opus-2020-07-14.yml

release: eng-trk/opus-2020-07-14.zip
release-date: 2020-07-14
dataset-name: opus
modeltype: transformer
pre-processing: normalization + SentencePiece (spm32k,spm32k)
subwords:
   source: spm32k
   target: spm32k
subword-models:
   source: source.spm
   target: target.spm
source-languages:
   - eng
target-languages:
   - aze
   - bak
   - chv
   - crh
   - kaz
   - kir
   - kjh
   - kum
   - ota
   - sah
   - tat
   - tuk
   - tur
   - tyv
   - uig
   - uzb
use-target-labels:
   - ">>aze_Latn<<"
   - ">>bak<<"
   - ">>chv<<"
   - ">>crh<<"
   - ">>crh_Latn<<"
   - ">>kaz_Cyrl<<"
   - ">>kaz_Latn<<"
   - ">>kir_Cyrl<<"
   - ">>kjh<<"
   - ">>kum<<"
   - ">>ota_Arab<<"
   - ">>ota_Latn<<"
   - ">>sah<<"
   - ">>tat<<"
   - ">>tat_Arab<<"
   - ">>tat_Latn<<"
   - ">>tuk<<"
   - ">>tuk_Latn<<"
   - ">>tur<<"
   - ">>tyv<<"
   - ">>uig_Arab<<"
   - ">>uig_Cyrl<<"
   - ">>uzb_Cyrl<<"
   - ">>uzb_Latn<<"
test-data:
   Tatoeba-test.eng-aze: 2659/10046
   Tatoeba-test.eng-bak: 39/140
   Tatoeba-test.eng-chv: 333/1358
   Tatoeba-test.eng-crh: 22/81
   Tatoeba-test.eng-kaz: 397/1668
   Tatoeba-test.eng-kir: 118/428
   Tatoeba-test.eng-kjh: 17/48
   Tatoeba-test.eng-kum: 8/25
   Tatoeba-test.eng-multi: 10000/46183
   Tatoeba-test.eng-ota: 678/3328
   Tatoeba-test.eng-sah: 39/131
   Tatoeba-test.eng-tat: 1451/6996
   Tatoeba-test.eng-tuk: 2500/12809
   Tatoeba-test.eng-tur: 10000/49076
   Tatoeba-test.eng-tyv: 5/19
   Tatoeba-test.eng-uig: 3024/13084
   Tatoeba-test.eng-uzb: 457/1514
BLEU-scores:
   Tatoeba-test.eng-aze: 25.7
   Tatoeba-test.eng-bak: 5.2
   Tatoeba-test.eng-chv: 3.7
   Tatoeba-test.eng-crh: 7.4
   Tatoeba-test.eng-kaz: 11.4
   Tatoeba-test.eng-kir: 25.4
   Tatoeba-test.eng-kjh: 1.3
   Tatoeba-test.eng-kum: 2.2
   Tatoeba-test.eng-multi: 18.0
   Tatoeba-test.eng-ota: 0.2
   Tatoeba-test.eng-sah: 0.5
   Tatoeba-test.eng-tat: 9.7
   Tatoeba-test.eng-tuk: 5.6
   Tatoeba-test.eng-tur: 32.1
   Tatoeba-test.eng-tyv: 4.8
   Tatoeba-test.eng-uig: 0.1
   Tatoeba-test.eng-uzb: 3.3
chr-F-scores:
   Tatoeba-test.eng-aze: 0.560
   Tatoeba-test.eng-bak: 0.267
   Tatoeba-test.eng-chv: 0.264
   Tatoeba-test.eng-crh: 0.301
   Tatoeba-test.eng-kaz: 0.353
   Tatoeba-test.eng-kir: 0.496
   Tatoeba-test.eng-kjh: 0.035
   Tatoeba-test.eng-kum: 0.046
   Tatoeba-test.eng-multi: 0.436
   Tatoeba-test.eng-ota: 0.059
   Tatoeba-test.eng-sah: 0.021
   Tatoeba-test.eng-tat: 0.304
   Tatoeba-test.eng-tuk: 0.305
   Tatoeba-test.eng-tur: 0.602
   Tatoeba-test.eng-tyv: 0.224
   Tatoeba-test.eng-uig: 0.150
   Tatoeba-test.eng-uzb: 0.264