PyThaiTTS 0.4.2__tar.gz → 0.5.0__tar.gz

{pythaitts-0.4.2 → pythaitts-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyThaiTTS
-Version: 0.4.2
+Version: 0.5.0
 Summary: Open Source Thai Text-to-speech library in Python
 Home-page: https://github.com/pythainlp/pythaitts
 Author: Wannaphong
@@ -26,6 +26,7 @@ Requires-Dist: numpy>=1.22
 Requires-Dist: onnxruntime
 Requires-Dist: vachanatts
 Requires-Dist: soundfile
+Requires-Dist: pythainlp
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -76,14 +77,22 @@ PyThaiTTS supports multiple TTS models. You can specify which model to use:
 from pythaitts import TTS
 
 # Use VachanaTTS (default voices: th_f_1, th_m_1, th_f_2, th_m_2)
+# Sample Rate is 22050 Hz
 tts = TTS(pretrained="vachana")
 file = tts.tts("สวัสดีครับ", speaker_idx="th_f_1", filename="output.wav")
 
 # Use Lunarlist ONNX (default)
+# Sample Rate is 22050 Hz
 tts = TTS(pretrained="lunarlist_onnx")
 file = tts.tts("ภาษาไทย ง่าย มาก", filename="output.wav")
 
+# Use FastThaiG2P (default voice: thai_som)
+# FastThaiG2P Sample Rate is 24000 Hz
+tts = TTS(pretrained="fastthaig2p")
+file = tts.tts("สวัสดีครับ", speaker_idx="thai_som", filename="output.wav")
+
 # Use KhanomTan
+# Sample Rate is 16000 Hz
 tts = TTS(pretrained="khanomtan")
 file = tts.tts("ภาษาไทย", speaker_idx="Linda", filename="output.wav")
 ```

{pythaitts-0.4.2 → pythaitts-0.5.0}/PyThaiTTS.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyThaiTTS
-Version: 0.4.2
+Version: 0.5.0
 Summary: Open Source Thai Text-to-speech library in Python
 Home-page: https://github.com/pythainlp/pythaitts
 Author: Wannaphong
@@ -26,6 +26,7 @@ Requires-Dist: numpy>=1.22
 Requires-Dist: onnxruntime
 Requires-Dist: vachanatts
 Requires-Dist: soundfile
+Requires-Dist: pythainlp
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -76,14 +77,22 @@ PyThaiTTS supports multiple TTS models. You can specify which model to use:
 from pythaitts import TTS
 
 # Use VachanaTTS (default voices: th_f_1, th_m_1, th_f_2, th_m_2)
+# Sample Rate is 22050 Hz
 tts = TTS(pretrained="vachana")
 file = tts.tts("สวัสดีครับ", speaker_idx="th_f_1", filename="output.wav")
 
 # Use Lunarlist ONNX (default)
+# Sample Rate is 22050 Hz
 tts = TTS(pretrained="lunarlist_onnx")
 file = tts.tts("ภาษาไทย ง่าย มาก", filename="output.wav")
 
+# Use FastThaiG2P (default voice: thai_som)
+# FastThaiG2P Sample Rate is 24000 Hz
+tts = TTS(pretrained="fastthaig2p")
+file = tts.tts("สวัสดีครับ", speaker_idx="thai_som", filename="output.wav")
+
 # Use KhanomTan
+# Sample Rate is 16000 Hz
 tts = TTS(pretrained="khanomtan")
 file = tts.tts("ภาษาไทย", speaker_idx="Linda", filename="output.wav")
 ```

