Index

_

__annotate_func__ (pythainlp.spell.NorvigSpellChecker attribute) __annotations__ (pythainlp.khavee.KhaveeVerifier attribute) __annotations_cache__ (pythainlp.spell.NorvigSpellChecker attribute) __dict__ (pythainlp.khavee.KhaveeVerifier attribute) (pythainlp.spell.NorvigSpellChecker attribute) __firstlineno__ (pythainlp.khavee.KhaveeVerifier attribute) (pythainlp.spell.NorvigSpellChecker attribute) __init__() (pythainlp.braille.core.Braille method) (pythainlp.chunk.CRFChunkParser method) (pythainlp.classify.GzipModel method) (pythainlp.classify.LayaModel method) (pythainlp.el.EntityLinker method) (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.generate.Unigram method) (pythainlp.khavee.KhaveeVerifier method) (pythainlp.lm.phayathaibert.NamedEntityTagger method) (pythainlp.lm.phayathaibert.PartOfSpeechTagger method) (pythainlp.lm.phayathaibert.ThaiTextAugmenter method) (pythainlp.lm.phayathaibert.ThaiTextProcessor method) (pythainlp.lm.Qwen3 method) (pythainlp.lm.wangchanberta.NamedEntityRecognition method) (pythainlp.lm.wangchanberta.ThaiNameTagger method) (pythainlp.spell.NorvigSpellChecker method) (pythainlp.summarize.keybert.KeyBERT method), [1] (pythainlp.tag.CRFTagger method) (pythainlp.tag.NER method) (pythainlp.tag.NNER method) (pythainlp.tag.thainer.ThaiNameTagger method) (pythainlp.tokenize.han_solo.Featurizer method) (pythainlp.tokenize.longest.LongestMatchTokenizer method) (pythainlp.tokenize.multi_cut.LatticeString method) (pythainlp.tokenize.Tokenizer method) (pythainlp.translate.th_fr.ThFrTranslator method) (pythainlp.translate.Translate method) (pythainlp.translate.zh_th.ThZhTranslator method) (pythainlp.translate.zh_th.ZhThTranslator method) (pythainlp.transliterate.fastthaig2p.FastThaiG2P method) (pythainlp.util.Trie method) (pythainlp.util.Trie.Node method) (pythainlp.word_vector.WordVector method)

__module__ (pythainlp.khavee.KhaveeVerifier attribute) (pythainlp.spell.NorvigSpellChecker attribute) __static_attributes__ (pythainlp.khavee.KhaveeVerifier attribute) (pythainlp.spell.NorvigSpellChecker attribute)

A

add() (pythainlp.util.Trie method)

aksonhan_to_current() (in module pythainlp.ancient) augment() (pythainlp.lm.phayathaibert.ThaiTextAugmenter method)

B

batch_size (pythainlp.classify.LayaModel attribute) benchmark() (in module pythainlp.benchmarks.word_tokenization) bi (pythainlp.generate.Bigram attribute) (pythainlp.generate.Trigram attribute)

bi_keys (pythainlp.generate.Bigram attribute) (pythainlp.generate.Trigram attribute) Bigram (class in pythainlp.generate) bleu_score() (in module pythainlp.benchmarks) Braille (class in pythainlp.braille.core)

C

calculate_ngram_counts() (in module pythainlp.lm) char_eval_function() (in module pythainlp.benchmarks) character_error_rate() (in module pythainlp.benchmarks) chat() (pythainlp.lm.Qwen3 method) check_aek_too() (pythainlp.khavee.KhaveeVerifier method) check_karu_lahu() (pythainlp.khavee.KhaveeVerifier method) check_klon() (pythainlp.khavee.KhaveeVerifier method) check_marttra() (pythainlp.khavee.KhaveeVerifier method) check_sara() (pythainlp.khavee.KhaveeVerifier method) children (pythainlp.util.Trie.Node attribute) chunk_parse() (in module pythainlp.chunk) (in module pythainlp.tag) classify() (pythainlp.classify.LayaModel method) classify_batch() (pythainlp.classify.LayaModel method) classify_tokens (pythainlp.lm.wangchanberta.ThaiNameTagger attribute)

close() (pythainlp.tag.CRFTagger method) complete_soundex() (in module pythainlp.soundex) complete_soundex_similarity() (in module pythainlp.soundex) compute_stats() (in module pythainlp.benchmarks.word_tokenization) convert() (pythainlp.transliterate.fastthaig2p.FastThaiG2P method) convert_currency() (in module pythainlp.ancient) coreference_resolution() (in module pythainlp.coref) corpus (pythainlp.chunk.CRFChunkParser attribute) correct() (in module pythainlp.spell) (pythainlp.spell.NorvigSpellChecker method) correct_sent() (in module pythainlp.spell) counts (pythainlp.generate.Unigram attribute) crf (pythainlp.tag.thainer.ThaiNameTagger attribute) CRFChunkParser (class in pythainlp.chunk) CRFTagger (class in pythainlp.tag) cx2_list (pythainlp.classify.GzipModel attribute)

