ViNMT: Neural Machine Translation Toolkit
This toolkit addresses the need for accessible and versatile tools for machine translation researchers and practitioners, but it is incremental as it builds on existing methods.
The authors developed an open-source toolkit for neural machine translation, based on the Transformer architecture with improvements, to provide a comprehensive framework for bilingual and multilingual translation tasks, including model building, inference, and deployment.
We present an open-source toolkit for neural machine translation (NMT). The new toolkit is mainly based on vaulted Transformer (Vaswani et al., 2017) along with many other improvements detailed below, in order to create a self-contained, simple to use, consistent and comprehensive framework for Machine Translation tasks of various domains. It is tooled to support both bilingual and multilingual translation tasks, starting from building the model from respective corpora, to inferring new predictions or packaging the model to serving-capable JIT format.