# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("sshleifer/opus-mt-en-he")
model = AutoModelForSeq2SeqLM.from_pretrained("sshleifer/opus-mt-en-he")en-he
source group: English
target group: Hebrew
OPUS readme: eng-heb
model: transformer
source language(s): eng
target language(s): heb
model: transformer
pre-processing: normalization + SentencePiece (spm32k,spm32k)
download original weights: opus-2020-10-04.zip
test set translations: opus-2020-10-04.test.txt
test set scores: opus-2020-10-04.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| Tatoeba-test.eng.heb | 37.9 | 0.602 |
System Info:
hf_name: en-he
source_languages: eng
target_languages: heb
opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-heb/README.md
original_repo: Tatoeba-Challenge
tags: ['translation']
languages: ['en', 'he']
src_constituents: ('English', {'eng'})
tgt_constituents: ('Hebrew', {'heb'})
src_multilingual: False
tgt_multilingual: False
long_pair: eng-heb
prepro: normalization + SentencePiece (spm32k,spm32k)
url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-heb/opus-2020-10-04.zip
url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-heb/opus-2020-10-04.test.txt
src_alpha3: eng
tgt_alpha3: heb
chrF2_score: 0.602
bleu: 37.9
brevity_penalty: 1.0
ref_len: 60359.0
src_name: English
tgt_name: Hebrew
train_date: 2020-10-04 00:00:00
src_alpha2: en
tgt_alpha2: he
prefer_old: False
short_pair: en-he
helsinki_git_sha: 7b1a514877868084fd74350d261519e092b5b2dc
transformers_git_sha: 8e58566183ee49f9dbc4819a95a678fcfb1b7528
port_machine: MacBook-Pro.local
port_time: 2020-10-11-13:07
- Downloads last month
- 4
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="sshleifer/opus-mt-en-he")