Update model entry

TTS/.models.json

@@ -3,17 +3,17 @@
         "multilingual": {
             "multi-dataset": {
                 "xtts_v2": {
-                    "description": "",
+                    "description": "XTTS-v2 by Coqui with 16 languages.",
                     "hf_url": [
-                        "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/v1.0.0/model.pth",
+                        "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/model.pth",
-                        "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/v1.0.0/config.json",
+                        "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/config.json",
-                        "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/v1.0.0/vocab.json",
+                        "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/vocab.json",
-                        "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.1/hash.md5"
+                        "https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/hash.md5"
                     ],
                     "default_vocoder": null,
-                    "commit": "e9a1953e",
+                    "commit": "480a6cdf7",
                     "license": "CPML",
-                    "contact": "",
+                    "contact": "info@coqui.ai",
                     "tos_required": true
                 },
                 "xtts_v1": {

TTS/tts/layers/xtts/tokenizer.py

@@ -8,6 +8,9 @@ from num2words import num2words
 from tokenizers import Tokenizer
 
 from TTS.tts.layers.xtts.zh_num2words import TextNorm as zh_num2words
+from hangul_romanize import Transliter
+from hangul_romanize.rule import academic
+
 
 _whitespace_re = re.compile(r"\s+")
 
@@ -112,7 +115,7 @@ _abbreviations = {
             # There are not many common abbreviations in Arabic as in English.
         ]
     ],
-    "zh-cn": [
+    "zh": [
         (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
         for x in [
             # Chinese doesn't typically use abbreviations in the same way as Latin-based scripts.
@@ -155,6 +158,22 @@ _abbreviations = {
             # Add other Turkish abbreviations here if needed.
         ]
     ],
+    "hu": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("dr", "doktor"),     # doctor
+            ("b", "bácsi"),   # Mr.
+            ("nőv", "nővér"),     # nurse
+            # Add other Hungarian abbreviations here if needed.
+        ]
+    ],
+    "ko": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            # Korean doesn't typically use abbreviations in the same way as Latin-based scripts.
+
+        ]
+    ]
 }
 
 
@@ -262,7 +281,7 @@ _symbols_multilingual = {
             ("°", " درجة "),
         ]
     ],
-    "zh-cn": [
+    "zh": [
         # Chinese
         (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
         for x in [
@@ -326,6 +345,31 @@ _symbols_multilingual = {
             ("°", " derece "),
         ]
     ],
+    "hu": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " és "),
+            ("@", " kukac "),
+            ("%", " százalék "),
+            ("#", " kettőskereszt "),
+            ("$", " dollár "),
+            ("£", " font "),
+            ("°", " fok ")
+        ]
+    ],
+    "ko": [
+        # Korean
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " 그리고 "),
+            ("@", " 에 "),
+            ("%", " 퍼센트 "),
+            ("#", " 번호 "),
+            ("$", " 달러 "),
+            ("£", " 파운드 "),
+            ("°", " 도 ")
+        ]
+    ]
 }
 
 
@@ -349,6 +393,8 @@ _ordinal_re = {
     "ru": re.compile(r"([0-9]+)(-й|-я|-е|-ое|-ье|-го)"),
     "nl": re.compile(r"([0-9]+)(de|ste|e)"),
     "tr": re.compile(r"([0-9]+)(\.|inci|nci|uncu|üncü|\.)"),
+    "hu": re.compile(r"([0-9]+)(\.|adik|edik|odik|edik|ödik|ödike|ik)"),
+    "ko": re.compile(r"([0-9]+)(번째|번|차|째)"),
 }
 _number_re = re.compile(r"[0-9]+")
 _currency_re = {
@@ -398,6 +444,8 @@ def _expand_currency(m, lang="en", currency="USD"):
         "nl": ", ",
         "ar": ", ",
         "tr": ", ",
+        "hu": ", ",
+        "ko": ", ",
     }
 
     if amount.is_integer():
@@ -415,9 +463,14 @@ def _expand_ordinal(m, lang="en"):
 def _expand_number(m, lang="en"):
     return num2words(int(m.group(0)), lang=lang if lang != "cs" else "cz")
 
