Merge pull request #923 from PyThaiNLP/add-thaig2p_v2

Add thaig2p_v2

Author: wannaphong

docs/api/transliterate.rst

@@ -55,7 +55,8 @@ This section includes multiple transliteration engines designed to suit various
 
 - **icu**: Utilizes the ICU transliteration system for phonetic conversion.
 - **ipa**: Provides International Phonetic Alphabet (IPA) representation of Thai text.
-- **thaig2p**: Transliterates Thai text into the Grapheme-to-Phoneme (G2P) representation.
+- **thaig2p**: (default) Transliterates Thai text into the Grapheme-to-Phoneme (G2P) representation.
+- **thaig2p_v2**: Transliterates Thai text into the Grapheme-to-Phoneme (G2P) representation. This model is from https://huggingface.co/pythainlp/thaig2p-v2.0
 - **tltk**: Utilizes the TLTK transliteration system for a specific approach to transliteration.
 - **iso_11940**: Focuses on the ISO 11940 transliteration standard.
 

pythainlp/transliterate/core.py

@@ -109,6 +109,8 @@ def transliterate(
             `TLTK <https://pypi.org/project/tltk/>`_.,
         * *iso_11940* - Thai text into Latin characters with ISO 11940.
         * *tltk_ipa* - tltk, output is International Phonetic Alphabet (IPA)
+        * *thaig2p_v2* - Thai Grapheme-to-Phoneme,
+          output is IPA. https://huggingface.co/pythainlp/thaig2p-v2.0
 
     :Example:
     ::
@@ -159,6 +161,8 @@ def transliterate(
         from pythainlp.transliterate.tltk import tltk_ipa as transliterate
     elif engine == "iso_11940":
         from pythainlp.transliterate.iso_11940 import transliterate
+    elif engine == "thaig2p_v2":
+        from pythainlp.transliterate.thaig2p_v2 import transliterate
     else:  # use default engine: "thaig2p"
         from pythainlp.transliterate.thaig2p import transliterate
 

pythainlp/transliterate/thaig2p_v2.py

@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-License-Identifier: Apache-2.0
+"""
+Thai Grapheme-to-Phoneme (Thai G2P)
+
+huggingface: https://huggingface.co/pythainlp/thaig2p-v2.0
+"""
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+
+class ThaiG2P:
+    """
+    Latin transliteration of Thai words, using International Phonetic Alphabet
+    """
+
+    def __init__(self, device: str = "cpu"):
+        self.pipe = pipeline("text2text-generation", model="pythainlp/thaig2p-v2.0", device=device)
+
+    def g2p(self, text: str) -> str:
+        return self.pipe(text)[0]["generated_text"]
+
+
+_THAI_G2P = None
+
+
+def transliterate(text: str, device="cpu") -> str:
+    global _THAI_G2P
+    if _THAI_G2P is None:
+        _THAI_G2P = ThaiG2P(device=device)
+    return _THAI_G2P.g2p(text)

tests/test_transliterate.py

@@ -216,6 +216,8 @@ def test_transliterate(self):
         self.assertEqual(transliterate("คน", engine="ipa"), "kʰon")
         self.assertIsNotNone(transliterate("คน", engine="thaig2p"))
         self.assertIsNotNone(transliterate("แมว", engine="thaig2p"))
+        self.assertIsNotNone(transliterate("คน", engine="thaig2p_v2"))
+        self.assertIsNotNone(transliterate("แมว", engine="thaig2p_v2"))
         self.assertIsNotNone(transliterate("คน", engine="tltk_g2p"))
         self.assertIsNotNone(transliterate("แมว", engine="tltk_g2p"))
         self.assertIsNotNone(transliterate("คน", engine="tltk_ipa"))