU
type: bleu
value: 24.4
- name: chr-F
type: chrf
value: 0.52803
- task:
name: Translation fao-deu
type: translation
args: fao-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: fao-deu
metrics:
- name: BLEU
type: bleu
value: 16.0
- name: chr-F
type: chrf
value: 0.41184
- task:
name: Translation fao-eng
type: translation
args: fao-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: fao-eng
metrics:
- name: BLEU
type: bleu
value: 21.2
- name: chr-F
type: chrf
value: 0.43308
- task:
name: Translation fao-fra
type: translation
args: fao-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: fao-fra
metrics:
- name: BLEU
type: bleu
value: 16.7
- name: chr-F
type: chrf
value: 0.39253
- task:
name: Translation fao-por
type: translation
args: fao-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: fao-por
metrics:
- name: BLEU
type: bleu
value: 19.0
- name: chr-F
type: chrf
value: 0.42649
- task:
name: Translation fao-spa
type: translation
args: fao-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: fao-spa
metrics:
- name: BLEU
type: bleu
value: 14.1
- name: chr-F
type: chrf
value: 0.38131
- task:
name: Translation isl-deu
type: translation
args: isl-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: isl-deu
metrics:
- name: BLEU
type: bleu
value: 22.7
- name: chr-F
type: chrf
value: 0.51165
- task:
name: Translation isl-eng
type: translation
args: isl-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: isl-eng
metrics:
- name: BLEU
type: bleu
value: 32.2
- name: chr-F
type: chrf
value: 0.57745
- task:
name: Translation isl-fra
type: translation
args: isl-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: isl-fra
metrics:
- name: BLEU
type: bleu
value: 27.6
- name: chr-F
type: chrf
value: 0.54210
- task:
name: Translation isl-por
type: translation
args: isl-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: isl-por
metrics:
- name: BLEU
type: bleu
value: 26.1
- name: chr-F
type: chrf
value: 0.52479
- task:
name: Translation isl-spa
type: translation
args: isl-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: isl-spa
metrics:
- name: BLEU
type: bleu
value: 19.2
- name: chr-F
type: chrf
value: 0.46837
- task:
name: Translation nno-deu
type: translation
args: nno-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: nno-deu
metrics:
- name: BLEU
type: bleu
value: 29.2
- name: chr-F
type: chrf
value: 0.58054
- task:
name: Translation nno-eng
type: translation
args: nno-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: nno-eng
metrics:
- name: BLEU
type: bleu
value: 45.0
- name: chr-F
type: chrf
value: 0.69114
- task:
name: Translation nno-fra
type: translation
args: nno-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: nno-fra
metrics:
- name: BLEU
type: bleu
value: 36.0
- name: chr-F
type: chrf
value: 0.61334
- task:
name: Translation nno-por
type: translation
args: nno-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: nno-por
metrics:
- name: BLEU
type: bleu
value: 34.1
- name: chr-F
type: chrf
value: 0.60055
- task:
name: Translation nno-spa
type: translation
args: nno-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: nno-spa
metrics:
- name: BLEU
type: bleu
value: 22.8
- name: chr-F
type: chrf
value: 0.51190
- task:
name: Translation nob-deu
type: translation
args: nob-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: nob-deu
metrics:
- name: BLEU
type: bleu
value: 27.6
- name: chr-F
type: chrf
value: 0.57023
- task:
name: Translation nob-eng
type: translation
args: nob-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: nob-eng
metrics:
- name: BLEU
type: bleu
value: 43.1
- name: chr-F
type: chrf
value: 0.67540
- task:
name: Translation nob-fra
type: translation
args: nob-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: nob-fra