+<<<<<<< HEAD
 
 def expand_numbers_multilingual(text, lang="en"):
     if lang == "zh-cn":
+=======
+def expand_numbers_multilingual(text, lang='en'):
+    if lang == "zh" or lang == "zh-cn":
+>>>>>>> Update model entry
         text = zh_num2words()(text)
     else:
         if lang in ["en", "ru"]:
@@ -472,30 +525,41 @@ def chinese_transliterate(text):
     )
 
 
+
 def japanese_cleaners(text, katsu):
     text = katsu.romaji(text)
     text = lowercase(text)
     return text
 
+<<<<<<< HEAD
 
 class VoiceBpeTokenizer:
     def __init__(self, vocab_file=None, preprocess=None):
         self.tokenizer = None
         self.katsu = None
+=======
+>>>>>>> Update model entry
 
-        if vocab_file is not None:
+def korean_cleaners(text):
-            with open(vocab_file, "r", encoding="utf-8") as f:
+    r = Transliter(academic)
-                vocab = json.load(f)
+    return r.translit(text)
 
-            self.language = vocab["model"]["language"] if "language" in vocab["model"] else None
 
-            if preprocess is None:
+def preprocess_text(txt, lang):
-                self.preprocess = "pre_tokenizer" in vocab and vocab["pre_tokenizer"]
+    if lang in ["en", "es", "fr", "de", "pt", "it", "pl", "zh", "ar", "cs", "ru", "nl", "tr", "hu"]:
-            else:
+        txt = multilingual_cleaners(txt, lang)
-                self.preprocess = preprocess
+    elif lang == "ja":
+        txt = japanese_cleaners(txt)
+    elif lang == "zh-cn" or lang == "zh":
+        txt = chinese_transliterate(txt)
+    elif lang == "ko":
+        txt = korean_cleaners(txt)
+    else:
+        raise NotImplementedError()
+    return txt
 
-            self.tokenizer = Tokenizer.from_file(vocab_file)
 
+<<<<<<< HEAD
     def preprocess_text(self, txt, lang):
         if lang in ["en", "es", "fr", "de", "pt", "it", "pl", "ar", "cs", "ru", "nl", "tr", "zh-cn"]:
             txt = multilingual_cleaners(txt, lang)
@@ -510,10 +574,20 @@ class VoiceBpeTokenizer:
         else:
             raise NotImplementedError()
         return txt
+=======
+DEFAULT_VOCAB_FILE = os.path.join(
+    os.path.dirname(os.path.realpath(__file__)), "../data/tokenizer.json"
+)
+
+class VoiceBpeTokenizer:
+    def __init__(self, vocab_file=None):
+        self.tokenizer = None
+        if vocab_file is not None:
+            self.tokenizer = Tokenizer.from_file(vocab_file)
+>>>>>>> Update model entry
 
     def encode(self, txt, lang):
-        if self.preprocess:
+        txt = preprocess_text(txt, lang)
-            txt = self.preprocess_text(txt, lang)
         txt = f"[{lang}]{txt}"
         txt = txt.replace(" ", "[SPACE]")
         return self.tokenizer.encode(txt).ids
@@ -532,3 +606,171 @@ class VoiceBpeTokenizer:
 
