模型:
Helsinki-NLP/opus-mt-en-bg
任务:
翻译许可:
apache-2.0源组:英语
目标组:保加利亚语
OPUS自述文件: eng-bul
模型:transformer
源语言:eng
目标语言:bul bul_Latn
模型:transformer
预处理:归一化 + SentencePiece (spm32k,spm32k)
需要一个句子的初始语言标记,形式为>>id<< (id = 有效的目标语言ID)
下载原始权重: opus-2020-07-03.zip
测试集翻译: opus-2020-07-03.test.txt
测试集分数: opus-2020-07-03.eval.txt
testset | BLEU | chr-F |
---|---|---|
Tatoeba-test.eng.bul | 50.6 | 0.680 |
hf_name:eng-bul
源语言:eng
目标语言:bul
opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-bul/README.md
原始仓库:Tatoeba-Challenge
标签:['translation']
语言:['en', 'bg']
src_constituents:{'eng'}
tgt_constituents:{'bul', 'bul_Latn'}
src_multilingual:False
tgt_multilingual:False
预处理:归一化 + SentencePiece (spm32k,spm32k)
url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-bul/opus-2020-07-03.zip
url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-bul/opus-2020-07-03.test.txt
src_alpha3:eng
tgt_alpha3:bul
short_pair:en-bg
chrF2_score:0.68
bleu:50.6
brevity_penalty:0.96
ref_len:69504.0
src_name:英语
tgt_name:保加利亚语
train_date:2020-07-03
src_alpha2:en
tgt_alpha2:bg
prefer_old:False
long_pair:eng-bul
helsinki_git_sha:480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
transformers_git_sha:2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
port_machine:brutasse
port_time:2020-08-21-14:41