# -*- coding: utf-8 -*-
"""
Lalita Chinese-Thai Machine Translation
from AI builder
- GitHub: https://github.com/LalitaDeelert/lalita-mt-zhth
- Facebook post https://web.facebook.com/aibuildersx/posts/166736255494822
"""
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
[docs]class ThZhTranslator:
"""
Thai-Chinese Machine Translation
from Lalita @ AI builder
- GitHub: https://github.com/LalitaDeelert/lalita-mt-zhth
- Facebook post https://web.facebook.com/aibuildersx/posts/166736255494822
:param bool use_gpu : load model to gpu (Default is False)
"""
[docs] def __init__(self,
use_gpu: bool = False,
pretrained: str = "Lalita/marianmt-th-zh_cn") -> None:
self.tokenizer_thzh = AutoTokenizer.from_pretrained(pretrained)
self.model_thzh = AutoModelForSeq2SeqLM.from_pretrained(pretrained)
if use_gpu:
self.model_thzh.cuda()
[docs] def translate(self, text: str) -> str:
"""
Translate text from Thai to Chinese
:param str text: input text in source language
:return: translated text in target language
:rtype: str
:Example:
Translate text from Thai to Chinese::
from pythainlp.translate import ThZhTranslator
thzh = ThZhTranslator()
thzh.translate("ผมรักคุณ")
# output: 我爱你
"""
self.translated = self.model_thzh.generate(
**self.tokenizer_thzh(text, return_tensors="pt", padding=True)
)
return [
self.tokenizer_thzh.decode(
t, skip_special_tokens=True
) for t in self.translated
][0]
[docs]class ZhThTranslator:
"""
Chinese-Thai Machine Translation
from Lalita @ AI builder
- GitHub: https://github.com/LalitaDeelert/lalita-mt-zhth
- Facebook post https://web.facebook.com/aibuildersx/posts/166736255494822
:param bool use_gpu : load model to gpu (Default is False)
"""
[docs] def __init__(self,
use_gpu: bool = False,
pretrained: str = "Lalita/marianmt-zh_cn-th") -> None:
self.tokenizer_zhth = AutoTokenizer.from_pretrained(pretrained)
self.model_zhth = AutoModelForSeq2SeqLM.from_pretrained(pretrained)
if use_gpu:
self.model_zhth.cuda()
[docs] def translate(self, text: str) -> str:
"""
Translate text from Chinese to Thai
:param str text: input text in source language
:return: translated text in target language
:rtype: str
:Example:
Translate text from Chinese to Thai::
from pythainlp.translate import ZhThTranslator
zhth = ZhThTranslator()
zhth.translate("我爱你")
# output: ผมรักคุณนะ
"""
self.translated = self.model_zhth.generate(
**self.tokenizer_zhth(text, return_tensors="pt", padding=True)
)
return [
self.tokenizer_zhth.decode(
t, skip_special_tokens=True
) for t in self.translated
][0]