Model on translating legal text from Swedish to Deustch. It was first released in this repository. This model is trained on three parallel corpus from jrc-acquis, europarl and dcep.
legal_t5_small_trans_sv_de 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.
The model could be used for translation of legal texts from Swedish to Deustch.
Here is how to use this model to translate legal text from Swedish to Deustch in PyTorch:
from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline pipeline = TranslationPipeline( model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_sv_de"), tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_sv_de", do_lower_case=False, skip_special_tokens=True), device=0 ) sv_text = "b) Bekämpning av skadegörare inom skogsbruket." pipeline([sv_text], max_length=512)
The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
When the model is used for translation test dataset, achieves the following results:
Test results :
- Downloads last month