D

dataset_name (pythainlp.lm.wangchanberta.ThaiNameTagger attribute) DEFAULT_SPELL_CHECKER (in module pythainlp.spell) delimiter (pythainlp.tokenize.han_solo.Featurizer attribute)

dependency_parsing() (in module pythainlp.parse) dictionary() (pythainlp.spell.NorvigSpellChecker method) display_cell_tokenize (class in pythainlp.tokenize) doesnt_match() (pythainlp.word_vector.WordVector method)

E

embed() (pythainlp.summarize.keybert.KeyBERT method), [1] end (pythainlp.util.Trie.Node attribute) engine (pythainlp.tag.NER attribute) (pythainlp.tag.NNER attribute) EntityLinker (class in pythainlp.el) environment variable PYTHAINLP_DATA, [1], [2], [3] PYTHAINLP_DATA_DIR PYTHAINLP_OFFLINE, [1], [2], [3] PYTHAINLP_READ_MODE, [1] PYTHAINLP_READ_ONLY, [1], [2], [3], [4]

evaluate_word_tokenization() (in module pythainlp.benchmarks) extract_keywords() (in module pythainlp.summarize) (pythainlp.summarize.keybert.KeyBERT method), [1]

F

FastThaiG2P (class in pythainlp.transliterate.fastthaig2p) featurize() (pythainlp.tokenize.han_solo.Featurizer method) Featurizer (class in pythainlp.tokenize.han_solo)

find_all_segment() (in module pythainlp.tokenize.multi_cut) freq() (pythainlp.spell.NorvigSpellChecker method) ft_pipeline (pythainlp.summarize.keybert.KeyBERT attribute), [1]

G

gen_sentence() (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.generate.Unigram method) generate() (pythainlp.lm.phayathaibert.ThaiTextAugmenter method) (pythainlp.lm.Qwen3 method) get_el() (pythainlp.el.EntityLinker method) get_model() (pythainlp.word_vector.WordVector method) get_ner() (pythainlp.lm.phayathaibert.NamedEntityTagger method) (pythainlp.lm.wangchanberta.NamedEntityRecognition method) (pythainlp.lm.wangchanberta.ThaiNameTagger method) (pythainlp.tag.thainer.ThaiNameTagger method)

get_sense() (in module pythainlp.wsd) get_tag() (pythainlp.lm.phayathaibert.PartOfSpeechTagger method) get_words_spell_suggestion() (in module pythainlp.spell) grouped_entities (pythainlp.lm.wangchanberta.ThaiNameTagger attribute) GzipModel (class in pythainlp.classify)

H

handle_karun_sound_silence() (pythainlp.khavee.KhaveeVerifier method)

I

in_dict (pythainlp.tokenize.multi_cut.LatticeString attribute)

is_sumpus() (pythainlp.khavee.KhaveeVerifier method)

J

json_ner (pythainlp.lm.wangchanberta.ThaiNameTagger attribute)

K

KeyBERT (class in pythainlp.summarize.keybert), [1]

KhaveeVerifier (class in pythainlp.khavee) known() (pythainlp.spell.NorvigSpellChecker method)

L

labels (pythainlp.tag.CRFTagger attribute) LatticeString (class in pythainlp.tokenize.multi_cut) LayaModel (class in pythainlp.classify) list_to_string() (in module pythainlp.tokenize.thaisumcut) lk82() (in module pythainlp.soundex) load() (pythainlp.classify.GzipModel method) load_dict() (in module pythainlp.tokenize.nlpo3)

load_engine() (pythainlp.tag.NER method) (pythainlp.tag.NNER method) load_model() (pythainlp.chunk.CRFChunkParser method) (pythainlp.lm.Qwen3 method) (pythainlp.translate.Translate method) load_wordvector() (pythainlp.word_vector.WordVector method) LongestMatchTokenizer (class in pythainlp.tokenize.longest)

