metadata
library_name: transformers
language:
- aa
- am
- ar
- arc
- bcw
- byn
- cop
- daa
- de
- dsh
- en
- es
- fr
- gde
- gnd
- ha
- hbo
- he
- hig
- irk
- jpa
- kab
- ker
- kqp
- ktb
- kxc
- lln
- lme
- meq
- mfh
- mfi
- mfk
- mif
- mpg
- mqb
- mt
- muy
- oar
- om
- pbi
- phn
- pt
- rif
- sgw
- shi
- shy
- so
- sur
- syc
- syr
- taq
- thv
- ti
- tig
- tmc
- tmh
- tmr
- ttr
- tzm
- wal
- xed
- zgh
tags:
- translation
- opus-mt-tc-bible
license: apache-2.0
model-index:
- name: opus-mt-tc-bible-big-afa-deu_eng_fra_por_spa
results:
- task:
name: Translation acm-deu
type: translation
args: acm-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: acm-deu
metrics:
- name: BLEU
type: bleu
value: 17.6
- name: chr-F
type: chrf
value: 0.48947
- task:
name: Translation acm-eng
type: translation
args: acm-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: acm-eng
metrics:
- name: BLEU
type: bleu
value: 28.5
- name: chr-F
type: chrf
value: 0.56799
- task:
name: Translation acm-fra
type: translation
args: acm-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: acm-fra
metrics:
- name: BLEU
type: bleu
value: 26.1
- name: chr-F
type: chrf
value: 0.53577
- task:
name: Translation acm-por
type: translation
args: acm-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: acm-por
metrics:
- name: BLEU
type: bleu
value: 23.9
- name: chr-F
type: chrf
value: 0.52441
- task:
name: Translation acm-spa
type: translation
args: acm-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: acm-spa
metrics:
- name: BLEU
type: bleu
value: 18.2
- name: chr-F
type: chrf
value: 0.46985
- task:
name: Translation amh-deu
type: translation
args: amh-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: amh-deu
metrics:
- name: BLEU
type: bleu
value: 12.6
- name: chr-F
type: chrf
value: 0.41553
- task:
name: Translation amh-eng
type: translation
args: amh-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: amh-eng
metrics:
- name: BLEU
type: bleu
value: 22.5
- name: chr-F
type: chrf
value: 0.49333
- task:
name: Translation amh-fra
type: translation
args: amh-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: amh-fra
metrics:
- name: BLEU
type: bleu
value: 17.8
- name: chr-F
type: chrf
value: 0.4489
- task:
name: Translation amh-por
type: translation
args: amh-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: amh-por
metrics:
- name: BLEU
type: bleu
value: 16.5
- name: chr-F
type: chrf
value: 0.43771
- task:
name: Translation amh-spa
type: translation
args: amh-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: amh-spa
metrics:
- name: BLEU
type: bleu
value: 12.8
- name: chr-F
type: chrf
value: 0.39526
- task:
name: Translation apc-deu
type: translation
args: apc-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: apc-deu
metrics:
- name: BLEU
type: bleu
value: 16
- name: chr-F
type: chrf
value: 0.4748
- task:
name: Translation apc-eng
type: translation
args: apc-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: apc-eng
metrics:
- name: BLEU
type: bleu
value: 28.1
- name: chr-F
type: chrf
value: 0.56075
- task:
name: Translation apc-fra
type: translation
args: apc-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: apc-fra
metrics:
- name: BLEU
type: bleu
value: 24.6
- name: chr-F
type: chrf
value: 0.52325
- task:
name: Translation apc-por
type: translation
args: apc-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: apc-por
metrics:
- name: BLEU
type: bleu
value: 22.9
- name: chr-F
type: chrf
value: 0.51055
- task:
name: Translation apc-spa
type: translation
args: apc-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: apc-spa
metrics:
- name: BLEU
type: bleu
value: 17.2
- name: chr-F
type: chrf
value: 0.45634
- task:
name: Translation arz-deu
type: translation
args: arz-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: arz-deu
metrics:
- name: BLEU
type: bleu
value: 14.1
- name: chr-F
type: chrf
value: 0.45844
- task:
name: Translation arz-eng
type: translation
