pythainlp.transliterate

The pythainlp.transliterate turns Thai text into a romanized one (put simply, spelled with English).

Modules

pythainlp.transliterate.romanize(text: str, engine: str = 'royin', fallback_engine: str = 'royin') → str

This function renders Thai words in the Latin alphabet or “romanization”, using the Royal Thai General System of Transcription (RTGS) [1]. RTGS is the official system published by the Royal Institute of Thailand. (Thai: ถอดเสียงภาษาไทยเป็นอักษรละติน)

Parameters:

• text (str) – Thai text to be romanized

• engine (str) – One of ‘royin’ (default), ‘thai2rom’, ‘thai2rom_onnx, ‘tltk’, and ‘lookup’. See more in options for engine section.

• fallback_engine (str) – If engine equals ‘lookup’, use fallback_engine for words that are not in the transliteration dict. No effect on other engines. Default to ‘royin’.

Returns:

A string of Thai words rendered in the Latin alphabet.

Return type:

str

Options for engines:

• royin - (default) based on the Royal Thai General System of Transcription issued by Royal Institute of Thailand.

• thai2rom - a deep learning-based Thai romanization engine (require PyTorch).

• thai2rom_onnx - a deep learning-based Thai romanization engine with ONNX runtime

• tltk - TLTK: Thai Language Toolkit

• lookup - Look up on Thai-English Transliteration dictionary v1.4 compiled by Wannaphong.

Example:

from pythainlp.transliterate import romanize

romanize("สามารถ", engine="royin")
# output: 'samant'

romanize("สามารถ", engine="thai2rom")
# output: 'samat'

romanize("สามารถ", engine="tltk")
# output: 'samat'

romanize("ภาพยนตร์", engine="royin")
# output: 'phapn'

romanize("ภาพยนตร์", engine="thai2rom")
# output: 'phapphayon'

romanize("ภาพยนตร์", engine="thai2rom_onnx")
# output: 'phapphayon'

romanize("ก็อปปี้", engine="lookup")
# output: 'copy'

pythainlp.transliterate.transliterate(text: str, engine: str = 'thaig2p') → str

This function transliterates Thai text.

Parameters:

• text (str) – Thai text to be transliterated

• engine (str) – ‘icu’, ‘ipa’, or ‘thaig2p’ (default)

Returns:

A string of phonetic alphabets indicating how the input text should be pronounced.

Return type:

str

Options for engines:

• thaig2p - (default) Thai Grapheme-to-Phoneme, output is IPA (require PyTorch)

• icu - pyicu, based on International Components for Unicode (ICU)

• ipa - epitran, output is International Phonetic Alphabet (IPA)

• tltk_g2p - Thai Grapheme-to-Phoneme from TLTK.,

• iso_11940 - Thai text into Latin characters with ISO 11940.

• tltk_ipa - tltk, output is International Phonetic Alphabet (IPA)

Example:

from pythainlp.transliterate import transliterate

transliterate("สามารถ", engine="icu")
# output: 's̄āmārt̄h'

transliterate("สามารถ", engine="ipa")
# output: 'saːmaːrot'

transliterate("สามารถ", engine="thaig2p")
# output: 's aː ˩˩˦ . m aː t̚ ˥˩'

transliterate("สามารถ", engine="tltk_ipa")
# output: 'saː5.maːt3'

transliterate("สามารถ", engine="tltk_g2p")
# output: 'saa4~maat2'

transliterate("สามารถ", engine="iso_11940")
# output: 's̄āmārt̄h'

transliterate("ภาพยนตร์", engine="icu")
# output: 'p̣hāphyntr̒'

transliterate("ภาพยนตร์", engine="ipa")
# output: 'pʰaːpjanot'

transliterate("ภาพยนตร์", engine="thaig2p")
# output: 'pʰ aː p̚ ˥˩ . pʰ a ˦˥ . j o n ˧'

transliterate("ภาพยนตร์", engine="iso_11940")
# output: 'p̣hāphyntr'

pythainlp.transliterate.pronunciate(word: str, engine: str = 'w2p') → str

This function pronunciates Thai word.

Parameters:

• word (str) – Thai text to be pronunciated

• engine (str) – ‘w2p’ (default)

Returns:

A string of Thai letters indicating how the input text should be pronounced.

Return type:

str

Options for engines:

• w2p - Thai Word-to-Phoneme

Example:

from pythainlp.transliterate import pronunciate

pronunciate("สามารถ", engine="w2p")
# output: 'สา-มาด'

pronunciate("ภาพยนตร์", engine="w2p")
# output: 'พาบ-พะ-ยน'

pythainlp.transliterate.puan(word: str, show_pronunciation: bool = True) → str

Thai Spoonerism

This function converts Thai word to spoonerism word.

Parameters:

• word (str) – Thai word to be spoonerized

• show_pronunciation (bool) – True (default) or False

Returns:

A string of Thai spoonerism word.

Return type:

str

Example:

from pythainlp.transliterate import puan

puan("นาริน")
# output: 'นิน-รา'

puan("นาริน", False)
# output: 'นินรา'

class pythainlp.transliterate.wunsen.WunsenTransliterate

Transliterating Japanese/Korean/Mandarin/Vietnamese romanization text to Thai text by Wunsen

See Also:

• GitHub

__init__() → None

transliterate(text: str, lang: str, jp_input: str | None = None, zh_sandhi: bool | None = None, system: str | None = None)

Use Wunsen for transliteration

Parameters:

• text (str) – text wants transliterated to Thai text.

