---
language: Deustch English  
tags:
- translation Deustch English  model
datasets:
- dcep europarl jrc-acquis
---

# legal_t5_small_trans_de_en model

Model on translating legal text from Deustch to English. It was first released in
[this repository](https://github.com/agemagician/LegalTrans). This model is trained on three parallel corpus from jrc-acquis, europarl and dcep.


## Model description

legal_t5_small_trans_de_en 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 Deustch to English.

### How to use

Here is how to use this model to translate legal text from Deustch to English in PyTorch:

```python
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline

pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_de_en"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_de_en", do_lower_case=False, 
                                            skip_special_tokens=True),
    device=0
)

de_text = "Takes the view that using the Internet of Things in connection with nature can help in the development of green technologies by increasing energy efficiency and hence also environmental protection, and enhance the relationship between ICTs and nature;
"

pipeline([de_text], max_length=512)
```

## Training data

The legal_t5_small_trans_de_en model was trained on [JRC-ACQUIS](https://wt-public.emm4u.eu/Acquis/index_2.2.html), [EUROPARL](https://www.statmt.org/europarl/), and [DCEP](https://ec.europa.eu/jrc/en/language-technologies/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 | secondary structure (3-states) |
|:-----:|:-----:|
|   legal_t5_small_trans_de_en | 49.1|


### BibTeX entry and citation info