Instructions to use tartuNLP/synest-fully-modular with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Fairseq
How to use tartuNLP/synest-fully-modular with Fairseq:
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub models, cfg, task = load_model_ensemble_and_task_from_hf_hub( "tartuNLP/synest-fully-modular" ) - Notebooks
- Google Colab
- Kaggle
SynEst fully modular translation model
The SynEst models are machine translation models focused on translating from and into the Estonian language.
The model uses a modular architecture, where each language has its own encoder and decoder that is used for all translation directions.
Languages
Translation directions: et-en, en-et, et-de, de-et,
et-fi, fi-et, et-ru, ru-et, et-uk, uk-et.
Model Card Authors [optional]
@lisskor