phoonnx 0.1.1a1__py3-none-any.whl → 0.2.0__py3-none-any.whl

phoonnx/config.py

@@ -45,6 +45,7 @@ class PhonemeType(str, Enum):
     MISAKI = "misaki"
     ESPEAK = "espeak"
     GRUUT = "gruut"
+    GORUUT = "goruut"
     EPITRAN = "epitran"
     BYT5 = "byt5"
     CHARSIU = "charsiu"  # technically same as byt5, but needs special handling for whitespace
@@ -394,7 +395,7 @@ def get_phonemizer(phoneme_type: PhonemeType,
     from phoonnx.phonemizers import (EpitranPhonemizer, EspeakPhonemizer, OpenPhonemizer, OpenJTaklPhonemizer,
                                      ByT5Phonemizer, CharsiuPhonemizer, DeepPhonemizer, PersianPhonemizer,
                                      G2pCPhonemizer, G2pMPhonemizer, G2PKPhonemizer, G2PEnPhonemizer,
-                                     TransphonePhonemizer, MirandesePhonemizer,
+                                     TransphonePhonemizer, MirandesePhonemizer, GoruutPhonemizer,
                                      GruutPhonemizer, GraphemePhonemizer, MantoqPhonemizer, MisakiPhonemizer,
                                      KoG2PPhonemizer, PypinyinPhonemizer, PyKakasiPhonemizer, CotoviaPhonemizer,
                                      CutletPhonemizer, PhonikudPhonemizer, VIPhonemePhonemizer, XpinyinPhonemizer,
@@ -407,6 +408,8 @@ def get_phonemizer(phoneme_type: PhonemeType,
         phonemizer = CharsiuPhonemizer(model)
     elif phoneme_type == PhonemeType.GRUUT:
         phonemizer = GruutPhonemizer()
+    elif phoneme_type == PhonemeType.GORUUT:
+        phonemizer = GoruutPhonemizer()
     elif phoneme_type == PhonemeType.EPITRAN:
         phonemizer = EpitranPhonemizer()
     elif phoneme_type == PhonemeType.MISAKI:

phoonnx/phonemizers/__init__.py

@@ -11,7 +11,7 @@ from phoonnx.phonemizers.ja import PyKakasiPhonemizer, CutletPhonemizer, OpenJTa
 from phoonnx.phonemizers.ko import KoG2PPhonemizer, G2PKPhonemizer
 from phoonnx.phonemizers.zh import (G2pCPhonemizer, G2pMPhonemizer, PypinyinPhonemizer,
                                     XpinyinPhonemizer, JiebaPhonemizer)
-from phoonnx.phonemizers.mul import (EspeakPhonemizer, EpitranPhonemizer, MisakiPhonemizer,
+from phoonnx.phonemizers.mul import (EspeakPhonemizer, EpitranPhonemizer, MisakiPhonemizer, GoruutPhonemizer,
                                      GruutPhonemizer, ByT5Phonemizer, CharsiuPhonemizer, TransphonePhonemizer)
 from phoonnx.phonemizers.mwl import MirandesePhonemizer
 
@@ -22,6 +22,7 @@ Phonemizer = Union[
     CharsiuPhonemizer,
     EspeakPhonemizer,
     GruutPhonemizer,
+    GoruutPhonemizer,
     EpitranPhonemizer,
     TransphonePhonemizer,
     MirandesePhonemizer,

phoonnx/phonemizers/mul.py

@@ -436,6 +436,187 @@ class GruutPhonemizer(BasePhonemizer):
         return pho.strip()
 
