Transformer from Scratch

This repository contains an implementation of a machine translation model based on the revolutionary "Attention Is All You Need" paper, commonly known as the Transformer architecture. The model is trained to translate English sentences into Spanish sentences using a neural network approach that focuses on self-attention mechanisms.

Features

• Transformer architecture implemented from scratch in PyTorch.
• The model trained from scratch on English - Spanish dataset.

Output

References

1. Attention Is All You Need
2. Build your own Transformer from scratch using PyTorch
3. The Annotated Transformer