|
--- |
|
license: mit |
|
--- |
|
|
|
This is a many-to-many model for Creole-English, English-Creole and Creole-Creole MT, trained from scratch on all data. |
|
|
|
``` |
|
from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM |
|
from transformers import AlbertTokenizer, AutoTokenizer |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("n8rob/kreyol-mt-scratch", do_lower_case=False, use_fast=False, keep_accents=True) |
|
|
|
# The tokenizer we use is based on the AlbertTokenizer class which is essentially sentencepiece. We train this sentencepeice model from scratch. |
|
# Or use tokenizer = AlbertTokenizer.from_pretrained("n8rob/kreyol-mt-scratch", do_lower_case=False, use_fast=False, keep_accents=True) |
|
|
|
model = AutoModelForSeq2SeqLM.from_pretrained("n8rob/kreyol-mt-scratch") |
|
|
|
# Or use model = MBartForConditionalGeneration.from_pretrained("n8rob/kreyol-mt-scratch") |
|
|
|
# Some initial mapping |
|
bos_id = tokenizer._convert_token_to_id_with_added_voc("<s>") |
|
eos_id = tokenizer._convert_token_to_id_with_added_voc("</s>") |
|
pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>") |
|
|
|
# First tokenize the input and outputs. The format below is how the model was trained so the input should be "Sentence </s> <2hwc>". Similarly, the output should be "<2eng> Sentence </s>". |
|
# For Hawaiian Creole to English translation, we need to use language indicator tags: <2hwc> and <2eng> where hwc represents Hawaiian Creole and eng represents English. |
|
# The following language indicator tokens are usable: <2acf>, <2aoa>, <2ara>, <2aze>, <2bah>, <2brc>, <2bzj>, <2bzk>, <2cab>, <2ceb>, <2cri>, <2crs>, <2dcr>, <2deu>, <2djk>, <2eng>, <2fab>, <2fng>, <2fpe>, <2fra>, <2gcf>, <2gcr>, <2gpe>, <2gul>, <2gyn>, <2hat>, <2icr>, <2jam>, <2kea>, <2kri>, <2ktu>, <2lou>, <2mart1259>, <2mfe>, <2mue>, <2nep>, <2pap>, <2pcm>, <2por>, <2pov>, <2pre>, <2rcf>, <2sag>, <2spa>, <2srm>, <2srn>, <2svc>, <2tpi>, <2trf>, <2wes>, <2zho> |
|
# For what language each language code corresponds to please look here: https://github.com/JHU-CLSP/Kreyol-MT?tab=readme-ov-file#building-machine-translation-for-latin-american-caribbean-and-colonial-african-creole-languages |
|
|
|
inp = tokenizer('Wen dey wen stretch him out fo whip him real hard , Paul wen tell da captain dat stay dea , "Dis okay in da rules fo da Rome peopo ? fo you fo whip one guy dat get da same rights jalike da Rome peopo ? even one guy dat neva do notting wrong ?" </s> <2hwc>', add_special_tokens=False, return_tensors="pt", padding=True).input_ids |
|
|
|
model.eval() # Set dropouts to zero |
|
|
|
model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=60, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2eng>")) |
|
|
|
decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False) |
|
|
|
print(decoded_output) |
|
|
|
``` |