 
+class GoruutPhonemizer(BasePhonemizer):
+    """
+    A phonemizer class that uses the pygoruut library to convert text into phonemes.
+    https://github.com/neurlang/pygoruut/
+    """
+    GORUUT_LANGS_NON_STD = [
+        'BengaliDhaka', 'BengaliRahr', 'MalayArab', 'VietnameseCentral', 'VietnameseSouthern',
+        'EnglishAmerican', 'EnglishBritish', 'NahuatlClassical', 'Hebrew2', 'Hebrew3',
+        'MinnanTawianese', 'MinnanHokkien', 'MinnanTawianese2', 'MinnanHokkien2']
+    ISO639 = {
+        "af": "Afrikaans",
+        "am": "Amharic",
+        "ar": "Arabic",
+        "az": "Azerbaijani",
+        "be": "Belarusian",
+        "bn": "Bengali",
+        "my": "Burmese",
+        "ceb": "Cebuano",
+        "ce": "Chechen",
+        "zh": "ChineseMandarin",
+        "cs": "Czech",
+        "da": "Danish",
+        "nl": "Dutch",
+        "dz": "Dzongkha",
+        "en": "English",
+        "eo": "Esperanto",
+        "fa": "Farsi",
+        "fi": "Finnish",
+        "fr": "French",
+        "de": "German",
+        "el": "Greek",
+        "gu": "Gujarati",
+        "ha": "Hausa",
+        "he": "Hebrew",
+        "hi": "Hindi",
+        "hu": "Hungarian",
+        "is": "Icelandic",
+        "id": "Indonesian",
+        "tts": "Isan",
+        "it": "Italian",
+        "jam": "Jamaican",
+        "ja": "Japanese",
+        "jv": "Javanese",
+        "kk": "Kazakh",
+        "ko": "Korean",
+        "lb": "Luxembourgish",
+        "mk": "Macedonian",
+        "ml": "Malayalam",
+        "ms": "MalayLatin",
+        "mt": "Maltese",
+        "mr": "Marathi",
+        "mn": "Mongolian",
+        "ne": "Nepali",
+        "no": "Norwegian",
+        "ps": "Pashto",
+        "pl": "Polish",
+        "pt": "Portuguese",
+        "pa": "Punjabi",
+        "ro": "Romanian",
+        "ru": "Russian",
+        "sk": "Slovak",
+        "es": "Spanish",
+        "sw": "Swahili",
+        "sv": "Swedish",
+        "ta": "Tamil",
+        "te": "Telugu",
+        "th": "Thai",
+        "bo": "Tibetan",
+        "tr": "Turkish",
+        "uk": "Ukrainian",
+        "ur": "Urdu",
+        "ug": "Uyghur",
+        "vi": "VietnameseNorthern",
+        "zu": "Zulu",
+        "hy": "Armenian",
+        "eu": "Basque",
+        "bg": "Bulgarian",
+        "ca": "Catalan",
+        "ny": "Chichewa",
+        "hr": "Croatian",
+        "et": "Estonian",
+        "gl": "Galician",
+        "ka": "Georgian",
+        "km": "KhmerCentral",
+        "lo": "Lao",
+        "lv": "Latvian",
+        "lt": "Lithuanian",
+        "sr": "Serbian",
+        "tl": "Tagalog",
+        "yo": "Yoruba",
+        "sq": "Albanian",
+        "an": "Aragonese",
+        "as": "Assamese",
+        "ba": "Bashkir",
+        "bpy": "BishnupriyaManipuri",
+        "bs": "Bosnian",
+        "chr": "Cherokee",
+        "cu": "Chuvash",
+        "gla": "GaelicScottish",
+        "gle": "GaelicIrish",
+        "kl": "Greenlandic",
+        "gn": "Guarani",
+        "ht": "HaitianCreole",
+        "haw": "Hawaiian",
+        "io": "Ido",
+        "ia": "Interlingua",
+        "kn": "Kannada",
+        "quc": "Kiche",
+        "kok": "Konkani",
+        "ku": "Kurdish",
+        "ky": "Kyrgyz",
