Swedish → English pico translator

A character-level encoder-decoder transformer trained on about 20,000 Tatoeba sentence pairs (EDAN20, lab 6). Two builds of the same model run side by side, in your browser. Short, everyday sentences work best.

Loading Python…

GPU build

22.1 M parameters · 80 epochs on an RTX 5070 Ti
Downloading weights (89 MB)…

Laptop build

3.7 M parameters · 5 epochs on a laptop CPU
Downloading weights (15 MB)…
About the models

Both builds come from the notebook 17_02_translation_transformer_shared_embs (Nugues, Python for NLP). They read and write one character at a time, with greedy decoding. The browser runs a NumPy re-implementation of the trained PyTorch model via Pyodide. It gives exactly the same translations as PyTorch.

GPU buildLaptop build
d_model / layers (enc+dec)512 / 3+3256 / 2+2
Training pairs / epochs20,521 / 8012,000 / 5
Val. char accuracy0.9130.637
BLEU (validation set)0.5050.043

Weights: IsacEP/edan20-lab6-swe-eng-translator