search

Caucasus-Rosetta / Lingua-Corpus

Caucasus languages focused multilingual and monolingual corpuses for Natural Language Processing(NLP)
Apache License 2.0
33 stars 6 forks source link

Train NMT domain specific ru-ab model #69

Closed danielinux7 closed 2 years ago

danielinux7 commented 3 years ago

Ахҳәаа

A domain specific NMT translator is needed to localize applications.

Ауадаҩрақәа

  1. Include additional characters and symbols to the AI memory.
  2. Augmenting the additional parallel corpus.

Аӡбара

update_vocab the model ru-ab Augment the extracted parallel corpus from applications to the training dataset.

Азхьарԥшқәа:

https://www.kaggle.com/nartaa/ru-ab-transformer-v6-v10-v3