+        "qdb": "LangBelta",
+        "ltg": "Latgalian",
+        "la": "LatinClassical",
+        "lat": "LatinEcclesiastical",
+        "lfn": "LinguaFrancaNova",
+        "jbo": "Lojban",
+        "smj": "LuleSaami",
+        "mi": "Maori",
+        "nah": "NahuatlCentral",
+        "nci": "NahuatlMecayapan",
+        "ncz": "NahuatlTetelcingo",
+        "nog": "Nogai",
+        "om": "Oromo",
+        "pap": "Papiamento",
+        "qu": "Quechua",
+        "qya": "Quenya",
+        "tn": "Setswana",
+        "shn": "ShanTaiYai",
+        "sjn": "Sindarin",
+        "sd": "Sindhi",
+        "si": "Sinhala",
+        "sl": "Slovenian",
+        "tt": "Tatar",
+        "tk": "Turkmen",
+        "uz": "Uzbek",
+        "cyw": "WelshNorth",
+        "cys": "WelshSouth",
+        "yue": "Cantonese"
+    }
+
+    def __init__(self, remote_url=None):
+        super().__init__(Alphabet.IPA)
+        from pygoruut.pygoruut import Pygoruut
+        from pygoruut.pygoruut_languages import PygoruutLanguages
+
+        self.pygoruut_langs = PygoruutLanguages()
+        if remote_url is not None:
+            # 'https://hashtron.cloud'
+            self.pygoruut = Pygoruut(api=remote_url)
+        else:
+            self.pygoruut = Pygoruut()
+
+    @classmethod
+    def get_lang(cls, target_lang: str) -> str:
+        """
+        Validates and returns the closest supported language code.
+
+        Args:
+            target_lang (str): The language code to validate.
+
+        Returns:
+            str: The validated language code.
+
+        Raises:
+            ValueError: If the language code is unsupported.
+        """
+        if target_lang in cls.GORUUT_LANGS_NON_STD:
+            return target_lang
+        if target_lang.lower() == "en-us":
+            return 'EnglishAmerican'
+        if target_lang.lower() == "en-gb" or target_lang.lower() == "en-uk":
+            return 'EnglishBritish'
+        lang = cls.match_lang(target_lang, list(cls.ISO639))
+        return cls.ISO639[lang]
+
+    def phonemize_string(self, text: str, lang: str) -> str:
+        lang = self.get_lang(lang)
+        return str(self.pygoruut.phonemize(language=lang, sentence=text))
+
+
 class EpitranPhonemizer(BasePhonemizer):
     """
     """
@@ -1178,6 +1359,7 @@ if __name__ == "__main__":
     byt5 = ByT5Phonemizer()
     espeak = EspeakPhonemizer()
     gruut = GruutPhonemizer()
+    goruut = GoruutPhonemizer(remote_url='https://hashtron.cloud')
     epitr = EpitranPhonemizer()
     charsiu = CharsiuPhonemizer()
     misaki = MisakiPhonemizer()
@@ -1194,6 +1376,7 @@ if __name__ == "__main__":
     phonemes1e = charsiu.phonemize(text1, lang)
     phonemes1f = misaki.phonemize(text1, lang)
     phonemes1g = tphone.phonemize(text1, lang)
+    phonemes1h = goruut.phonemize(text1, lang)
     print(f" Espeak         Phonemes: {phonemes1}")
     print(f" Gruut          Phonemes: {phonemes1b}")
     print(f" byt5           Phonemes: {phonemes1c}")
@@ -1201,6 +1384,7 @@ if __name__ == "__main__":
     print(f" Charsiu        Phonemes: {phonemes1e}")
     print(f" Misaki         Phonemes: {phonemes1f}")
     print(f" Transphone     Phonemes: {phonemes1g}")
+    print(f" Goruut         Phonemes: {phonemes1h}")
 
