fvalerii/nmt-seq2seq-translation

🚀 High-performance NMT study scaling Seq2Seq LSTMs to 200k+ sentence pairs. Features a streaming tf.data pipeline, Transfer Learning (NNLM), and masked loss. Reaches 17.32 BLEU on English-to-German translation. Developed for Imperial College London's TensorFlow Certification.

19
/ 100
Experimental
No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 30, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/fvalerii/nmt-seq2seq-translation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.