Downloads · 30 days
7
25% of all-time downloads
opus-tatoeba-eng-lav-bt
Neurora/opus-tatoeba-eng-lav-bt
opus-tatoeba-eng-lav-bt is a translation model from Neurora. Use it when you need text moved from one language to another. The card lists the license as apache-2.0.
dataset: opus+bt model: transformer-align source language(s): eng target language(s): lav ltg model: transformer-align pre-processing: normalization + SentencePiece (spm32k,spm32k) a sentence initial language token is…
All-time downloads
28
Public
Parameters
104M
210 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors208 MB · 99%
At a glance
- Task
- Translation
- License
- apache-2.0
- Model type
- marian
- Access
- Public
- Created
- Feb 26, 2025
- Updated
- Jun 6, 2025
- SHA
- 7f2a3a68
Try a prompt
Model card
From the Hugging Face model README
Opus Tatoeba | English -> Latvian
- dataset: opus+bt
- model: transformer-align
- source language(s): eng
- target language(s): lav ltg
- model: transformer-align
- pre-processing: normalization + SentencePiece (spm32k,spm32k)
- a sentence initial language token is required in the form of
>>id<<(id = valid target language ID) - valid language labels: >>lav<< >>ltg<<
- download: opus+bt-2021-04-14.zip
- test set translations: opus+bt-2021-04-14.test.txt
- test set scores: opus+bt-2021-04-14.eval.txt
Benchmarks
| testset | BLEU | chr-F | #sent | #words | BP |
|---|---|---|---|---|---|
| newsdev2017-enlv.eng-lav | 27.9 | 0.578 | 2003 | 41503 | 0.992 |
| newstest2017-enlv.eng-lav | 21.1 | 0.531 | 2001 | 39434 | 1.000 |
| Tatoeba-test.eng-lav | 46.8 | 0.683 | 1631 | 9932 | 0.986 |
| Tatoeba-test.eng-ltg | 10.7 | 0.392 | 1 | 4 | 1.000 |
- Task
- Translation
- Type
- marian
- License
- apache-2.0
- Languages
- en, lv
- Created
- Feb 26, 2025
- Updated
- Jun 6, 2025