en-mt HPLT v1.0
Note: This repository only contains the model weights. For usage instructions, evaluation scripts, and inference scripts, please refer to the HPLT-MT-Models v1.0 GitHub repository.
- source language: en
- target language: mt
- dataset: OPUS + HPLTDatasets v1.2
- model: transformer-base
- tokenizer: SentencePiece (Unigram)
- cleaning: We use OpusCleaner for cleaning the corpus. Details about rules used can be found in the filter files in Github
Benchmarks
| testset | BLEU | chr-F | comet |
|---|---|---|---|
| flores200.en.mt | 47.5 | 0.64 | 0.64 |
| ntrex.en.mt | 25 | 0.62 | 0.62 |