     lang = "nl"
     sentence = "DJ's en bezoekers van Tomorrowland waren woensdagavond dolblij toen het paradepaardje van het festival alsnog opende in Oostenrijk op de Mainstage.\nWant het optreden van Metallica, waar iedereen zo blij mee was, zou hoe dan ook doorgaan, aldus de DJ die het nieuws aankondigde."

phoonnx/phonemizers/mwl.py

@@ -1,5 +1,4 @@
 from phoonnx.phonemizers.base import BasePhonemizer, Alphabet
-from mwl_phonemizer import CRFOrthoCorrector
 
 
 class MirandesePhonemizer(BasePhonemizer):
@@ -7,6 +6,7 @@ class MirandesePhonemizer(BasePhonemizer):
 
     def __init__(self):
         super().__init__(Alphabet.IPA)
+        from mwl_phonemizer import CRFOrthoCorrector
         self.pho = CRFOrthoCorrector()
 
     @classmethod

phoonnx/version.py

@@ -1,8 +1,8 @@
 # START_VERSION_BLOCK
 VERSION_MAJOR = 0
-VERSION_MINOR = 1
-VERSION_BUILD = 1
-VERSION_ALPHA = 1
+VERSION_MINOR = 2
+VERSION_BUILD = 0
+VERSION_ALPHA = 0
 # END_VERSION_BLOCK
 
 VERSION_STR = f"{VERSION_MAJOR}.{VERSION_MINOR}.{VERSION_BUILD}"

{phoonnx-0.1.1a1.dist-info → phoonnx-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phoonnx
-Version: 0.1.1a1
+Version: 0.2.0
 Home-page: https://github.com/TigreGotico/phoonnx
 Author: JarbasAi
 Author-email: jarbasai@mailfence.com

