README.md

metadata

license: mit
language:
  - en
  - ami
metrics:
  - bleu
  - chrf
  - wer
datasets:
  - hunterschep/amis-english

Model Performance

The performance of the translation model has been evaluated using the following metrics:

• BLEU Score: 15.58
• chrF++ Score: 40.10

This model was trained on a ~76,000 line parralel-corpus of Amis-English translations. Most of these translations were assembled using Mandarin Chinese as a pivot language. The model itself was evaluated on the 'test' portion of the dataset. Total training length was 60,000 epochs.