pythaitts-0.5.0/PyThaiTTS.egg-info/SOURCES.txt

@@ -0,0 +1,37 @@
+LICENSE
+README.md
+setup.py
+PyThaiTTS.egg-info/PKG-INFO
+PyThaiTTS.egg-info/SOURCES.txt
+PyThaiTTS.egg-info/dependency_links.txt
+PyThaiTTS.egg-info/not-zip-safe
+PyThaiTTS.egg-info/requires.txt
+PyThaiTTS.egg-info/top_level.txt
+pythaitts/__init__.py
+pythaitts/preprocess.py
+pythaitts/pretrained/__init__.py
+pythaitts/pretrained/khanomtan_tts.py
+pythaitts/pretrained/lunarlist_model.py
+pythaitts/pretrained/lunarlist_onnx.py
+pythaitts/pretrained/vachana_tts.py
+pythaitts/pretrained/fastthaig2p/__init__.py
+pythaitts/pretrained/fastthaig2p/_data.py
+pythaitts/pretrained/fastthaig2p/_th2ipa.py
+pythaitts/pretrained/fastthaig2p/fallback.py
+pythaitts/pretrained/fastthaig2p/g2p.py
+pythaitts/pretrained/fastthaig2p/kokoro.py
+pythaitts/pretrained/fastthaig2p/normalizer.py
+pythaitts/pretrained/fastthaig2p/tokenizer.py
+pythaitts/pretrained/fastthaig2p/tts.py
+pythaitts/pretrained/fastthaig2p/data/dict.txt
+pythaitts/pretrained/fastthaig2p/data/ipa.json
+pythaitts/pretrained/fastthaig2p/data/fallback/PhSTrigram.sts
+pythaitts/pretrained/fastthaig2p/data/fallback/sylform_var.pkl
+pythaitts/pretrained/fastthaig2p/data/fallback/sylrule.lts
+pythaitts/pretrained/fastthaig2p/data/fallback/sylseg.3g
+pythaitts/pretrained/fastthaig2p/data/fallback/thaisyl.dict
+pythaitts/pretrained/fastthaig2p/data/fallback/thdict
+tests/__init__.py
+tests/test_fastthaig2p.py
+tests/test_preprocess.py
+tests/test_vachana.py

{pythaitts-0.4.2 → pythaitts-0.5.0}/PyThaiTTS.egg-info/requires.txt

@@ -3,3 +3,4 @@ numpy>=1.22
 onnxruntime
 vachanatts
 soundfile
+pythainlp

{pythaitts-0.4.2 → pythaitts-0.5.0}/README.md

@@ -34,14 +34,22 @@ PyThaiTTS supports multiple TTS models. You can specify which model to use:
 from pythaitts import TTS
 
 # Use VachanaTTS (default voices: th_f_1, th_m_1, th_f_2, th_m_2)
+# Sample Rate is 22050 Hz
 tts = TTS(pretrained="vachana")
 file = tts.tts("สวัสดีครับ", speaker_idx="th_f_1", filename="output.wav")
 
 # Use Lunarlist ONNX (default)
+# Sample Rate is 22050 Hz
 tts = TTS(pretrained="lunarlist_onnx")
 file = tts.tts("ภาษาไทย ง่าย มาก", filename="output.wav")
 