M

metasound() (in module pythainlp.soundex) middle_cut() (in module pythainlp.tokenize.thaisumcut) mmcut() (in module pythainlp.tokenize.multi_cut) model (pythainlp.lm.wangchanberta.NamedEntityRecognition attribute) model_path (pythainlp.classify.LayaModel attribute) model_thfr (pythainlp.translate.th_fr.ThFrTranslator attribute) module pythainlp.summarize.keybert pythainlp.tokenize.crfcut pythainlp.tokenize.etcc pythainlp.tokenize.han_solo pythainlp.tokenize.longest pythainlp.tokenize.multi_cut pythainlp.tokenize.nercut pythainlp.tokenize.newmm pythainlp.tokenize.nlpo3 pythainlp.tokenize.tcc pythainlp.tokenize.tcc_p pythainlp.tokenize.thaisumcut

most_similar_cosmul() (pythainlp.word_vector.WordVector method) multi (pythainlp.tokenize.multi_cut.LatticeString attribute)

N

n (pythainlp.generate.Unigram attribute) N (pythainlp.tokenize.han_solo.Featurizer attribute) name_engine (pythainlp.tag.NER attribute) NamedEntityRecognition (class in pythainlp.lm.wangchanberta)

NamedEntityTagger (class in pythainlp.lm.phayathaibert) NER (class in pythainlp.tag) nighit() (in module pythainlp.morpheme) NNER (class in pythainlp.tag) NorvigSpellChecker (class in pythainlp.spell)

O

open() (pythainlp.tag.CRFTagger method)

output (pythainlp.lm.wangchanberta.ThaiNameTagger attribute)

P

pad() (pythainlp.tokenize.han_solo.Featurizer method) parse() (pythainlp.chunk.CRFChunkParser method) PartOfSpeechTagger (class in pythainlp.lm.phayathaibert) pos_tag() (in module pythainlp.tag) pos_tag_name (pythainlp.tag.thainer.ThaiNameTagger attribute) pos_tag_sents() (in module pythainlp.tag) prayut_and_somchaip() (in module pythainlp.soundex) predict() (pythainlp.classify.GzipModel method) (pythainlp.classify.LayaModel method) prefixes() (pythainlp.util.Trie method) preprocess() (pythainlp.lm.phayathaibert.ThaiTextProcessor method) preprocessing() (in module pythainlp.benchmarks.word_tokenization) printbraille() (pythainlp.braille.core.Braille method) prob (pythainlp.generate.Unigram attribute) prob() (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.spell.NorvigSpellChecker method) providers (pythainlp.classify.LayaModel attribute) pythainlp.summarize.keybert module pythainlp.tokenize.crfcut module pythainlp.tokenize.etcc module

pythainlp.tokenize.han_solo module pythainlp.tokenize.longest module pythainlp.tokenize.multi_cut module pythainlp.tokenize.nercut module pythainlp.tokenize.newmm module pythainlp.tokenize.nlpo3 module pythainlp.tokenize.tcc module pythainlp.tokenize.tcc_p module pythainlp.tokenize.thaisumcut module PYTHAINLP_DATA, [1], [2] PYTHAINLP_OFFLINE, [1], [2] PYTHAINLP_READ_MODE PYTHAINLP_READ_ONLY, [1], [2], [3]

Q

Qwen3 (class in pythainlp.lm)

R

radius (pythainlp.tokenize.han_solo.Featurizer attribute) remove() (pythainlp.util.Trie method) remove_repeated_ngrams() (in module pythainlp.lm) remove_space() (pythainlp.lm.phayathaibert.ThaiTextProcessor method) replace_newlines() (pythainlp.lm.phayathaibert.ThaiTextProcessor method) replace_rep_after() (pythainlp.lm.phayathaibert.ThaiTextProcessor method) replace_spaces() (pythainlp.lm.phayathaibert.ThaiTextProcessor method)

replace_url() (pythainlp.lm.phayathaibert.ThaiTextProcessor method) replace_wrep_post() (pythainlp.lm.phayathaibert.ThaiTextProcessor method) rm_brackets() (pythainlp.lm.phayathaibert.ThaiTextProcessor method) rm_useless_spaces() (pythainlp.lm.phayathaibert.ThaiTextProcessor method) romanize() (in module pythainlp.transliterate.royin) root (pythainlp.util.Trie attribute) rouge_score() (in module pythainlp.benchmarks)

