nmt-keras is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named nmt-keras among their alternatives. The relationship is not symmetric — how nmt-keras rates them is a separate judgement, made when nmt-keras is analysed in its own right.
calls nmt-keras “Choose if you are committed to Keras/TensorFlow 1.x for NMT, though it predates modern TF2/PyTorch practices.”
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.