{phoonnx-0.1.1a1.dist-info → phoonnx-0.2.0.dist-info}/RECORD

@@ -1,14 +1,14 @@
 phoonnx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-phoonnx/config.py,sha256=aGX7PWq3_nLdn3zCp0orMsdNQaiBfjZZmvGWd_VU2KQ,19858
+phoonnx/config.py,sha256=DKgsU03g8jrAuMcVqbu-w3MWPXOUihFtRnavg6WGQ1Y,19983
 phoonnx/phoneme_ids.py,sha256=FiNgZwV6naEsBh6XwFLh3_FyOgPiCsK9qo7S0v-CmI4,13667
 phoonnx/util.py,sha256=XSjFEoqSFcujFTHxednacgC9GrSYyF-Il5L6Utmxmu4,25909
-phoonnx/version.py,sha256=Ll52GTfYXTiW5lVvWRVNSo3-ay5hISE7zYWp2aFzXvQ,237
+phoonnx/version.py,sha256=PnyMSsZaXZdPjuXrw8HLZfaosKeET2xuCUkvdWi6vRI,237
 phoonnx/voice.py,sha256=JXjmbrhJd4mmTiLgz4O_Pa5_rKGUC9xzuBfqxYDw3Mg,19420
 phoonnx/locale/ca/phonetic_spellings.txt,sha256=igv3t7jxLSRE5GHsdn57HOpxiWNcEmECPql6m02wbO0,47
 phoonnx/locale/en/phonetic_spellings.txt,sha256=xGQlWOABLzbttpQvopl9CU-NnwEJRqKx8iuylsdUoQA,27
 phoonnx/locale/gl/phonetic_spellings.txt,sha256=igv3t7jxLSRE5GHsdn57HOpxiWNcEmECPql6m02wbO0,47
 phoonnx/locale/pt/phonetic_spellings.txt,sha256=KntS8QMynEJ5A3Clvcjq4qlmL-ThSbhfD6v0nKSrlqs,49
-phoonnx/phonemizers/__init__.py,sha256=NcI_iwtWBD2hIFTfEzLo-XOhVvmZpwAVFC3sqIFS1MY,1776
+phoonnx/phonemizers/__init__.py,sha256=Ryregys3nWJrXJrOEJA-6xzOiXZWOCIwtYgd4KLW6UE,1816
 phoonnx/phonemizers/ar.py,sha256=xxILq5iyH0kcI-NqFfRK4abGtpdUbykBjt_dZmPuO2w,3216
 phoonnx/phonemizers/base.py,sha256=FHvAsvSjAl_oSa1GoeEi96CQ_JO_xkKXWq0ukuMxiuo,8660
 phoonnx/phonemizers/en.py,sha256=N2SVoVhplQao7Ej5TXbxJU-YkAgkY0Fr9iYBFnsjFSE,9271
@@ -17,8 +17,8 @@ phoonnx/phonemizers/gl.py,sha256=jEFKJJViHufZtB7lGNwWQCdWGiNKDCVZ_GRYXTaw_2c,661
 phoonnx/phonemizers/he.py,sha256=49OFS34wSFvvR9B3z2bGSzSLmlIvnn2HtkHBOkHS9Ns,1383
 phoonnx/phonemizers/ja.py,sha256=Xojsrt715ihnIiEk9K6giYqDo9Iykw-SHfIidrHtHSU,3834
 phoonnx/phonemizers/ko.py,sha256=kwWoOFqanCB8kv2JRx17A0hP78P1wbXlX6e8VBn1ezQ,2989
-phoonnx/phonemizers/mul.py,sha256=-h6uN_laUD-unNRGThzjyiOZpN6pSl4uinCndg5-0TA,94184
-phoonnx/phonemizers/mwl.py,sha256=9bwKmKQ-fXQQKK04fmKbT9QiraD0r3rKdNFZkWZP-eI,999
+phoonnx/phonemizers/mul.py,sha256=Y_M5BUY4Yka6Ba62Eea1HvgC6FTrrigaulo4KNRi1vE,99580
+phoonnx/phonemizers/mwl.py,sha256=xAOB1Bz_uVO14WbYlSFgvPxsezxzUKFwy6GT2mDgP2w,1007
 phoonnx/phonemizers/vi.py,sha256=_XJc-Xeawr1Lxr7o8mE_hJao1aGcj4g01XYAOxC_Scg,1311
 phoonnx/phonemizers/zh.py,sha256=88Ywq8h9LDanlyz8RHjRSCY_PRK_Dq808tBADyrgaP8,9657
 phoonnx/thirdparty/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -83,7 +83,7 @@ phoonnx_train/vits/utils.py,sha256=exiyrtPHbnnGvcHWSbaH9-gR6srH5ZPHlKiqV2IHUrQ,4
 phoonnx_train/vits/wavfile.py,sha256=oQZiTIrdw0oLTbcVwKfGXye1WtKte6qK_52qVwiMvfc,26396
 phoonnx_train/vits/monotonic_align/__init__.py,sha256=5IdAOD1Z7UloMb6d_9NRFsXoNIjEQ3h9mvOSh_AtO3k,636
 phoonnx_train/vits/monotonic_align/setup.py,sha256=0K5iJJ2mKIklx6ncEfCQS34skm5hHPiz9vRlQEvevvY,266
-phoonnx-0.1.1a1.dist-info/METADATA,sha256=HkE1TTQPlxfTGOzlG55_lO4BH_4mjNlhL7vr_UrAwyI,8250
-phoonnx-0.1.1a1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-phoonnx-0.1.1a1.dist-info/top_level.txt,sha256=ZrnHXe-4HqbOSX6fbdY-JiP7YEu2Bok9T0ji351MrmM,22
-phoonnx-0.1.1a1.dist-info/RECORD,,
+phoonnx-0.2.0.dist-info/METADATA,sha256=dusaBmyR3gLPkJJ4ZHCre1N_8AWsY6W-Q3kNEpImGjA,8248
+phoonnx-0.2.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+phoonnx-0.2.0.dist-info/top_level.txt,sha256=ZrnHXe-4HqbOSX6fbdY-JiP7YEu2Bok9T0ji351MrmM,22
+phoonnx-0.2.0.dist-info/RECORD,,