cloudlanguagetools 11.3.0__tar.gz → 11.3.2__tar.gz

{cloudlanguagetools-11.3.0 → cloudlanguagetools-11.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cloudlanguagetools
-Version: 11.3.0
+Version: 11.3.2
 Summary: Interface with various cloud APIs for language processing such as translation, text to speech
 Home-page: https://github.com/Language-Tools/cloud-language-tools-core
 Author: Luc

{cloudlanguagetools-11.3.0 → cloudlanguagetools-11.3.2}/cloudlanguagetools/azure.py

@@ -91,6 +91,12 @@ class AzureVoice(cloudlanguagetools.ttsvoice.TtsVoice):
         return VOICE_OPTIONS
 
 def locale_to_audio_language(locale: str) -> cloudlanguagetools.languages.AudioLanguage:
+
+    locale_override_map = {
+        'zh-CN-shanxi': 'zh-CN-shaanxi'
+    }
+    locale = locale_override_map.get(locale, locale)
+
     locale = AUDIO_LOCALE_OVERRIDE_MAP.get(locale, locale)
     language_enum_name = locale.replace('-', '_')
     audio_language = cloudlanguagetools.languages.AudioLanguage[language_enum_name]    
@@ -159,7 +165,7 @@ def get_translation_language_enum(language_id):
         'iu-Latn': 'iu_latn',
         'lug': 'lg',
         'nya': 'ny',
-        'run': 'rn'
+        'run': 'rn',
     }
     if language_id in azure_language_id_map:
         language_id = azure_language_id_map[language_id]

{cloudlanguagetools-11.3.0 → cloudlanguagetools-11.3.2}/cloudlanguagetools/elevenlabs.py

@@ -247,12 +247,13 @@ class ElevenLabsService(cloudlanguagetools.service.Service):
             model_short_name = model_name.replace('Eleven ', '').strip()
             # for language_record in model['languages']:
             for voice_data in data['voices']:
+                voice_name = voice_data['name']
                 try:
                     languages = model['languages']
                     language_id_list = [language_record['language_id'] for language_record in languages]
                     audio_language_enum_list = [self.get_audio_language(language_id) for language_id in language_id_list]
                     voice = cloudlanguagetools.ttsvoice.TtsVoice_v3(
-                        name=voice_data['name'],
+                        name=f'{voice_name} ({model_short_name})',
                         voice_key={
                             'voice_id': voice_data['voice_id'],
                             'model_id': model_id,

{cloudlanguagetools-11.3.0 → cloudlanguagetools-11.3.2}/cloudlanguagetools/forvo.py

@@ -127,8 +127,8 @@ class ForvoService(cloudlanguagetools.service.Service):
             'ind': 'id_',
             'pt': 'pt_pt'
         }
-        if language_id in forvo_language_id_map:
-            language_id = forvo_language_id_map[language_id]
+        language_id = forvo_language_id_map.get(language_id, language_id)
+        logger.debug(f'looking for {language_id}')
         return cloudlanguagetools.languages.Language[language_id]
 
     def get_audio_language_enum(self, language_id):
@@ -226,6 +226,7 @@ class ForvoService(cloudlanguagetools.service.Service):
             cloudlanguagetools.languages.AudioLanguage.zh_HK: 'HKG',
             cloudlanguagetools.languages.AudioLanguage.yue_CN: 'CHN',
             cloudlanguagetools.languages.AudioLanguage.wuu_CN: 'CHN',
+            cloudlanguagetools.languages.AudioLanguage.nan_CN: 'CHN',
             cloudlanguagetools.languages.AudioLanguage.zh_CN_henan: 'CHN',
             cloudlanguagetools.languages.AudioLanguage.zh_CN_liaoning: 'CHN',
             cloudlanguagetools.languages.AudioLanguage.zh_CN_shaanxi: 'CHN',
@@ -233,6 +234,10 @@ class ForvoService(cloudlanguagetools.service.Service):
             cloudlanguagetools.languages.AudioLanguage.zh_CN_sichuan: 'CHN',
             cloudlanguagetools.languages.AudioLanguage.zh_CN_guangxi: 'CHN',
 