metrics:
- name: BLEU
type: bleu
value: 34.2
- name: chr-F
type: chrf
value: 0.60568
- task:
name: Translation nob-por
type: translation
args: nob-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: nob-por
metrics:
- name: BLEU
type: bleu
value: 32.8
- name: chr-F
type: chrf
value: 0.59466
- task:
name: Translation nob-spa
type: translation
args: nob-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: nob-spa
metrics:
- name: BLEU
type: bleu
value: 22.4
- name: chr-F
type: chrf
value: 0.51138
- task:
name: Translation swe-deu
type: translation
args: swe-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: swe-deu
metrics:
- name: BLEU
type: bleu
value: 32.6
- name: chr-F
type: chrf
value: 0.60630
- task:
name: Translation swe-eng
type: translation
args: swe-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: swe-eng
metrics:
- name: BLEU
type: bleu
value: 48.1
- name: chr-F
type: chrf
value: 0.70584
- task:
name: Translation swe-fra
type: translation
args: swe-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: swe-fra
metrics:
- name: BLEU
type: bleu
value: 39.1
- name: chr-F
type: chrf
value: 0.63608
- task:
name: Translation swe-por
type: translation
args: swe-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: swe-por
metrics:
- name: BLEU
type: bleu
value: 36.4
- name: chr-F
type: chrf
value: 0.62046
- task:
name: Translation swe-spa
type: translation
args: swe-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: swe-spa
metrics:
- name: BLEU
type: bleu
value: 23.9
- name: chr-F
type: chrf
value: 0.52328
- task:
name: Translation dan-eng
type: translation
args: dan-eng
dataset:
name: flores101-devtest
type: flores_101
args: dan eng devtest
metrics:
- name: BLEU
type: bleu
value: 47.6
- name: chr-F
type: chrf
value: 0.71193
- task:
name: Translation dan-fra
type: translation
args: dan-fra
dataset:
name: flores101-devtest
type: flores_101
args: dan fra devtest
metrics:
- name: BLEU
type: bleu
value: 38.1
- name: chr-F
type: chrf
value: 0.63349
- task:
name: Translation dan-por
type: translation
args: dan-por
dataset:
name: flores101-devtest
type: flores_101
args: dan por devtest
metrics:
- name: BLEU
type: bleu
value: 36.2
- name: chr-F
type: chrf
value: 0.62063
- task:
name: Translation dan-spa
type: translation
args: dan-spa
dataset:
name: flores101-devtest
type: flores_101
args: dan spa devtest
metrics:
- name: BLEU
type: bleu
value: 24.2
- name: chr-F
type: chrf
value: 0.52557
- task:
name: Translation isl-deu
type: translation
args: isl-deu
dataset:
name: flores101-devtest
type: flores_101
args: isl deu devtest
metrics:
- name: BLEU
type: bleu
value: 22.2
- name: chr-F
type: chrf
value: 0.50581
- task:
name: Translation isl-eng
type: translation
args: isl-eng
dataset:
name: flores101-devtest
type: flores_101
args: isl eng devtest
metrics:
- name: BLEU
type: bleu
value: 31.6
- name: chr-F
type: chrf
value: 0.57294
- task:
name: Translation isl-por
type: translation
args: isl-por
dataset:
name: flores101-devtest
type: flores_101
args: isl por devtest
metrics:
- name: BLEU
type: bleu
value: 25.8
- name: chr-F
type: chrf
value: 0.52192
- task:
name: Translation isl-spa
type: translation
args: isl-spa
dataset:
name: flores101-devtest
type: flores_101
args: isl spa devtest
metrics:
- name: BLEU
type: bleu
value: 18.5
- name: chr-F
type: chrf
value: 0.46364
- task:
name: Translation nob-eng
type: translation
args: nob-eng
dataset:
name: flores101-devtest
type: flores_101
args: nob eng devtest
metrics:
- name: BLEU
type: bleu
value: 42.6
- name: chr-F
type: chrf
value: 0.67120
- task:
name: Translation nob-fra
type: translation
args: nob-fra
dataset:
name: flores101-devtest
type: flores_101
args: nob fra devtest
metrics:
- name: BLEU
type: bleu
value: 33.9
