|
|
--- |
|
|
|
|
|
language: |
|
|
- 'zh' |
|
|
- 'en' |
|
|
tags: |
|
|
- translation |
|
|
- game |
|
|
- cultivation |
|
|
license: 'cc-by-nc-4.0' |
|
|
datasets: |
|
|
- Custom |
|
|
metrics: |
|
|
- BLEU |
|
|
--- |
|
|
|
|
|
This is a finetuned version of Facebook/M2M100. |
|
|
It has been trained on a parallel corpus on several Chinese video games translations. All of them are from human/fan translations. |
|
|
|
|
|
Sample generation script : |
|
|
|
|
|
```from transformers import AutoModelForSeq2SeqLM, AutoTokenizer |
|
|
tokenizer = transformers.AutoTokenizer.from_pretrained(r"path\to\checkpoint") |
|
|
model = AutoModelForSeq2SeqLM.from_pretrained(r"path\to\checkpoint") |
|
|
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") |
|
|
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 : [here](https://docs.google.com/spreadsheets/d/1J1i9P0nyI9q5-m2iZGSUatt3ZdHSxU8NOp9tJH7wxsk/edit?usp=sharing) |
|
|
|
|
|
|
