metadata
language:
- en
- en
tags:
- translation
license: cc-by-4.0
Translation model for en-en OPUS_HPLT v1.0
This repository contains the model weights for translation models trained with Marian for HPLT project. For usage instructions, evaluation scripts, and inference scripts, please refer to the HPLT-MT-Models v1.0 GitHub repository.
- Source language: en
- Target language: nn
- Dataset: All of OPUS including HPLT
- 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
To run inference with Marian, refer to the Inference/Decoding/Translation section of our GitHub repository.
Benchmarks
testset | BLEU | chr-F | COMET-22 |
---|---|---|---|
flores200 | 16.6 | 39.8 | 0.6749 |
ntrex | 15.7 | 38.3 | 0.6204 |