- name: chr-F
type: chrf
value: 0.60289
- task:
name: Translation nob-spa
type: translation
args: nob-spa
dataset:
name: flores101-devtest
type: flores_101
args: nob spa devtest
metrics:
- name: BLEU
type: bleu
value: 21.9
- name: chr-F
type: chrf
value: 0.50848
- task:
name: Translation swe-deu
type: translation
args: swe-deu
dataset:
name: flores101-devtest
type: flores_101
args: swe deu devtest
metrics:
- name: BLEU
type: bleu
value: 32.2
- name: chr-F
type: chrf
value: 0.60306
- task:
name: Translation swe-eng
type: translation
args: swe-eng
dataset:
name: flores101-devtest
type: flores_101
args: swe eng devtest
metrics:
- name: BLEU
type: bleu
value: 47.9
- name: chr-F
type: chrf
value: 0.70404
- task:
name: Translation swe-por
type: translation
args: swe-por
dataset:
name: flores101-devtest
type: flores_101
args: swe por devtest
metrics:
- name: BLEU
type: bleu
value: 35.7
- name: chr-F
type: chrf
value: 0.61418
- task:
name: Translation dan-deu
type: translation
args: dan-deu
dataset:
name: ntrex128
type: ntrex128
args: dan-deu
metrics:
- name: BLEU
type: bleu
value: 25.3
- name: chr-F
type: chrf
value: 0.54229
- task:
name: Translation dan-eng
type: translation
args: dan-eng
dataset:
name: ntrex128
type: ntrex128
args: dan-eng
metrics:
- name: BLEU
type: bleu
value: 38.7
- name: chr-F
type: chrf
value: 0.63083
- task:
name: Translation dan-fra
type: translation
args: dan-fra
dataset:
name: ntrex128
type: ntrex128
args: dan-fra
metrics:
- name: BLEU
type: bleu
value: 26.2
- name: chr-F
type: chrf
value: 0.54088
- task:
name: Translation dan-por
type: translation
args: dan-por
dataset:
name: ntrex128
type: ntrex128
args: dan-por
metrics:
- name: BLEU
type: bleu
value: 27.0
- name: chr-F
type: chrf
value: 0.53626
- task:
name: Translation dan-spa
type: translation
args: dan-spa
dataset:
name: ntrex128
type: ntrex128
args: dan-spa
metrics:
- name: BLEU
type: bleu
value: 30.8
- name: chr-F
type: chrf
value: 0.56217
- task:
name: Translation fao-deu
type: translation
args: fao-deu
dataset:
name: ntrex128
type: ntrex128
args: fao-deu
metrics:
- name: BLEU
type: bleu
value: 16.4
- name: chr-F
type: chrf
value: 0.41701
- task:
name: Translation fao-eng
type: translation
args: fao-eng
dataset:
name: ntrex128
type: ntrex128
args: fao-eng
metrics:
- name: BLEU
type: bleu
value: 25.3
- name: chr-F
type: chrf
value: 0.47105
- task:
name: Translation fao-fra
type: translation
args: fao-fra
dataset:
name: ntrex128
type: ntrex128
args: fao-fra
metrics:
- name: BLEU
type: bleu
value: 16.3
- name: chr-F
type: chrf
value: 0.40070
- task:
name: Translation fao-por
type: translation
args: fao-por
dataset:
name: ntrex128
type: ntrex128
args: fao-por
metrics:
- name: BLEU
type: bleu
value: 18.0
- name: chr-F
type: chrf
value: 0.42005
- task:
name: Translation fao-spa
type: translation
args: fao-spa
dataset:
name: ntrex128
type: ntrex128
args: fao-spa
metrics:
- name: BLEU
type: bleu
value: 20.5
- name: chr-F
type: chrf
value: 0.44085
- task:
name: Translation isl-deu
type: translation
args: isl-deu
dataset:
name: ntrex128
type: ntrex128
args: isl-deu
metrics:
- name: BLEU
type: bleu
value: 20.5
- name: chr-F
type: chrf
value: 0.49932
- task:
name: Translation isl-eng
type: translation
args: isl-eng
dataset:
name: ntrex128
type: ntrex128
args: isl-eng
metrics:
- name: BLEU
type: bleu
value: 29.7
- name: chr-F
type: chrf
value: 0.56856
- task:
name: Translation isl-fra
type: translation
args: isl-fra
dataset:
name: ntrex128
type: ntrex128
args: isl-fra
metrics:
- name: BLEU
type: bleu
value: 24.6
- name: chr-F
type: chrf
value: 0.51998
- task:
name: Translation isl-por
type: translation
args: isl-por
dataset:
name: ntrex128
type: ntrex128
args: isl-por
metrics:
- name: BLEU
type: bleu
value: 21.7