args: arz-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: arz-eng
metrics:
- name: BLEU
type: bleu
value: 22.7
- name: chr-F
type: chrf
value: 0.52534
- task:
name: Translation arz-fra
type: translation
args: arz-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: arz-fra
metrics:
- name: BLEU
type: bleu
value: 21.8
- name: chr-F
type: chrf
value: 0.50336
- task:
name: Translation arz-por
type: translation
args: arz-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: arz-por
metrics:
- name: BLEU
type: bleu
value: 20
- name: chr-F
type: chrf
value: 0.48741
- task:
name: Translation arz-spa
type: translation
args: arz-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: arz-spa
metrics:
- name: BLEU
type: bleu
value: 15.8
- name: chr-F
type: chrf
value: 0.44516
- task:
name: Translation hau-eng
type: translation
args: hau-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: hau-eng
metrics:
- name: BLEU
type: bleu
value: 23.4
- name: chr-F
type: chrf
value: 0.48137
- task:
name: Translation hau-fra
type: translation
args: hau-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: hau-fra
metrics:
- name: BLEU
type: bleu
value: 17.2
- name: chr-F
type: chrf
value: 0.42981
- task:
name: Translation hau-por
type: translation
args: hau-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: hau-por
metrics:
- name: BLEU
type: bleu
value: 15.7
- name: chr-F
type: chrf
value: 0.41385
- task:
name: Translation hau-spa
type: translation
args: hau-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: hau-spa
metrics:
- name: BLEU
type: bleu
value: 11.7
- name: chr-F
type: chrf
value: 0.378
- task:
name: Translation heb-deu
type: translation
args: heb-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: heb-deu
metrics:
- name: BLEU
type: bleu
value: 22.8
- name: chr-F
type: chrf
value: 0.53482
- task:
name: Translation heb-eng
type: translation
args: heb-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: heb-eng
metrics:
- name: BLEU
type: bleu
value: 38
- name: chr-F
type: chrf
value: 0.63368
- task:
name: Translation heb-fra
type: translation
args: heb-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: heb-fra
metrics:
- name: BLEU
type: bleu
value: 32.6
- name: chr-F
type: chrf
value: 0.58417
- task:
name: Translation heb-por
type: translation
args: heb-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: heb-por
metrics:
- name: BLEU
type: bleu
value: 30.7
- name: chr-F
type: chrf
value: 0.5714
- task:
name: Translation kab-eng
type: translation
args: kab-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: kab-eng
metrics:
- name: BLEU
type: bleu
value: 10
- name: chr-F
type: chrf
value: 0.32121
- task:
name: Translation mlt-eng
type: translation
args: mlt-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: mlt-eng
metrics:
- name: BLEU
type: bleu
value: 51.1
- name: chr-F
type: chrf
value: 0.73415
- task:
name: Translation mlt-fra
type: translation
args: mlt-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: mlt-fra
metrics:
- name: BLEU
type: bleu
value: 35.8
- name: chr-F
type: chrf
value: 0.61626
- task:
name: Translation mlt-spa
type: translation
args: mlt-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: mlt-spa
metrics:
- name: BLEU
type: bleu
value: 21.8
- name: chr-F
type: chrf
value: 0.50534
- task:
name: Translation som-eng
type: translation
args: som-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: som-eng
metrics:
- name: BLEU
type: bleu
value: 17.7
- name: chr-F
type: chrf
value: 0.42764
- task:
name: Translation som-fra
type: translation
args: som-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: som-fra
metrics:
- name: BLEU
type: bleu
value: 14.4
- name: chr-F
type: chrf
value: 0.39536
- task:
name: Translation som-por
type: translation
args: som-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: som-por
metrics:
- name: BLEU
type: bleu
value: 14.1
- name: chr-F
type: chrf
value: 0.3944
- task:
name: Translation som-spa
type: translation
