metadata
tags:
- translation
license: cc-by-4.0
language:
- en
- zh
Translation model for en-zh_hant 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: zh_hant
- Dataset: HPLT only
- 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 | 25.4 | 18.9 | 0.8017 |
| ntrex | 21.3 | 21.6 | 0.7492 |