- name: chr-F
type: chrf
value: 0.49903
- task:
name: Translation isl-spa
type: translation
args: isl-spa
dataset:
name: ntrex128
type: ntrex128
args: isl-spa
metrics:
- name: BLEU
type: bleu
value: 27.1
- name: chr-F
type: chrf
value: 0.53171
- task:
name: Translation nno-deu
type: translation
args: nno-deu
dataset:
name: ntrex128
type: ntrex128
args: nno-deu
metrics:
- name: BLEU
type: bleu
value: 24.4
- name: chr-F
type: chrf
value: 0.53000
- task:
name: Translation nno-eng
type: translation
args: nno-eng
dataset:
name: ntrex128
type: ntrex128
args: nno-eng
metrics:
- name: BLEU
type: bleu
value: 42.9
- name: chr-F
type: chrf
value: 0.65866
- task:
name: Translation nno-fra
type: translation
args: nno-fra
dataset:
name: ntrex128
type: ntrex128
args: nno-fra
metrics:
- name: BLEU
type: bleu
value: 27.5
- name: chr-F
type: chrf
value: 0.54339
- task:
name: Translation nno-por
type: translation
args: nno-por
dataset:
name: ntrex128
type: ntrex128
args: nno-por
metrics:
- name: BLEU
type: bleu
value: 26.3
- name: chr-F
type: chrf
value: 0.53242
- task:
name: Translation nno-spa
type: translation
args: nno-spa
dataset:
name: ntrex128
type: ntrex128
args: nno-spa
metrics:
- name: BLEU
type: bleu
value: 30.4
- name: chr-F
type: chrf
value: 0.55889
- task:
name: Translation nob-deu
type: translation
args: nob-deu
dataset:
name: ntrex128
type: ntrex128
args: nob-deu
metrics:
- name: BLEU
type: bleu
value: 26.8
- name: chr-F
type: chrf
value: 0.55549
- task:
name: Translation nob-eng
type: translation
args: nob-eng
dataset:
name: ntrex128
type: ntrex128
args: nob-eng
metrics:
- name: BLEU
type: bleu
value: 40.9
- name: chr-F
type: chrf
value: 0.65580
- task:
name: Translation nob-fra
type: translation
args: nob-fra
dataset:
name: ntrex128
type: ntrex128
args: nob-fra
metrics:
- name: BLEU
type: bleu
value: 29.2
- name: chr-F
type: chrf
value: 0.56187
- task:
name: Translation nob-por
type: translation
args: nob-por
dataset:
name: ntrex128
type: ntrex128
args: nob-por
metrics:
- name: BLEU
type: bleu
value: 26.6
- name: chr-F
type: chrf
value: 0.54392
- task:
name: Translation nob-spa
type: translation
args: nob-spa
dataset:
name: ntrex128
type: ntrex128
args: nob-spa
metrics:
- name: BLEU
type: bleu
value: 32.6
- name: chr-F
type: chrf
value: 0.57998
- task:
name: Translation swe-deu
type: translation
args: swe-deu
dataset:
name: ntrex128
type: ntrex128
args: swe-deu
metrics:
- name: BLEU
type: bleu
value: 26.7
- name: chr-F
type: chrf
value: 0.55549
- task:
name: Translation swe-eng
type: translation
args: swe-eng
dataset:
name: ntrex128
type: ntrex128
args: swe-eng
metrics:
- name: BLEU
type: bleu
value: 42.2
- name: chr-F
type: chrf
value: 0.66348
- task:
name: Translation swe-fra
type: translation
args: swe-fra
dataset:
name: ntrex128
type: ntrex128
args: swe-fra
metrics:
- name: BLEU
type: bleu
value: 29.0
- name: chr-F
type: chrf
value: 0.56310
- task:
name: Translation swe-por
type: translation
args: swe-por
dataset:
name: ntrex128
type: ntrex128
args: swe-por
metrics:
- name: BLEU
type: bleu
value: 27.8
- name: chr-F
type: chrf
value: 0.54965
- task:
name: Translation swe-spa
type: translation
args: swe-spa
dataset:
name: ntrex128
type: ntrex128
args: swe-spa
metrics:
- name: BLEU
type: bleu
value: 32.8
- name: chr-F
type: chrf
value: 0.58035
- task:
name: Translation dan-deu
type: translation
args: dan-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: dan-deu
metrics:
- name: BLEU
type: bleu
value: 56.7
- name: chr-F
type: chrf
value: 0.74460
- task:
name: Translation dan-eng
type: translation
args: dan-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: dan-eng
metrics:
- name: BLEU
type: bleu
value: 64.3
- name: chr-F
type: chrf
value: 0.77233
- task:
name: Translation dan-fra