+            cloudlanguagetools.languages.AudioLanguage.zh_CN_gansu: 'CHN',
+            cloudlanguagetools.languages.AudioLanguage.zh_CN_anhui: 'CHN',
+            cloudlanguagetools.languages.AudioLanguage.zh_CN_hunan: 'CHN'
+
         }
         if audio_language not in country_code_map:
             logging.error(f'no country code found for {audio_language}')
@@ -244,6 +249,7 @@ class ForvoService(cloudlanguagetools.service.Service):
             language_enum = self.get_language_enum(language_code)
             # create as many voices as there are audio languages available
 
+            logger.debug(f'processing language_enum {language_enum}')
             audio_language_list = self.audio_language_map[language_enum]
             
             voices = []
@@ -287,7 +293,8 @@ class ForvoService(cloudlanguagetools.service.Service):
             data = response.json()
             languages = data['items']
             for language in languages:
-                voice_list.extend(self.get_voices_for_language_entry(language))
+                language_voice_list = self.get_voices_for_language_entry(language)
+                voice_list.extend(language_voice_list)
 
             # pprint.pprint(data)
         else:

{cloudlanguagetools-11.3.0 → cloudlanguagetools-11.3.2}/cloudlanguagetools/google.py

@@ -86,6 +86,7 @@ def get_translation_language_enum(language_id):
         'or': 'or_',
         'pt': 'pt_br',
         'pt-pt': 'pt_pt',
+        'pt-PT': 'pt_pt',
         'sr': 'sr_cyrl',
         'sr-Cyrl': 'sr_cyrl',
         'sr-Latn': 'sr_latn',
@@ -201,7 +202,7 @@ class GoogleService(cloudlanguagetools.service.Service):
                 translation_language = GoogleTranslationLanguage(entry['language'])
                 result_dict[translation_language.get_language_code()] = translation_language
             except KeyError:
-                logging.error(f'could not process translation language for {entry}', exc_info=True)                
+                logging.warn(f'could not process translation language for {entry}', exc_info=True)
         return result_dict.values()
 
     def get_transliteration_language_list(self):

{cloudlanguagetools-11.3.0 → cloudlanguagetools-11.3.2}/cloudlanguagetools/languages.py

@@ -352,6 +352,7 @@ class AudioLanguage(enum.Enum):
     ms_MY = (Language.ms, "Malay")
     mt_MT = (Language.mt, "Maltese (Malta)")
     my_MM = (Language.my, "Burmese (Myanmar [Burma])")
+    nan_CN = (Language.zh_cn, "Chinese (Minnan)")
     nb_NO = (Language.nb, "Norwegian (Norway)")
     ne_NP = (Language.ne, "Nepali (Nepal)")
     nl_BE = (Language.nl, "Dutch (Belgium)")
@@ -400,6 +401,10 @@ class AudioLanguage(enum.Enum):
     zh_CN_shandong = (Language.zh_cn, 'Chinese (Jilu Mandarin, Simplified)')
     zh_CN_sichuan = (Language.zh_cn, 'Chinese (Southwestern Mandarin, Simplified)')
     zh_CN_guangxi = (Language.zh_cn, 'Chinese (Guangxi Accent Mandarin, Simplified)')
+    zh_CN_gansu = (Language.zh_cn, 'Chinese (Lanyin Mandarin Gansu, Simplified)')
+    zh_CN_anhui = (Language.zh_cn, 'Chinese (Jianghuai Mandarin Anhui, Simplified)')
+    zh_CN_hunan = (Language.zh_cn, 'Chinese (Hunan Accent Mandarin, Simplified)')
+
 
     fa_IR = (Language.fa, "Persian (Iran)")
     zu_ZA = (Language.zu, "Zulu (South Africa)")

{cloudlanguagetools-11.3.0 → cloudlanguagetools-11.3.2}/cloudlanguagetools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cloudlanguagetools
-Version: 11.3.0
+Version: 11.3.2
 Summary: Interface with various cloud APIs for language processing such as translation, text to speech
 Home-page: https://github.com/Language-Tools/cloud-language-tools-core
 Author: Luc

{cloudlanguagetools-11.3.0 → cloudlanguagetools-11.3.2}/setup.py

@@ -6,7 +6,7 @@ from setuptools.command.install import install
 # twine upload dist/*
 
 setup(name='cloudlanguagetools',
-      version='11.3.0',
+      version='11.3.2',
       description='Interface with various cloud APIs for language processing such as translation, text to speech',
       long_description=open('README.rst', encoding='utf-8').read(),
       url='https://github.com/Language-Tools/cloud-language-tools-core',