language:
- zh
- en
tags:
- translation
- game
- cultivation
license: cc-by-nc-4.0
datasets:
- Custom
metrics:
- BLEU
pipeline_tag: translation
inference:
parameters:
src_lang: zh
tgt_lang: en
widget:
- text: <color=#c7471a>【小报】：听闻聚集在君山丐帮的各路江湖人士正在举办野擂台切磋，市面上花生瓜子各类小食行情见涨。</color>
This is a finetuned version of Facebook/M2M100. It's a project born from the activity of Amateur Modding Avenue, a Discord based modding community. Special thanks to the Path of Wuxia modding team for kindly sharing their translations to help build the dataset.
It has been trained on a 46k lines parallel corpus on several Chinese video games translations. All of them are from human/fan translations.
It's not perfect but it's the best I could do. It should be sitting somewhere between Google Translate and DeepL, I guess. So... Before you go any further, lower your expectations. No, lower. Just a bit lower... and.. here we are.
That being said, it has upsides for first MT pass in a game translation context :
- It should not mess up tags
- It has basic cultivation/martial arts vocabulary
- Nothing is locked behind a paywall \o/
Sample generation script :
from transformers import AutoModelForSeq2SeqLM, M2M100Tokenizer
import torch
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
tokenizer = transformers.M2M100Tokenizer.from_pretrained("CadenzaBaron/M2M100-418M-for-GameTranslation-Finetuned-Zh-En")
model = AutoModelForSeq2SeqLM.from_pretrained("CadenzaBaron/M2M100-418M-for-GameTranslation-Finetuned-Zh-En")
model.to(device)
tokenizer.src_lang = "zh"
tokenizer.tgt_lang = "en"
test_string = "地阶上品遁术，施展后便可立于所持之剑上，以极快的速度自由飞行。"
inputs = tokenizer(test_string, return_tensors="pt").to(device)
translated_tokens = model.generate(**inputs, num_beams=10, do_sample=True)
translation = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
print("CH : ", test_string , " // EN : ", translation)
Translation sample and comparison with Google Translate and DeepL : Link to Spreadsheet