type: translation
args: dan-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: dan-fra
metrics:
- name: BLEU
type: bleu
value: 60.8
- name: chr-F
type: chrf
value: 0.76425
- task:
name: Translation dan-por
type: translation
args: dan-por
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: dan-por
metrics:
- name: BLEU
type: bleu
value: 60.0
- name: chr-F
type: chrf
value: 0.77248
- task:
name: Translation dan-spa
type: translation
args: dan-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: dan-spa
metrics:
- name: BLEU
type: bleu
value: 54.9
- name: chr-F
type: chrf
value: 0.72567
- task:
name: Translation fao-eng
type: translation
args: fao-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: fao-eng
metrics:
- name: BLEU
type: bleu
value: 39.6
- name: chr-F
type: chrf
value: 0.54571
- task:
name: Translation isl-deu
type: translation
args: isl-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: isl-deu
metrics:
- name: BLEU
type: bleu
value: 51.4
- name: chr-F
type: chrf
value: 0.68535
- task:
name: Translation isl-eng
type: translation
args: isl-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: isl-eng
metrics:
- name: BLEU
type: bleu
value: 51.7
- name: chr-F
type: chrf
value: 0.67066
- task:
name: Translation isl-spa
type: translation
args: isl-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: isl-spa
metrics:
- name: BLEU
type: bleu
value: 48.5
- name: chr-F
type: chrf
value: 0.65659
- task:
name: Translation multi-multi
type: translation
args: multi-multi
dataset:
name: tatoeba-test-v2020-07-28-v2023-09-26
type: tatoeba_mt
args: multi-multi
metrics:
- name: BLEU
type: bleu
value: 58.2
- name: chr-F
type: chrf
value: 0.73325
- task:
name: Translation nno-eng
type: translation
args: nno-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nno-eng
metrics:
- name: BLEU
type: bleu
value: 55.5
- name: chr-F
type: chrf
value: 0.69415
- task:
name: Translation nob-deu
type: translation
args: nob-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nob-deu
metrics:
- name: BLEU
type: bleu
value: 50.5
- name: chr-F
type: chrf
value: 0.69862
- task:
name: Translation nob-eng
type: translation
args: nob-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nob-eng
metrics:
- name: BLEU
type: bleu
value: 59.2
- name: chr-F
type: chrf
value: 0.72912
- task:
name: Translation nob-fra
type: translation
args: nob-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nob-fra
metrics:
- name: BLEU
type: bleu
value: 52.5
- name: chr-F
type: chrf
value: 0.71392
- task:
name: Translation nob-spa
type: translation
args: nob-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nob-spa
metrics:
- name: BLEU
type: bleu
value: 55.1
- name: chr-F
type: chrf
value: 0.73300
- task:
name: Translation nor-deu
type: translation
args: nor-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nor-deu
metrics:
- name: BLEU
type: bleu
value: 50.7
- name: chr-F
type: chrf
value: 0.69923
- task:
name: Translation nor-eng
type: translation
args: nor-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nor-eng
metrics:
- name: BLEU
type: bleu
value: 58.8
- name: chr-F
type: chrf
value: 0.72587
- task:
name: Translation nor-fra
type: translation
args: nor-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nor-fra
metrics:
- name: BLEU
type: bleu
value: 55.1
- name: chr-F
type: chrf
value: 0.73052
- task:
name: Translation nor-por
type: translation
args: nor-por
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nor-por
metrics:
- name: BLEU
type: bleu
value: 45.4
- name: chr-F
type: chrf
value: 0.67948
- task:
name: Translation nor-spa
type: translation
args: nor-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: nor-spa
metrics:
- name: BLEU
type: bleu
value: 55.3