args: som-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: som-spa
metrics:
- name: BLEU
type: bleu
value: 10
- name: chr-F
type: chrf
value: 0.35321
- task:
name: Translation tir-eng
type: translation
args: tir-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: tir-eng
metrics:
- name: BLEU
type: bleu
value: 11.6
- name: chr-F
type: chrf
value: 0.37119
- task:
name: Translation amh-deu
type: translation
args: amh-deu
dataset:
name: flores101-devtest
type: flores_101
args: amh deu devtest
metrics:
- name: BLEU
type: bleu
value: 11.5
- name: chr-F
type: chrf
value: 0.3989
- task:
name: Translation amh-eng
type: translation
args: amh-eng
dataset:
name: flores101-devtest
type: flores_101
args: amh eng devtest
metrics:
- name: BLEU
type: bleu
value: 21
- name: chr-F
type: chrf
value: 0.47357
- task:
name: Translation amh-fra
type: translation
args: amh-fra
dataset:
name: flores101-devtest
type: flores_101
args: amh fra devtest
metrics:
- name: BLEU
type: bleu
value: 16.2
- name: chr-F
type: chrf
value: 0.43155
- task:
name: Translation amh-por
type: translation
args: amh-por
dataset:
name: flores101-devtest
type: flores_101
args: amh por devtest
metrics:
- name: BLEU
type: bleu
value: 15.1
- name: chr-F
type: chrf
value: 0.42109
- task:
name: Translation amh-spa
type: translation
args: amh-spa
dataset:
name: flores101-devtest
type: flores_101
args: amh spa devtest
metrics:
- name: BLEU
type: bleu
value: 11.5
- name: chr-F
type: chrf
value: 0.38003
- task:
name: Translation ara-deu
type: translation
args: ara-deu
dataset:
name: flores101-devtest
type: flores_101
args: ara deu devtest
metrics:
- name: BLEU
type: bleu
value: 20.4
- name: chr-F
type: chrf
value: 0.5111
- task:
name: Translation ara-fra
type: translation
args: ara-fra
dataset:
name: flores101-devtest
type: flores_101
args: ara fra devtest
metrics:
- name: BLEU
type: bleu
value: 29.7
- name: chr-F
type: chrf
value: 0.56934
- task:
name: Translation ara-por
type: translation
args: ara-por
dataset:
name: flores101-devtest
type: flores_101
args: ara por devtest
metrics:
- name: BLEU
type: bleu
value: 28.2
- name: chr-F
type: chrf
value: 0.55727
- task:
name: Translation ara-spa
type: translation
args: ara-spa
dataset:
name: flores101-devtest
type: flores_101
args: ara spa devtest
metrics:
- name: BLEU
type: bleu
value: 19.5
- name: chr-F
type: chrf
value: 0.4835
- task:
name: Translation hau-eng
type: translation
args: hau-eng
dataset:
name: flores101-devtest
type: flores_101
args: hau eng devtest
metrics:
- name: BLEU
type: bleu
value: 21.6
- name: chr-F
type: chrf
value: 0.46804
- task:
name: Translation hau-fra
type: translation
args: hau-fra
dataset:
name: flores101-devtest
type: flores_101
args: hau fra devtest
metrics:
- name: BLEU
type: bleu
value: 15.9
- name: chr-F
type: chrf
value: 0.41827
- task:
name: Translation hau-spa
type: translation
args: hau-spa
dataset:
name: flores101-devtest
type: flores_101
args: hau spa devtest
metrics:
- name: BLEU
type: bleu
value: 11.5
- name: chr-F
type: chrf
value: 0.37201
- task:
name: Translation heb-eng
type: translation
args: heb-eng
dataset:
name: flores101-devtest
type: flores_101
args: heb eng devtest
metrics:
- name: BLEU
type: bleu
value: 36.6
- name: chr-F
type: chrf
value: 0.62422
- task:
name: Translation mlt-eng
type: translation
args: mlt-eng
dataset:
name: flores101-devtest
type: flores_101
args: mlt eng devtest
metrics:
- name: BLEU
type: bleu
value: 49.1
- name: chr-F
type: chrf
value: 0.7239
- task:
name: Translation mlt-fra
type: translation
args: mlt-fra
dataset:
name: flores101-devtest
type: flores_101
args: mlt fra devtest
metrics:
- name: BLEU
type: bleu
value: 34.7
- name: chr-F
type: chrf
value: 0.6084
- task:
name: Translation mlt-por
type: translation
args: mlt-por
dataset:
name: flores101-devtest
type: flores_101
args: mlt por devtest
metrics:
- name: BLEU
type: bleu
value: 31.8
- name: chr-F
type: chrf
value: 0.59863
- task:
name: Translation amh-eng
