diff --git a/pythainlp/corpus/tnc.py b/pythainlp/corpus/tnc.py index 7a01849a6..21e359b74 100644 --- a/pythainlp/corpus/tnc.py +++ b/pythainlp/corpus/tnc.py @@ -1,4 +1,5 @@ -# SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project. +# SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project +# SPDX-FileType: SOURCE # SPDX-License-Identifier: Apache-2.0 """Thai National Corpus word frequency """ diff --git a/pythainlp/tag/_tag_perceptron.py b/pythainlp/tag/_tag_perceptron.py index d815d64ea..53de2fd46 100644 --- a/pythainlp/tag/_tag_perceptron.py +++ b/pythainlp/tag/_tag_perceptron.py @@ -9,6 +9,7 @@ Wannaphong Phatthiyaphaibun (PyThaiNLP port) URL: + Copyright 2013 Matthew Honnibal NLTK modifications Copyright 2015 The NLTK Project PyThaiNLP modifications Copyright 2020 PyThaiNLP Project diff --git a/pythainlp/tokenize/thai2fit.py b/pythainlp/tokenize/thai2fit.py index e6f1059f3..fab9dac62 100644 --- a/pythainlp/tokenize/thai2fit.py +++ b/pythainlp/tokenize/thai2fit.py @@ -1,4 +1,4 @@ -# SPDX-FileCopyrightText: 2026 PyThaiNLP Project +# SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project # SPDX-FileType: SOURCE # SPDX-License-Identifier: Apache-2.0 diff --git a/pythainlp/tokenize/thaisumcut.py b/pythainlp/tokenize/thaisumcut.py index 9981fda64..f1dc30f37 100644 --- a/pythainlp/tokenize/thaisumcut.py +++ b/pythainlp/tokenize/thaisumcut.py @@ -1,5 +1,6 @@ # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project -# SPDX-FileCopyrightText: Copyright 2020 Nakhun Chumpolsathien +# SPDX-FileCopyrightText: 2020 Nakhun Chumpolsathien +# SPDX-FileType: SOURCE # SPDX-License-Identifier: Apache-2.0 """The implementation of sentence segmentator from Nakhun Chumpolsathien, 2020 original codes are from: https://github.com/nakhunchumpolsathien/ThaiSum diff --git a/pythainlp/transliterate/thaig2p.py b/pythainlp/transliterate/thaig2p.py index e3d5c85e5..c86609ad0 100644 --- a/pythainlp/transliterate/thaig2p.py +++ b/pythainlp/transliterate/thaig2p.py @@ -22,7 +22,16 @@ class ThaiG2P: - """Latin transliteration of Thai words, using International Phonetic Alphabet""" + """ + Thai Grapheme-to-Phoneme using PyTorch-based model (v1). + + This is the original Thai G2P model that converts Thai text to + International Phonetic Alphabet (IPA) representation using a custom + PyTorch neural network architecture. + + For more information, see: + https://github.com/wannaphong/thai-g2p + """ def __init__(self): # get the model, download it if it's not available locally diff --git a/pythainlp/transliterate/thaig2p_v2.py b/pythainlp/transliterate/thaig2p_v2.py index aad18c0d4..6ad4fa381 100644 --- a/pythainlp/transliterate/thaig2p_v2.py +++ b/pythainlp/transliterate/thaig2p_v2.py @@ -13,7 +13,15 @@ class ThaiG2P: - """Latin transliteration of Thai words, using International Phonetic Alphabet + """ + Thai Grapheme-to-Phoneme using transformer-based model (v2). + + This version uses the Hugging Face transformers pipeline with the + pythainlp/thaig2p-v2.0 model for converting Thai text to International + Phonetic Alphabet (IPA) representation. + + For more information, see: + https://huggingface.co/pythainlp/thaig2p-v2.0 """ def __init__(self, device: str = "cpu"): diff --git a/pythainlp/transliterate/umt5_thaig2p.py b/pythainlp/transliterate/umt5_thaig2p.py index 4976fe547..57e9c7749 100644 --- a/pythainlp/transliterate/umt5_thaig2p.py +++ b/pythainlp/transliterate/umt5_thaig2p.py @@ -13,7 +13,15 @@ class Umt5ThaiG2P: - """Latin transliteration of Thai words, using International Phonetic Alphabet + """ + Thai Grapheme-to-Phoneme using UMT5 model. + + This version uses the B-K/umt5-thai-g2p-v2-0.5k model based on UMT5 + (Unified Multilingual T5) for converting Thai text to International + Phonetic Alphabet (IPA) representation. + + For more information, see: + https://huggingface.co/B-K/umt5-thai-g2p-v2-0.5k """ def __init__(self, device: str = "cpu"):