- name: chr-F
type: chrf
value: 0.73320
- task:
name: Translation swe-deu
type: translation
args: swe-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: swe-deu
metrics:
- name: BLEU
type: bleu
value: 55.4
- name: chr-F
type: chrf
value: 0.71816
- task:
name: Translation swe-eng
type: translation
args: swe-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: swe-eng
metrics:
- name: BLEU
type: bleu
value: 64.8
- name: chr-F
type: chrf
value: 0.76648
- task:
name: Translation swe-fra
type: translation
args: swe-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: swe-fra
metrics:
- name: BLEU
type: bleu
value: 57.4
- name: chr-F
type: chrf
value: 0.72847
- task:
name: Translation swe-por
type: translation
args: swe-por
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: swe-por
metrics:
- name: BLEU
type: bleu
value: 50.3
- name: chr-F
type: chrf
value: 0.70554
- task:
name: Translation swe-spa
type: translation
args: swe-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: swe-spa
metrics:
- name: BLEU
type: bleu
value: 54.3
- name: chr-F
type: chrf
value: 0.70926
- task:
name: Translation isl-eng
type: translation
args: isl-eng
dataset:
name: newstest2021
type: wmt-2021-news
args: isl-eng
metrics:
- name: BLEU
type: bleu
value: 32.4
- name: chr-F
type: chrf
value: 0.56364
---
# opus-mt-tc-bible-big-gmq-deu_eng_fra_por_spa
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
- [Training](#training)
- [Evaluation](#evaluation)
- [Citation Information](#citation-information)
- [Acknowledgements](#acknowledgements)
## Model Details
Neural machine translation model for translating from North Germanic languages (gmq) to unknown (deu+eng+fra+por+spa).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
**Model Description:**
- **Developed by:** Language Technology Research Group at the University of Helsinki
- **Model Type:** Translation (transformer-big)
- **Release**: 2024-05-30
- **License:** Apache-2.0
- **Language(s):**
- Source Language(s): dan fao isl nno nob non nor swe
- Target Language(s): deu eng fra por spa
- Valid Target Language Labels: >>deu<< >>eng<< >>fra<< >>por<< >>spa<< >>xxx<<
- **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
- **Resources for more information:**
- [OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/gmq-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
- [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
- [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
- [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/)
- [HPLT bilingual data v1 (as part of the Tatoeba Translation Challenge dataset)](https://hplt-project.org/datasets/v1)
- [A massively parallel Bible corpus](https://aclanthology.org/L14-1215/)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>deu<<`
## Uses
This model can be used for translation and text-to-text generation.
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
## How to Get Started With the Model
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>deu<< Replace this with text in an accepted source language.",
">>spa<< This is the second sentence."
]
model_name = "pytorch-models/opus-mt-tc-bible-big-gmq-deu_eng_fra_por_spa"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-gmq-deu_eng_fra_por_spa")
print(pipe(">>deu<< Replace this with text in an accepted source language."))
```
## Training
- **Data**: opusTCv20230926max50+bt+jhubc ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
- **Pre-processing**: SentencePiece (spm32k,spm32k)
- **Model Type:** transformer-big
- **Original MarianNMT Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
## Evaluation
* [Model scores at the OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/gmq-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
