Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 6 additions & 9 deletions docs/api/translate.rst
Original file line number Diff line number Diff line change
Expand Up @@ -9,12 +9,9 @@ Modules

.. autoclass:: Translate
:members:
.. autofunction:: download_model_all
.. autoclass:: EnThTranslator
:members: translate
.. autoclass:: ThEnTranslator
:members: translate
.. autoclass:: ThZhTranslator
:members: translate
.. autoclass:: ZhThTranslator
:members: translate
.. autofunction:: pythainlp.translate.en_th.download_model_all
.. autoclass:: pythainlp.translate.en_th.EnThTranslator
.. autoclass:: pythainlp.translate.en_th.ThEnTranslator
.. autoclass:: pythainlp.translate.zh_th.ThZhTranslator
.. autoclass:: pythainlp.translate.zh_th.ZhThTranslator
.. autoclass:: pythainlp.translate.th_fr.ThFrTranslator
8 changes: 0 additions & 8 deletions pythainlp/translate/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,21 +4,13 @@
"""

__all__ = [
"EnThTranslator",
"ThEnTranslator",
"download_model_all",
"ThZhTranslator",
"ZhThTranslator",
"Translate"
]

from pythainlp.translate.core import Translate

from pythainlp.translate.en_th import (
EnThTranslator,
ThEnTranslator,
download_model_all,
)
from pythainlp.translate.zh_th import (
ThZhTranslator,
ZhThTranslator,
Expand Down
5 changes: 5 additions & 0 deletions pythainlp/translate/core.py
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ class Translate:
* *en* - *th* - English to Thai
* *th* - *zh* - Thai to Chinese
* *zh* - *th* - Chinese to Thai
* *th* - *fr* - Thai to French

:Example:

Expand All @@ -34,6 +35,7 @@ def __init__(self, src_lang: str, target_lang: str) -> None:
* *en* - *th* - English to Thai
* *th* - *zh* - Thai to Chinese
* *zh* - *th* - Chinese to Thai
* *th* - *fr* - Thai to French

:Example:

Expand Down Expand Up @@ -61,6 +63,9 @@ def load_model(self, src_lang: str, target_lang: str):
elif src_lang == "zh" and target_lang == "th":
from pythainlp.translate.zh_th import ZhThTranslator
self.model = ZhThTranslator()
elif src_lang == "th" and target_lang == "fr":
from pythainlp.translate.th_fr import ThFrTranslator
self.model = ThFrTranslator()
else:
raise ValueError("Not support language!")

Expand Down
59 changes: 59 additions & 0 deletions pythainlp/translate/th_fr.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
# -*- coding: utf-8 -*-
"""
Thai-French Machine Translation

Trained by OPUS Corpus

Model from Language Technology Research Group at the University of Helsinki

BLEU 20.4

- Huggingface https://huggingface.co/Helsinki-NLP/opus-mt-th-fr
"""
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM


class ThFrTranslator:
"""
Thai-French Machine Translation

Trained by OPUS Corpus

Model from Language Technology Research Group at the University of Helsinki

BLEU 20.4

- Huggingface https://huggingface.co/Helsinki-NLP/opus-mt-th-fr
"""
def __init__(self, pretrained: str = "Helsinki-NLP/opus-mt-th-fr") -> None:
self.tokenizer_thzh = AutoTokenizer.from_pretrained(pretrained)
self.model_thzh = AutoModelForSeq2SeqLM.from_pretrained(pretrained)

def translate(self, text: str) -> str:
"""
Translate text from Thai to French

:param str text: input text in source language
:return: translated text in target language
:rtype: str

:Example:

Translate text from Thai to French::

from pythainlp.translate.th_fr import ThFrTranslator

thfr = ThFrTranslator()

thfr.translate("ทดสอบระบบ")
# output: "Test du système."

"""
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]
14 changes: 11 additions & 3 deletions tests/test_translate.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,13 +3,15 @@
import unittest

from pythainlp.translate import (
EnThTranslator,
ThEnTranslator,
ThZhTranslator,
ZhThTranslator,
download_model_all,
Translate
)
from pythainlp.translate.en_th import (
EnThTranslator,
ThEnTranslator,
download_model_all
)
from pythainlp.corpus import remove


Expand Down Expand Up @@ -65,5 +67,11 @@ def test_translate(self):
"我爱你",
)
)
self.th_fr_translator = Translate('th', 'fr')
self.assertIsNotNone(
self.th_fr_translator.translate(
"ทดสอบระบบ",
)
)
with self.assertRaises(ValueError):
self.th_cat_translator = Translate('th', 'cat')