type: translation
args: amh-eng
dataset:
name: ntrex128
type: ntrex128
args: amh-eng
metrics:
- name: BLEU
type: bleu
value: 15
- name: chr-F
type: chrf
value: 0.42042
- task:
name: Translation amh-fra
type: translation
args: amh-fra
dataset:
name: ntrex128
type: ntrex128
args: amh-fra
metrics:
- name: BLEU
type: bleu
value: 10.8
- name: chr-F
type: chrf
value: 0.37274
- task:
name: Translation amh-spa
type: translation
args: amh-spa
dataset:
name: ntrex128
type: ntrex128
args: amh-spa
metrics:
- name: BLEU
type: bleu
value: 12.1
- name: chr-F
type: chrf
value: 0.38306
- task:
name: Translation hau-eng
type: translation
args: hau-eng
dataset:
name: ntrex128
type: ntrex128
args: hau-eng
metrics:
- name: BLEU
type: bleu
value: 26.1
- name: chr-F
type: chrf
value: 0.50349
- task:
name: Translation hau-fra
type: translation
args: hau-fra
dataset:
name: ntrex128
type: ntrex128
args: hau-fra
metrics:
- name: BLEU
type: bleu
value: 15.8
- name: chr-F
type: chrf
value: 0.41837
- task:
name: Translation hau-por
type: translation
args: hau-por
dataset:
name: ntrex128
type: ntrex128
args: hau-por
metrics:
- name: BLEU
type: bleu
value: 15.3
- name: chr-F
type: chrf
value: 0.40851
- task:
name: Translation hau-spa
type: translation
args: hau-spa
dataset:
name: ntrex128
type: ntrex128
args: hau-spa
metrics:
- name: BLEU
type: bleu
value: 18.5
- name: chr-F
type: chrf
value: 0.43376
- task:
name: Translation heb-deu
type: translation
args: heb-deu
dataset:
name: ntrex128
type: ntrex128
args: heb-deu
metrics:
- name: BLEU
type: bleu
value: 17.7
- name: chr-F
type: chrf
value: 0.49482
- task:
name: Translation heb-eng
type: translation
args: heb-eng
dataset:
name: ntrex128
type: ntrex128
args: heb-eng
metrics:
- name: BLEU
type: bleu
value: 31.3
- name: chr-F
type: chrf
value: 0.59241
- task:
name: Translation heb-fra
type: translation
args: heb-fra
dataset:
name: ntrex128
type: ntrex128
args: heb-fra
metrics:
- name: BLEU
type: bleu
value: 24
- name: chr-F
type: chrf
value: 0.5218
- task:
name: Translation heb-por
type: translation
args: heb-por
dataset:
name: ntrex128
type: ntrex128
args: heb-por
metrics:
- name: BLEU
type: bleu
value: 23.2
- name: chr-F
type: chrf
value: 0.51248
- task:
name: Translation mlt-spa
type: translation
args: mlt-spa
dataset:
name: ntrex128
type: ntrex128
args: mlt-spa
metrics:
- name: BLEU
type: bleu
value: 30.9
- name: chr-F
type: chrf
value: 0.57078
- task:
name: Translation som-deu
type: translation
args: som-deu
dataset:
name: ntrex128
type: ntrex128
args: som-deu
metrics:
- name: BLEU
type: bleu
value: 11
- name: chr-F
type: chrf
value: 0.39394
- task:
name: Translation som-eng
type: translation
args: som-eng
dataset:
name: ntrex128
type: ntrex128
args: som-eng
metrics:
- name: BLEU
type: bleu
value: 24.3
- name: chr-F
type: chrf
value: 0.49187
- task:
name: Translation som-fra
type: translation
args: som-fra
dataset:
name: ntrex128
type: ntrex128
args: som-fra
metrics:
- name: BLEU
type: bleu
value: 15.1
- name: chr-F
type: chrf
value: 0.41236
- task:
name: Translation som-por
type: translation
args: som-por
dataset:
name: ntrex128
type: ntrex128
args: som-por
metrics:
- name: BLEU
type: bleu
value: 15.2
- name: chr-F
type: chrf
value: 0.4155
- task:
name: Translation som-spa
type: translation
args: som-spa
dataset:
name: ntrex128
type: ntrex128
args: som-spa
metrics:
- name: BLEU
type: bleu
value: 17.6
- name: chr-F
type: chrf
value: 0.43278
- task:
name: Translation tir-eng
type: translation
args: tir-eng
dataset:
name: ntrex128
type: ntrex128
args: tir-eng
metrics:
- name: BLEU
type: bleu
value: 12.5
- name: chr-F
type: chrf
value: 0.37185
- task:
name: Translation tir-spa
type: translation
args: tir-spa
dataset:
name: ntrex128
type: ntrex128
args: tir-spa
metrics:
- name: BLEU
type: bleu
value: 10.2
- name: chr-F
type: chrf
value: 0.34985
- task:
name: Translation amh-eng
type: translation
args: amh-eng
dataset:
name: tatoeba-test-v2021-03-30
type: tatoeba_mt
args: amh-eng