* test set translations: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt)
* test set scores: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmq-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| dan-deu | tatoeba-test-v2021-08-07 | 0.74460 | 56.7 | 9998 | 76055 |
| dan-eng | tatoeba-test-v2021-08-07 | 0.77233 | 64.3 | 10795 | 79684 |
| dan-fra | tatoeba-test-v2021-08-07 | 0.76425 | 60.8 | 1731 | 11882 |
| dan-por | tatoeba-test-v2021-08-07 | 0.77248 | 60.0 | 873 | 5360 |
| dan-spa | tatoeba-test-v2021-08-07 | 0.72567 | 54.9 | 5000 | 35528 |
| fao-eng | tatoeba-test-v2021-08-07 | 0.54571 | 39.6 | 294 | 1984 |
| isl-deu | tatoeba-test-v2021-08-07 | 0.68535 | 51.4 | 969 | 6279 |
| isl-eng | tatoeba-test-v2021-08-07 | 0.67066 | 51.7 | 2503 | 19788 |
| isl-spa | tatoeba-test-v2021-08-07 | 0.65659 | 48.5 | 238 | 1229 |
| nno-eng | tatoeba-test-v2021-08-07 | 0.69415 | 55.5 | 460 | 3524 |
| nob-deu | tatoeba-test-v2021-08-07 | 0.69862 | 50.5 | 3525 | 33592 |
| nob-eng | tatoeba-test-v2021-08-07 | 0.72912 | 59.2 | 4539 | 36823 |
| nob-fra | tatoeba-test-v2021-08-07 | 0.71392 | 52.5 | 323 | 2269 |
| nob-spa | tatoeba-test-v2021-08-07 | 0.73300 | 55.1 | 885 | 6866 |
| nor-deu | tatoeba-test-v2021-08-07 | 0.69923 | 50.7 | 3651 | 34575 |
| nor-eng | tatoeba-test-v2021-08-07 | 0.72587 | 58.8 | 5000 | 40355 |
| nor-fra | tatoeba-test-v2021-08-07 | 0.73052 | 55.1 | 477 | 3213 |
| nor-por | tatoeba-test-v2021-08-07 | 0.67948 | 45.4 | 481 | 4182 |
| nor-spa | tatoeba-test-v2021-08-07 | 0.73320 | 55.3 | 960 | 7311 |
| swe-deu | tatoeba-test-v2021-08-07 | 0.71816 | 55.4 | 3410 | 23494 |
| swe-eng | tatoeba-test-v2021-08-07 | 0.76648 | 64.8 | 10362 | 68513 |
| swe-fra | tatoeba-test-v2021-08-07 | 0.72847 | 57.4 | 1407 | 9580 |
| swe-por | tatoeba-test-v2021-08-07 | 0.70554 | 50.3 | 320 | 2032 |
| swe-spa | tatoeba-test-v2021-08-07 | 0.70926 | 54.3 | 1351 | 8235 |
| dan-eng | flores101-devtest | 0.71193 | 47.6 | 1012 | 24721 |
| dan-fra | flores101-devtest | 0.63349 | 38.1 | 1012 | 28343 |
| dan-por | flores101-devtest | 0.62063 | 36.2 | 1012 | 26519 |
| dan-spa | flores101-devtest | 0.52557 | 24.2 | 1012 | 29199 |
| isl-deu | flores101-devtest | 0.50581 | 22.2 | 1012 | 25094 |
| isl-eng | flores101-devtest | 0.57294 | 31.6 | 1012 | 24721 |
| isl-por | flores101-devtest | 0.52192 | 25.8 | 1012 | 26519 |
| isl-spa | flores101-devtest | 0.46364 | 18.5 | 1012 | 29199 |
| nob-eng | flores101-devtest | 0.67120 | 42.6 | 1012 | 24721 |
| nob-fra | flores101-devtest | 0.60289 | 33.9 | 1012 | 28343 |
| nob-spa | flores101-devtest | 0.50848 | 21.9 | 1012 | 29199 |
| swe-deu | flores101-devtest | 0.60306 | 32.2 | 1012 | 25094 |
| swe-eng | flores101-devtest | 0.70404 | 47.9 | 1012 | 24721 |
| swe-por | flores101-devtest | 0.61418 | 35.7 | 1012 | 26519 |
| dan-deu | flores200-devtest | 0.60897 | 32.3 | 1012 | 25094 |
| dan-eng | flores200-devtest | 0.71641 | 48.2 | 1012 | 24721 |
| dan-fra | flores200-devtest | 0.63777 | 38.9 | 1012 | 28343 |
| dan-por | flores200-devtest | 0.62302 | 36.7 | 1012 | 26519 |
| dan-spa | flores200-devtest | 0.52803 | 24.4 | 1012 | 29199 |
| fao-deu | flores200-devtest | 0.41184 | 16.0 | 1012 | 25094 |
| fao-eng | flores200-devtest | 0.43308 | 21.2 | 1012 | 24721 |
| fao-por | flores200-devtest | 0.42649 | 19.0 | 1012 | 26519 |
| isl-deu | flores200-devtest | 0.51165 | 22.7 | 1012 | 25094 |
| isl-eng | flores200-devtest | 0.57745 | 32.2 | 1012 | 24721 |
| isl-fra | flores200-devtest | 0.54210 | 27.6 | 1012 | 28343 |
| isl-por | flores200-devtest | 0.52479 | 26.1 | 1012 | 26519 |
| isl-spa | flores200-devtest | 0.46837 | 19.2 | 1012 | 29199 |
| nno-deu | flores200-devtest | 0.58054 | 29.2 | 1012 | 25094 |
| nno-eng | flores200-devtest | 0.69114 | 45.0 | 1012 | 24721 |
