Helsinki-NLP/opus-mt-fj-en

Back to all models

Model: Helsinki-NLP/opus-mt-fj-en

Monthly model downloads

Helsinki-NLP/opus-mt-fj-en

- downloads
last 30 days

pytorch

Contributed by

Language Technology Research Group at the University of Helsinki university

1 team member · 1011 models

How to use this model directly from the 🤗/transformers library:

			
			tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-fj-en")
			
			model = AutoModelWithLMHead.from_pretrained("Helsinki-NLP/opus-mt-fj-en")

List all files in model · See raw config file

Model card

Uploaded in S3

opus-mt-fj-en

source languages: fj
target languages: en
OPUS readme: fj-en
dataset: opus
model: transformer-align
pre-processing: normalization + SentencePiece
download original weights: opus-2020-01-09.zip
test set translations: opus-2020-01-09.test.txt
test set scores: opus-2020-01-09.eval.txt

Benchmarks

testset	BLEU	chr-F
JW300.fj.en	31.0	0.471
Tatoeba.fj.en	79.7	0.835

File name	Last modified	File size
README.md	Wed, 13 May 2020 12:38:56 GMT	802.0B
config.json	Thu, 07 May 2020 22:33:30 GMT	1.1KB
pytorch_model.bin	Wed, 29 Apr 2020 12:11:08 GMT	279.7MB
source.spm	Wed, 29 Apr 2020 12:11:17 GMT	772.4KB
target.spm	Wed, 29 Apr 2020 12:11:17 GMT	800.5KB
tokenizer_config.json	Wed, 29 Apr 2020 12:11:17 GMT	42.0B
vocab.json	Wed, 29 Apr 2020 12:11:18 GMT	1.2MB

Done