S

save() (pythainlp.classify.GzipModel method) segment() (in module pythainlp.lm.phayathaibert) (in module pythainlp.tokenize.crfcut) (in module pythainlp.tokenize.etcc) (in module pythainlp.tokenize.han_solo) (in module pythainlp.tokenize.longest) (in module pythainlp.tokenize.multi_cut) (in module pythainlp.tokenize.nercut) (in module pythainlp.tokenize.newmm) (in module pythainlp.tokenize.nlpo3) (in module pythainlp.tokenize.tcc) (in module pythainlp.tokenize.tcc_p)

sent_ner (pythainlp.lm.wangchanberta.ThaiNameTagger attribute) sentence_vectorizer() (pythainlp.word_vector.WordVector method) set_tokenize_engine() (pythainlp.tokenize.Tokenizer method) similarity() (pythainlp.word_vector.WordVector method) soundex() (in module pythainlp.soundex) spell() (in module pythainlp.spell) (pythainlp.spell.NorvigSpellChecker method) spell_sent() (in module pythainlp.spell) split_into_sentences() (pythainlp.tokenize.thaisumcut.ThaiSentenceSegmentor method) summarize() (in module pythainlp.summarize) system_one() (pythainlp.classify.LayaModel method)

T

tag() (pythainlp.tag.CRFTagger method) (pythainlp.tag.NER method) (pythainlp.tag.NNER method) tag_provinces() (in module pythainlp.tag) tagger (pythainlp.chunk.CRFChunkParser attribute) tcc() (in module pythainlp.tokenize.tcc) (in module pythainlp.tokenize.tcc_p) tcc_pos() (in module pythainlp.tokenize.tcc) (in module pythainlp.tokenize.tcc_p) tcc_pos_array() (in module pythainlp.tokenize.tcc_p) thai_consonant_to_spelling() (in module pythainlp.util) thai_text_braille() (in module pythainlp.braille) thai_word_braille() (in module pythainlp.braille) ThaiNameTagger (class in pythainlp.lm.wangchanberta) (class in pythainlp.tag.thainer) ThaiSentenceSegmentor (class in pythainlp.tokenize.thaisumcut) ThaiTextAugmenter (class in pythainlp.lm.phayathaibert) ThaiTextProcessor (class in pythainlp.lm.phayathaibert) ThFrTranslator (class in pythainlp.translate.th_fr)

ThZhTranslator (class in pythainlp.translate.zh_th) ti (pythainlp.generate.Trigram attribute) ti_keys (pythainlp.generate.Trigram attribute) tobraille() (pythainlp.braille.core.Braille method) tokenize() (pythainlp.tokenize.longest.LongestMatchTokenizer method) Tokenizer (class in pythainlp.tokenize) tokenizer (pythainlp.lm.wangchanberta.NamedEntityRecognition attribute) tokenizer_thfr (pythainlp.translate.th_fr.ThFrTranslator attribute) tone_to_spelling() (in module pythainlp.util) train() (pythainlp.classify.GzipModel method) training_data (pythainlp.classify.GzipModel attribute) Translate (class in pythainlp.translate) translate() (pythainlp.translate.th_fr.ThFrTranslator method) (pythainlp.translate.Translate method) (pythainlp.translate.zh_th.ThZhTranslator method) (pythainlp.translate.zh_th.ZhThTranslator method) translated (pythainlp.translate.th_fr.ThFrTranslator attribute) Trie (class in pythainlp.util) Trie.Node (class in pythainlp.util) Trigram (class in pythainlp.generate)

U

udom83() (in module pythainlp.soundex) uni (pythainlp.generate.Bigram attribute) (pythainlp.generate.Trigram attribute)

uni_keys (pythainlp.generate.Bigram attribute) (pythainlp.generate.Trigram attribute) Unigram (class in pythainlp.generate) unique (pythainlp.tokenize.multi_cut.LatticeString attribute)

V

VALID_CONSONANTS (pythainlp.khavee.KhaveeVerifier attribute)

W

word (pythainlp.generate.Unigram attribute) word_error_rate() (in module pythainlp.benchmarks) word_eval_function() (in module pythainlp.benchmarks) word_tokenize() (pythainlp.tokenize.Tokenizer method)

word_translate (class in pythainlp.translate) words (pythainlp.generate.Bigram attribute) (pythainlp.generate.Trigram attribute) WordVector (class in pythainlp.word_vector)

X

xseq (pythainlp.chunk.CRFChunkParser attribute)

Z

ZhThTranslator (class in pythainlp.translate.zh_th)