metrics:
- name: BLEU
type: bleu
value: 59.5
- name: chr-F
type: chrf
value: 0.70202
- task:
name: Translation ara-deu
type: translation
args: ara-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ara-deu
metrics:
- name: BLEU
type: bleu
value: 41.7
- name: chr-F
type: chrf
value: 0.61039
- task:
name: Translation ara-eng
type: translation
args: ara-eng
dataset:
name: tatoeba-test-v2020-07-28
type: tatoeba_mt
args: ara-eng
metrics:
- name: BLEU
type: bleu
value: 42.8
- name: chr-F
type: chrf
value: 0.60134
- task:
name: Translation ara-fra
type: translation
args: ara-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ara-fra
metrics:
- name: BLEU
type: bleu
value: 38.8
- name: chr-F
type: chrf
value: 0.5612
- task:
name: Translation ara-spa
type: translation
args: ara-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: ara-spa
metrics:
- name: BLEU
type: bleu
value: 43.7
- name: chr-F
type: chrf
value: 0.62567
- task:
name: Translation heb-deu
type: translation
args: heb-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: heb-deu
metrics:
- name: BLEU
type: bleu
value: 42.4
- name: chr-F
type: chrf
value: 0.63131
- task:
name: Translation heb-eng
type: translation
args: heb-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: heb-eng
metrics:
- name: BLEU
type: bleu
value: 49.2
- name: chr-F
type: chrf
value: 0.6496
- task:
name: Translation heb-fra
type: translation
args: heb-fra
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: heb-fra
metrics:
- name: BLEU
type: bleu
value: 46.3
- name: chr-F
type: chrf
value: 0.64348
- task:
name: Translation heb-por
type: translation
args: heb-por
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: heb-por
metrics:
- name: BLEU
type: bleu
value: 43.2
- name: chr-F
type: chrf
value: 0.6335
- task:
name: Translation kab-eng
type: translation
args: kab-eng
dataset:
name: tatoeba-test-v2021-03-30
type: tatoeba_mt
args: kab-eng
metrics:
- name: BLEU
type: bleu
value: 27.8
- name: chr-F
type: chrf
value: 0.44646
- task:
name: Translation kab-spa
type: translation
args: kab-spa
dataset:
name: tatoeba-test-v2020-07-28
type: tatoeba_mt
args: kab-spa
metrics:
- name: BLEU
type: bleu
value: 23.4
- name: chr-F
type: chrf
value: 0.41526
- task:
name: Translation mlt-eng
type: translation
args: mlt-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: mlt-eng
metrics:
- name: BLEU
type: bleu
value: 51
- name: chr-F
type: chrf
value: 0.66653
- 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: 34
- name: chr-F
type: chrf
value: 0.51369
- task:
name: Translation hau-eng
type: translation
args: hau-eng
dataset:
name: newstest2021
type: wmt-2021-news
args: hau-eng
metrics:
- name: BLEU
type: bleu
value: 15.5
- name: chr-F
type: chrf
value: 0.43744
opus-mt-tc-bible-big-afa-deu_eng_fra_por_spa
Table of Contents
- Model Details
- Uses
- Risks, Limitations and Biases
- How to Get Started With the Model
- Training
- Evaluation
- Citation Information
- Acknowledgements
Model Details
Neural machine translation model for translating from Afro-Asiatic languages (afa) to unknown (deu+eng+fra+por+spa).
This model is part of the OPUS-MT project, 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, 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 and training pipelines use the procedures of OPUS-MT-train. Model Description:
- Developed by: Language Technology Research Group at the University of Helsinki
- Model Type: Translation (transformer-big)
- Release: 2024-05-29
- License: Apache-2.0
- Language(s):
- Source Language(s): aar acm afb amh apc ara arc arq arz bcw byn cop daa dsh gde gnd hau hbo heb hig irk jpa kab ker kqp ktb kxc lln lme meq mfh mfi mfk mif mlt mpg mqb muy oar orm pbi phn rif sgw shi shy som sur syc syr taq thv tig tir tmc tmh tmr ttr tzm wal xed zgh
- 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_2024-05-29.zip
- Resources for more information:
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) and Bender et al. (2021)).
