Downloads · 30 days
15
1% of all-time downloads
omoekan/opus-tatoeba-eng-yor
opus-tatoeba-eng-yor is a machine learning model from omoekan. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
This model was obtained by running the script convertmariantopytorch.py with the flag -m eng-yor. The original models were trained by Jörg Tiedemann using the MarianNMT library. See all available MarianMTModel models…
Downloads · 30 days
15
1% of all-time downloads
All-time downloads
1K
Public
Repo size
265 MB
Likes
0
Public
Click a slice to open those files.
.bin132 MB · 99%
From the Hugging Face model README
This model was obtained by running the script convert_marian_to_pytorch.py with the flag -m eng-yor. The original models were trained by Jörg Tiedemann using the MarianNMT library. See all available MarianMTModel models on the profile of the Helsinki NLP group.
tags: translation
source language: English
target language: Yoruba
dataset: opus+bt -model: transformer-align -pre-processing: normalization + SentencePiece (spm12k,spm12k) -download original weights: opus+bt-2021-04-10.zip -test set translations: opus+bt-2021-04-10.test.txt -test set scores: opus+bt-2021-04-10.eval.txt
-Benchmarks
| test set | BLEU | chr-F |
|---|---|---|
| Tatoeba-test.eng-yor | 13.0 | 0.333 |