• lang (str) – source language

• jp_input (str) – japanese input method (for japanese only)

• zh_sandhi (bool) – mandarin third tone sandhi option (for mandarin only)

• system (str) – transliteration system (for japanese and mandarin only)

Returns:

Thai text

Return type:

str

Options for lang:

• jp - Japanese (from Hepburn romanization)

• ko - Korean (from Revised Romanization)

• vi - Vietnamese (Latin script)

• zh - Mandarin (from Hanyu Pinyin)

Options for jp_input:

• Hepburn-no diacritic - Hepburn-no diacritic (without macron)

Options for zh_sandhi:

• True - apply third tone sandhi rule

• False - do not apply third tone sandhi rule

Options for system:

• ORS61 - for Japanese หลักเกณฑ์การทับศัพท์ภาษาญี่ปุ่น

  (สำนักงานราชบัณฑิตยสภา พ.ศ. 2561)

• RI35 - for Japanese หลักเกณฑ์การทับศัพท์ภาษาญี่ปุ่น

  (ราชบัณฑิตยสถาน พ.ศ. 2535)

• RI49 - for Mandarin หลักเกณฑ์การทับศัพท์ภาษาจีน

  (ราชบัณฑิตยสถาน พ.ศ. 2549)

• THC43 - for Mandarin เกณฑ์การถ่ายทอดเสียงภาษาจีนแมนดาริน

  ด้วยอักขรวิธีไทย (คณะกรรมการสืบค้นประวัติศาสตร์ไทยในเอกสาร ภาษาจีน พ.ศ. 2543)

Example:

::

from pythainlp.transliterate.wunsen import WunsenTransliterate

wt = WunsenTransliterate()

wt.transliterate(“ohayō”, lang=”jp”) # output: ‘โอฮาโย’

wt.transliterate(

“ohayou”, lang=”jp”, jp_input=”Hepburn-no diacritic”

) # output: ‘โอฮาโย’

wt.transliterate(“ohayō”, lang=”jp”, system=”RI35”) # output: ‘โอะฮะโย’

wt.transliterate(“annyeonghaseyo”, lang=”ko”) # output: ‘อันนย็องฮาเซโย’

wt.transliterate(“xin chào”, lang=”vi”) # output: ‘ซีน จ่าว’

wt.transliterate(“ni3 hao3”, lang=”zh”) # output: ‘หนี เห่า’

wt.transliterate(“ni3 hao3”, lang=”zh”, zh_sandhi=False) # output: ‘หนี่ เห่า’

wt.transliterate(“ni3 hao3”, lang=”zh”, system=”RI49”) # output: ‘หนี ห่าว’

Romanize Engines

thai2rom

royin

Render Thai words in Latin alphabet, using RTGS

Royal Thai General System of Transcription (RTGS), is the official system by the Royal Institute of Thailand.

param text:

Thai text to be romanized

type text:

str

return:

A string of Thai words rendered in the Latin alphabet

rtype:

str

Transliterate Engines

icu

Transliterating text to International Phonetic Alphabet (IPA) Using International Components for Unicode (ICU)

See Also:

• GitHub

pythainlp.transliterate.pyicu.transliterate(text: str) → str

Use ICU (International Components for Unicode) for transliteration :param str text: Thai text to be transliterated. :return: A string of Internaitonal Phonetic Alphabets indicating how the text should be pronounced.

pythainlp.transliterate.pyicu.transliterate(text: str) → str

Use ICU (International Components for Unicode) for transliteration :param str text: Thai text to be transliterated. :return: A string of Internaitonal Phonetic Alphabets indicating how the text should be pronounced.

ipa

Transliterating text to International Phonetic Alphabet (IPA) Using epitran

See Also:

• GitHub

pythainlp.transliterate.ipa.transliterate(text: str) → str

pythainlp.transliterate.ipa.trans_list(text: str) → List[str]

pythainlp.transliterate.ipa.xsampa_list(text: str) → List[str]

pythainlp.transliterate.ipa.transliterate(text: str) → str

pythainlp.transliterate.ipa.trans_list(text: str) → List[str]

pythainlp.transliterate.ipa.xsampa_list(text: str) → List[str]

thaig2p

pythainlp.transliterate.thaig2p.transliterate(text: str) → str

tltk

pythainlp.transliterate.tltk.romanize(text: str) → str

Transliterating thai text to the Latin alphabet with tltk.

Parameters:

text (str) – Thai text to be romanized

Returns:

A string of Thai words rendered in the Latin alphabet.

Return type:

str

pythainlp.transliterate.tltk.tltk_g2p(text: str) → str

pythainlp.transliterate.tltk.tltk_ipa(text: str) → str

iso_11940

Transliterating Thai text with ISO 11940

See Also:

• Wikipedia

pythainlp.transliterate.iso_11940.transliterate(word: str) → str

Use ISO 11940 for transliteration :param str text: Thai text to be transliterated. :return: A string of IPA indicating how the text should be pronounced.

References

[1]

Nitaya Kanchanawan. (2006). Romanization, Transliteration, and Transcription for the Globalization of the Thai Language. The Journal of the Royal Institute of Thailand.