How to Get Started With the Model
A short example code:
from transformers import MarianMTModel, MarianTokenizer
src_text = [
">>eng<< Anta i ak-d-yennan ur yerbiḥ ara Tom?",
">>fra<< Iselman d aɣbalu axatar i wučči n yemdanen."
]
model_name = "pytorch-models/opus-mt-tc-bible-big-afa-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) )
# expected output:
# Who told you that he didn't?
# L'eau est une source importante de nourriture pour les gens.
You can also use OPUS-MT models with the transformers pipelines, for example:
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-afa-deu_eng_fra_por_spa")
print(pipe(">>eng<< Anta i ak-d-yennan ur yerbiḥ ara Tom?"))
# expected output: Who told you that he didn't?
Training
- Data: opusTCv20230926max50+bt+jhubc (source)
- Pre-processing: SentencePiece (spm32k,spm32k)
- Model Type: transformer-big
- Original MarianNMT Model: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip
- Training Scripts: GitHub Repo
Evaluation
- Model scores at the OPUS-MT dashboard
- test set translations: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt
- test set scores: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt
- benchmark results: benchmark_results.txt
- benchmark output: benchmark_translations.zip
| langpair | testset | chr-F | BLEU | #sent | #words |
|---|---|---|---|---|---|
| ara-deu | tatoeba-test-v2021-08-07 | 0.61039 | 41.7 | 1209 | 8371 |
| ara-eng | tatoeba-test-v2021-08-07 | 5.430 | 0.0 | 10305 | 76975 |
| ara-fra | tatoeba-test-v2021-08-07 | 0.56120 | 38.8 | 1569 | 11066 |
| ara-spa | tatoeba-test-v2021-08-07 | 0.62567 | 43.7 | 1511 | 9708 |
| heb-deu | tatoeba-test-v2021-08-07 | 0.63131 | 42.4 | 3090 | 25101 |
| heb-eng | tatoeba-test-v2021-08-07 | 0.64960 | 49.2 | 10519 | 77427 |
| heb-fra | tatoeba-test-v2021-08-07 | 0.64348 | 46.3 | 3281 | 26123 |
| heb-por | tatoeba-test-v2021-08-07 | 0.63350 | 43.2 | 719 | 5335 |
| mlt-eng | tatoeba-test-v2021-08-07 | 0.66653 | 51.0 | 203 | 1165 |
| amh-eng | flores101-devtest | 0.47357 | 21.0 | 1012 | 24721 |
| amh-fra | flores101-devtest | 0.43155 | 16.2 | 1012 | 28343 |
| amh-por | flores101-devtest | 0.42109 | 15.1 | 1012 | 26519 |
| ara-deu | flores101-devtest | 0.51110 | 20.4 | 1012 | 25094 |
| ara-fra | flores101-devtest | 0.56934 | 29.7 | 1012 | 28343 |
| ara-por | flores101-devtest | 0.55727 | 28.2 | 1012 | 26519 |
| ara-spa | flores101-devtest | 0.48350 | 19.5 | 1012 | 29199 |
| hau-eng | flores101-devtest | 0.46804 | 21.6 | 1012 | 24721 |
| hau-fra | flores101-devtest | 0.41827 | 15.9 | 1012 | 28343 |
| heb-eng | flores101-devtest | 0.62422 | 36.6 | 1012 | 24721 |
| mlt-eng | flores101-devtest | 0.72390 | 49.1 | 1012 | 24721 |
| mlt-fra | flores101-devtest | 0.60840 | 34.7 | 1012 | 28343 |
| mlt-por | flores101-devtest | 0.59863 | 31.8 | 1012 | 26519 |
| acm-deu | flores200-devtest | 0.48947 | 17.6 | 1012 | 25094 |
| acm-eng | flores200-devtest | 0.56799 | 28.5 | 1012 | 24721 |
| acm-fra | flores200-devtest | 0.53577 | 26.1 | 1012 | 28343 |
| acm-por | flores200-devtest | 0.52441 | 23.9 | 1012 | 26519 |
| acm-spa | flores200-devtest | 0.46985 | 18.2 | 1012 | 29199 |