+# Use FastThaiG2P (default voice: thai_som)
+# FastThaiG2P Sample Rate is 24000 Hz
+tts = TTS(pretrained="fastthaig2p")
+file = tts.tts("สวัสดีครับ", speaker_idx="thai_som", filename="output.wav")
+
 # Use KhanomTan
+# Sample Rate is 16000 Hz
 tts = TTS(pretrained="khanomtan")
 file = tts.tts("ภาษาไทย", speaker_idx="Linda", filename="output.wav")
 ```

{pythaitts-0.4.2 → pythaitts-0.5.0}/pythaitts/__init__.py

@@ -2,16 +2,16 @@
 """
 PyThaiTTS
 """
-__version__ = "0.4.2"
+__version__ = "0.5.0"
 
 from pythaitts.preprocess import preprocess_text, num_to_thai, expand_maiyamok
 
 
 class TTS:
-    def __init__(self, pretrained="lunarlist_onnx", mode="last_checkpoint", version="1.0", device:str="cpu") -> None:
+    def __init__(self, pretrained="lunarlist_onnx", mode="last_checkpoint", version="1.0", device:str="cpu", **kwargs) -> None:
         """
-        :param str pretrained: TTS pretrained (lunarlist_onnx, khanomtan, lunarlist, vachana)
-        :param str mode: pretrained mode (lunarlist_onnx and vachana don't support)
+        :param str pretrained: TTS pretrained (lunarlist_onnx, khanomtan, lunarlist, vachana, fastthaig2p)
+        :param str mode: pretrained mode (lunarlist_onnx, vachana, and fastthaig2p don't support)
         :param str version: model version (default is 1.0 or 1.1)
         :param str device: device for running model. (lunarlist_onnx and vachana support CPU only.)
 
@@ -32,14 +32,15 @@ class TTS:
         For vachana tts model, \
         You can see more about vachana tts at `https://github.com/VYNCX/VachanaTTS2 <https://github.com/VYNCX/VachanaTTS2>`_
 
-        
+        For fastthaig2p tts model, \
+        You can see more about fastthaig2p at `https://github.com/awslabs/FastThaiG2P <https://github.com/awslabs/FastThaiG2P>`_
         """
         self.pretrained = pretrained
         self.mode = mode
         self.device = device
-        self.load_pretrained(version=version)
+        self.load_pretrained(version=version, **kwargs)
 
-    def load_pretrained(self,version):
+    def load_pretrained(self, version="1.0", **kwargs):
         """
         Load pretrained
         """
@@ -55,21 +56,25 @@ class TTS:
         elif self.pretrained == "vachana":
             from pythaitts.pretrained.vachana_tts import VachanaTTS
             self.model = VachanaTTS()
+        elif self.pretrained in ("fastthaig2p", "FastThaiG2P"):
+            from pythaitts.pretrained.fastthaig2p import FastThaiG2P
+            self.model = FastThaiG2P(device=self.device, **kwargs)
         else:
             raise NotImplementedError(
                 "PyThaiTTS doesn't support %s pretrained." % self.pretrained
             )
 
-    def tts(self, text: str, speaker_idx: str = "Linda", language_idx: str = "th-th", return_type: str = "file", filename: str = None, preprocess: bool = True):
+    def tts(self, text: str, speaker_idx: str = "Linda", language_idx: str = "th-th", return_type: str = "file", filename: str = None, preprocess: bool = True, **kwargs):
         """
         speech synthesis
 
         :param str text: text
-        :param str speaker_idx: speaker (default is Linda for khanomtan, th_f_1 for vachana)
+        :param str speaker_idx: speaker (default is Linda for khanomtan, th_f_1 for vachana, thai_som for fastthaig2p)
         :param str language_idx: language (default is th-th)
         :param str return_type: return type (default is file)
         :param str filename: path filename for save wav file if return_type is file.
         :param bool preprocess: whether to preprocess text (convert numbers to Thai text and expand ๆ). Default is True.
+        :param kwargs: Additional parameters passed to the underlying model.
         """
         # Preprocess text if requested
         if preprocess:
@@ -79,7 +84,11 @@ class TTS:
         if self.pretrained == "lunarlist" or self.pretrained == "lunarlist_onnx":
             return self.model(text=text,return_type=return_type,filename=filename)
         elif self.pretrained == "vachana":
-            return self.model(text=text,speaker_idx=speaker_idx,return_type=return_type,filename=filename)
+            return self.model(text=text,speaker_idx=speaker_idx,return_type=return_type,filename=filename, **kwargs)
+        elif self.pretrained in ("fastthaig2p", "FastThaiG2P"):
+            if speaker_idx in ("Linda", None):
+                speaker_idx = "thai_som"
+            return self.model(text=text,speaker_idx=speaker_idx,return_type=return_type,filename=filename, **kwargs)
         return self.model(
             text=text,
             speaker_idx=speaker_idx,

pythaitts-0.5.0/pythaitts/pretrained/fastthaig2p/__init__.py

@@ -0,0 +1,35 @@
+# -*- coding: utf-8 -*-
+"""
+## License
+
+Copyright 2026 Charin Polpanumas and Amazon Web Services
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+"""
+from __future__ import annotations
+
+from .g2p import G2P
+from .kokoro import ipa_to_kokoro
+from .normalizer import normalize
+from .tokenizer import Tokenizer
+
+__all__ = ["G2P", "Tokenizer", "normalize", "ipa_to_kokoro", "TTS", "FastThaiG2P"]
+
+
+def __getattr__(name):
+    if name in ("TTS", "FastThaiG2P"):
+        from .tts import TTS, FastThaiG2P
+
+        return FastThaiG2P if name == "FastThaiG2P" else TTS
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+

pythaitts-0.5.0/pythaitts/pretrained/fastthaig2p/_data.py

@@ -0,0 +1,30 @@
+"""Locate runtime data in both layouts: installed wheel (fastthaig2p/data,
+via the force-include in pyproject.toml) and repo checkout (../data).
+
+## License
+
+Copyright 2026 Charin Polpanumas and Amazon Web Services
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+"""
+
+from pathlib import Path
+
+_PKG = Path(__file__).parent
+
+
+def data_path(*parts: str) -> Path:
+    installed = _PKG / "data" / Path(*parts)
+    if installed.exists():
+        return installed
+    return _PKG.parent / "data" / Path(*parts)