Language-Translation

1. Combination of different NMT architectures for Machine Translation Task. Currently, GCNN (Gated Convolution Neural Network) model is completed for German to English Translation and it has a BLEU score of 32.4.
2. BERT-base model is completed.
3. English to Hindi CNN Sequence to Sequence Model is trained with MultiIndic Language Corpus. Performance evaluation is left.
4. English to Hindi Pre-process part is done in generic for all BERT-base, CNN Seq2Seq and RNN-With Attention Model.

Future Works:

1. Training BERT-base is left.
2. Web-App Frontend and Backend for Language Translation is currently being done parallelly in separate repo.