Part 1 video:    • Let's Recreate Google Translate! | Ne...  

In the first video we talked a little bit of some general theory behind Neural Machine Translation (NMT). This time we covered the data pipeline and data processing we will need to train our model. We are using an Asian language + English dataset for our training.

The previous video went over NLP models for sequential data, attention, self-attention, the mT5 model, and the Hugging Face library for transformers.

GitHub repo: https://github.com/ejmejm/multilingua...
Colab code: https://colab.research.google.com/dri...
Transformer paper: https://arxiv.org/abs/1706.03762
mT5 paper: https://arxiv.org/abs/2010.11934
Article on how transformers work: https://towardsdatascience.com/transf...