language: Italian Cszech
tags:
- translation Italian Cszech model
datasets:
- dcep europarl jrc-acquis
widget:
- text: >-
k udělení absolutoria za plnění rozpočtu Evropské agentury pro chemické
látky na rozpočtový rok 2009
legal_t5_small_trans_it_cs model
Model on translating legal text from Italian to Cszech. It was first released in this repository. This model is trained on three parallel corpus from jrc-acquis, europarl and dcep.
Model description
legal_t5_small_trans_it_cs is based on the t5-small model and was trained on a large corpus of parallel text. This is a smaller model, which scales the baseline model of t5 down by using dmodel = 512, dff = 2,048, 8-headed attention, and only 6 layers each in the encoder and decoder. This variant has about 60 million parameters.
Intended uses & limitations
The model could be used for translation of legal texts from Italian to Cszech.
How to use
Here is how to use this model to translate legal text from Italian to Cszech in PyTorch:
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline
pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_it_cs"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_it_cs", do_lower_case=False,
skip_special_tokens=True),
device=0
)
it_text = "k udělení absolutoria za plnění rozpočtu Evropské agentury pro chemické látky na rozpočtový rok 2009
"
pipeline([it_text], max_length=512)
Training data
The legal_t5_small_trans_it_cs model was trained on JRC-ACQUIS, EUROPARL, and DCEP dataset consisting of 5 Million parallel texts.
Training procedure
Preprocessing
Pretraining
An unigram model with 88M parameters is trained over the complete parallel corpus to get the vocabulary (with byte pair encoding), which is used with this model.
Evaluation results
When the model is used for translation test dataset, achieves the following results:
Test results :
| Model | BLEU score |
|---|---|
| legal_t5_small_trans_it_cs | 43.3 |