| amh-deu | flores200-devtest | 0.41553 | 12.6 | 1012 | 25094 |
| amh-eng | flores200-devtest | 0.49333 | 22.5 | 1012 | 24721 |
| amh-fra | flores200-devtest | 0.44890 | 17.8 | 1012 | 28343 |
| amh-por | flores200-devtest | 0.43771 | 16.5 | 1012 | 26519 |
| apc-deu | flores200-devtest | 0.47480 | 16.0 | 1012 | 25094 |
| apc-eng | flores200-devtest | 0.56075 | 28.1 | 1012 | 24721 |
| apc-fra | flores200-devtest | 0.52325 | 24.6 | 1012 | 28343 |
| apc-por | flores200-devtest | 0.51055 | 22.9 | 1012 | 26519 |
| apc-spa | flores200-devtest | 0.45634 | 17.2 | 1012 | 29199 |
| arz-deu | flores200-devtest | 0.45844 | 14.1 | 1012 | 25094 |
| arz-eng | flores200-devtest | 0.52534 | 22.7 | 1012 | 24721 |
| arz-fra | flores200-devtest | 0.50336 | 21.8 | 1012 | 28343 |
| arz-por | flores200-devtest | 0.48741 | 20.0 | 1012 | 26519 |
| arz-spa | flores200-devtest | 0.44516 | 15.8 | 1012 | 29199 |
| hau-eng | flores200-devtest | 0.48137 | 23.4 | 1012 | 24721 |
| hau-fra | flores200-devtest | 0.42981 | 17.2 | 1012 | 28343 |
| hau-por | flores200-devtest | 0.41385 | 15.7 | 1012 | 26519 |
| heb-deu | flores200-devtest | 0.53482 | 22.8 | 1012 | 25094 |
| heb-eng | flores200-devtest | 0.63368 | 38.0 | 1012 | 24721 |
| heb-fra | flores200-devtest | 0.58417 | 32.6 | 1012 | 28343 |
| heb-por | flores200-devtest | 0.57140 | 30.7 | 1012 | 26519 |
| mlt-eng | flores200-devtest | 0.73415 | 51.1 | 1012 | 24721 |
| mlt-fra | flores200-devtest | 0.61626 | 35.8 | 1012 | 28343 |
| mlt-spa | flores200-devtest | 0.50534 | 21.8 | 1012 | 29199 |
| som-eng | flores200-devtest | 0.42764 | 17.7 | 1012 | 24721 |
| tir-por | flores200-devtest | 2.931 | 0.0 | 1012 | 26519 |
| hau-eng | newstest2021 | 0.43744 | 15.5 | 997 | 27372 |
| amh-eng | ntrex128 | 0.42042 | 15.0 | 1997 | 47673 |
| hau-eng | ntrex128 | 0.50349 | 26.1 | 1997 | 47673 |
| hau-fra | ntrex128 | 0.41837 | 15.8 | 1997 | 53481 |
| hau-por | ntrex128 | 0.40851 | 15.3 | 1997 | 51631 |
| hau-spa | ntrex128 | 0.43376 | 18.5 | 1997 | 54107 |
| heb-deu | ntrex128 | 0.49482 | 17.7 | 1997 | 48761 |
| heb-eng | ntrex128 | 0.59241 | 31.3 | 1997 | 47673 |
| heb-fra | ntrex128 | 0.52180 | 24.0 | 1997 | 53481 |
| heb-por | ntrex128 | 0.51248 | 23.2 | 1997 | 51631 |
| mlt-spa | ntrex128 | 0.57078 | 30.9 | 1997 | 54107 |
| som-eng | ntrex128 | 0.49187 | 24.3 | 1997 | 47673 |
| som-fra | ntrex128 | 0.41236 | 15.1 | 1997 | 53481 |
| som-por | ntrex128 | 0.41550 | 15.2 | 1997 | 51631 |
| som-spa | ntrex128 | 0.43278 | 17.6 | 1997 | 54107 |
| tir-eng | tico19-test | 2.655 | 0.0 | 2100 | 56824 |
Citation Information
- Publications: Democratizing neural machine translation with OPUS-MT and OPUS-MT – Building open translation services for the World and The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT (Please, cite if you use this model.)
@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, 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, Finland, and the EuroHPC supercomputer LUMI.
Model conversion info
- transformers version: 4.45.1
- OPUS-MT git hash: a0ea3b3
- port time: Mon Oct 7 17:08:30 EEST 2024
- port machine: LM0-400-22516.local