| nno-fra | flores200-devtest | 0.61334 | 36.0 | 1012 | 28343 |
| nno-por | flores200-devtest | 0.60055 | 34.1 | 1012 | 26519 |
| nno-spa | flores200-devtest | 0.51190 | 22.8 | 1012 | 29199 |
| nob-deu | flores200-devtest | 0.57023 | 27.6 | 1012 | 25094 |
| nob-eng | flores200-devtest | 0.67540 | 43.1 | 1012 | 24721 |
| nob-fra | flores200-devtest | 0.60568 | 34.2 | 1012 | 28343 |
| nob-por | flores200-devtest | 0.59466 | 32.8 | 1012 | 26519 |
| nob-spa | flores200-devtest | 0.51138 | 22.4 | 1012 | 29199 |
| swe-deu | flores200-devtest | 0.60630 | 32.6 | 1012 | 25094 |
| swe-eng | flores200-devtest | 0.70584 | 48.1 | 1012 | 24721 |
| swe-fra | flores200-devtest | 0.63608 | 39.1 | 1012 | 28343 |
| swe-por | flores200-devtest | 0.62046 | 36.4 | 1012 | 26519 |
| swe-spa | flores200-devtest | 0.52328 | 23.9 | 1012 | 29199 |
| isl-eng | newstest2021 | 0.56364 | 32.4 | 1000 | 22529 |
| dan-deu | ntrex128 | 0.54229 | 25.3 | 1997 | 48761 |
| dan-eng | ntrex128 | 0.63083 | 38.7 | 1997 | 47673 |
| dan-fra | ntrex128 | 0.54088 | 26.2 | 1997 | 53481 |
| dan-por | ntrex128 | 0.53626 | 27.0 | 1997 | 51631 |
| dan-spa | ntrex128 | 0.56217 | 30.8 | 1997 | 54107 |
| fao-deu | ntrex128 | 0.41701 | 16.4 | 1997 | 48761 |
| fao-eng | ntrex128 | 0.47105 | 25.3 | 1997 | 47673 |
| fao-fra | ntrex128 | 0.40070 | 16.3 | 1997 | 53481 |
| fao-por | ntrex128 | 0.42005 | 18.0 | 1997 | 51631 |
| fao-spa | ntrex128 | 0.44085 | 20.5 | 1997 | 54107 |
| isl-deu | ntrex128 | 0.49932 | 20.5 | 1997 | 48761 |
| isl-eng | ntrex128 | 0.56856 | 29.7 | 1997 | 47673 |
| isl-fra | ntrex128 | 0.51998 | 24.6 | 1997 | 53481 |
| isl-por | ntrex128 | 0.49903 | 21.7 | 1997 | 51631 |
| isl-spa | ntrex128 | 0.53171 | 27.1 | 1997 | 54107 |
| nno-deu | ntrex128 | 0.53000 | 24.4 | 1997 | 48761 |
| nno-eng | ntrex128 | 0.65866 | 42.9 | 1997 | 47673 |
| nno-fra | ntrex128 | 0.54339 | 27.5 | 1997 | 53481 |
| nno-por | ntrex128 | 0.53242 | 26.3 | 1997 | 51631 |
| nno-spa | ntrex128 | 0.55889 | 30.4 | 1997 | 54107 |
| nob-deu | ntrex128 | 0.55549 | 26.8 | 1997 | 48761 |
| nob-eng | ntrex128 | 0.65580 | 40.9 | 1997 | 47673 |
| nob-fra | ntrex128 | 0.56187 | 29.2 | 1997 | 53481 |
| nob-por | ntrex128 | 0.54392 | 26.6 | 1997 | 51631 |
| nob-spa | ntrex128 | 0.57998 | 32.6 | 1997 | 54107 |
| swe-deu | ntrex128 | 0.55549 | 26.7 | 1997 | 48761 |
| swe-eng | ntrex128 | 0.66348 | 42.2 | 1997 | 47673 |
| swe-fra | ntrex128 | 0.56310 | 29.0 | 1997 | 53481 |
| swe-por | ntrex128 | 0.54965 | 27.8 | 1997 | 51631 |
| swe-spa | ntrex128 | 0.58035 | 32.8 | 1997 | 54107 |
## Citation Information
* Publications: [Democratizing neural machine translation with OPUS-MT](https://doi.org/10.1007/s10579-023-09704-w) and [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```bibtex
@article{tiedemann2023democratizing,
title={Democratizing neural machine translation with {OPUS-MT}},
author={Tiedemann, J{\"o}rg and Aulamo, Mikko and Bakshandaeva, Daria and Boggia, Michele and Gr{\"o}nroos, Stig-Arne and Nieminen, Tommi and Raganato, Alessandro and Scherrer, Yves and Vazquez, Raul and Virpioja, Sami},
journal={Language Resources and Evaluation},
number={58},
pages={713--755},
year={2023},
publisher={Springer Nature},
issn={1574-0218},
doi={10.1007/s10579-023-09704-w}
}
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Acknowledgements
The work is supported by the [HPLT project](https://hplt-project.org/), funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101070350. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland, and the [EuroHPC supercomputer LUMI](https://www.lumi-supercomputer.eu/).
## Model conversion info
* transformers version: 4.45.1
* OPUS-MT git hash: 0882077
* port time: Tue Oct 8 11:11:37 EEST 2024
* port machine: LM0-400-22516.local