Downloads · 30 days
221
5% of all-time downloads
opus-mt-afa-en
Helsinki-NLP/opus-mt-afa-en
opus-mt-afa-en is a translation model from Helsinki-NLP. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as apache-2.0.
source group: Afro-Asiatic languages target group: English OPUS readme: afa-eng
All-time downloads
4.9K
Public
Repo size
1.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h5305 MB · 50%
At a glance
- Task
- Translation
- Library
- transformers
- License
- apache-2.0
- Model type
- marian
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Aug 16, 2023
- SHA
- 946737c1
Model card
From the Hugging Face model README
afa-eng
-
source group: Afro-Asiatic languages
-
target group: English
-
OPUS readme: afa-eng
-
model: transformer
-
source language(s): acm afb amh apc ara arq ary arz hau_Latn heb kab mlt rif_Latn shy_Latn som tir
-
target language(s): eng
-
model: transformer
-
pre-processing: normalization + SentencePiece (spm32k,spm32k)
-
download original weights: opus2m-2020-07-31.zip
-
test set translations: opus2m-2020-07-31.test.txt
-
test set scores: opus2m-2020-07-31.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| Tatoeba-test.amh-eng.amh.eng | 35.9 | 0.550 |
| Tatoeba-test.ara-eng.ara.eng | 36.6 | 0.543 |
| Tatoeba-test.hau-eng.hau.eng | 11.9 | 0.327 |
| Tatoeba-test.heb-eng.heb.eng | 42.7 | 0.591 |
| Tatoeba-test.kab-eng.kab.eng | 4.3 | 0.213 |
| Tatoeba-test.mlt-eng.mlt.eng | 44.3 | 0.618 |
| Tatoeba-test.multi.eng | 27.1 | 0.464 |
| Tatoeba-test.rif-eng.rif.eng | 3.5 | 0.141 |
| Tatoeba-test.shy-eng.shy.eng | 0.6 | 0.125 |
| Tatoeba-test.som-eng.som.eng | 23.6 | 0.472 |
| Tatoeba-test.tir-eng.tir.eng | 13.1 | 0.328 |
System Info:
-
hf_name: afa-eng
-
source_languages: afa
-
target_languages: eng
-
opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/afa-eng/README.md
-
original_repo: Tatoeba-Challenge
-
tags: ['translation']
-
languages: ['so', 'ti', 'am', 'he', 'mt', 'ar', 'afa', 'en']
-
src_constituents: {'som', 'rif_Latn', 'tir', 'kab', 'arq', 'afb', 'amh', 'arz', 'heb', 'shy_Latn', 'apc', 'mlt', 'thv', 'ara', 'hau_Latn', 'acm', 'ary'}
-
tgt_constituents: {'eng'}
-
src_multilingual: True
-
tgt_multilingual: False
-
prepro: normalization + SentencePiece (spm32k,spm32k)
-
url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/afa-eng/opus2m-2020-07-31.zip
-
url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/afa-eng/opus2m-2020-07-31.test.txt
-
src_alpha3: afa
-
tgt_alpha3: eng
-
short_pair: afa-en
-
chrF2_score: 0.46399999999999997
-
bleu: 27.1
-
brevity_penalty: 1.0
-
ref_len: 69373.0
-
src_name: Afro-Asiatic languages
-
tgt_name: English
-
train_date: 2020-07-31
-
src_alpha2: afa
-
tgt_alpha2: en
-
prefer_old: False
-
long_pair: afa-eng
-
helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
-
transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
-
port_machine: brutasse
-
port_time: 2020-08-21-14:41
- Task
- Translation
- Library
- transformers
- Type
- marian
- License
- apache-2.0
- Languages
- so, ti, am, he, mt, ar
- Created
- Mar 2, 2022
- Updated
- Aug 16, 2023