     def get_number_tokens(self):
         return max(self.tokenizer.get_vocab().values()) + 1
+
+
+def test_expand_numbers_multilingual():
+    test_cases = [
+        # English
+        ("In 12.5 seconds.", 'In twelve point five seconds.', 'en'),
+        ("There were 50 soldiers.", 'There were fifty soldiers.', 'en'),
+        ("This is a 1st test", 'This is a first test', 'en'),
+        ("That will be $20 sir.", 'That will be twenty dollars sir.', 'en'),
+        ("That will be 20€ sir.", 'That will be twenty euro sir.', 'en'),
+        ("That will be 20.15€ sir.", 'That will be twenty euro, fifteen cents sir.', 'en'),
+        ("That's 100,000.5.", 'That\'s one hundred thousand point five.', 'en'),
+        # French
+        ("En 12,5 secondes.", 'En douze virgule cinq secondes.', 'fr'),
+        ("Il y avait 50 soldats.", 'Il y avait cinquante soldats.', 'fr'),
+        ("Ceci est un 1er test", 'Ceci est un premier test', 'fr'),
+        ("Cela vous fera $20 monsieur.", 'Cela vous fera vingt dollars monsieur.', 'fr'),
+        ("Cela vous fera 20€ monsieur.", 'Cela vous fera vingt euros monsieur.', 'fr'),
+        ("Cela vous fera 20,15€ monsieur.", 'Cela vous fera vingt euros et quinze centimes monsieur.', 'fr'),
+        ("Ce sera 100.000,5.", 'Ce sera cent mille virgule cinq.', 'fr'),
+        # German
+        ("In 12,5 Sekunden.", 'In zwölf Komma fünf Sekunden.', 'de'),
+        ("Es gab 50 Soldaten.", 'Es gab fünfzig Soldaten.', 'de'),
+        ("Dies ist ein 1. Test", 'Dies ist ein erste Test', 'de'), # Issue with gender
+        ("Das macht $20 Herr.", 'Das macht zwanzig Dollar Herr.', 'de'),
+        ("Das macht 20€ Herr.", 'Das macht zwanzig Euro Herr.', 'de'),
+        ("Das macht 20,15€ Herr.", 'Das macht zwanzig Euro und fünfzehn Cent Herr.', 'de'),
+        # Spanish
+        ("En 12,5 segundos.", 'En doce punto cinco segundos.', 'es'),
+        ("Había 50 soldados.", 'Había cincuenta soldados.', 'es'),
+        ("Este es un 1er test", 'Este es un primero test', 'es'),
+        ("Eso le costará $20 señor.", 'Eso le costará veinte dólares señor.', 'es'),
+        ("Eso le costará 20€ señor.", 'Eso le costará veinte euros señor.', 'es'),
+        ("Eso le costará 20,15€ señor.", 'Eso le costará veinte euros con quince céntimos señor.', 'es'),
+        # Italian
+        ("In 12,5 secondi.", 'In dodici virgola cinque secondi.', 'it'),
+        ("C'erano 50 soldati.", "C'erano cinquanta soldati.", 'it'),
+        ("Questo è un 1° test", 'Questo è un primo test', 'it'),
+        ("Ti costerà $20 signore.", 'Ti costerà venti dollari signore.', 'it'),
+        ("Ti costerà 20€ signore.", 'Ti costerà venti euro signore.', 'it'),
+        ("Ti costerà 20,15€ signore.", 'Ti costerà venti euro e quindici centesimi signore.', 'it'),
+        # Portuguese
+        ("Em 12,5 segundos.", 'Em doze vírgula cinco segundos.', 'pt'),
+        ("Havia 50 soldados.", 'Havia cinquenta soldados.', 'pt'),
+        ("Este é um 1º teste", 'Este é um primeiro teste', 'pt'),
+        ("Isso custará $20 senhor.", 'Isso custará vinte dólares senhor.', 'pt'),
+        ("Isso custará 20€ senhor.", 'Isso custará vinte euros senhor.', 'pt'),
+        ("Isso custará 20,15€ senhor.", 'Isso custará vinte euros e quinze cêntimos senhor.', 'pt'), # "cêntimos" should be "centavos" num2words issue
+        # Polish
+        ("W 12,5 sekundy.", 'W dwanaście przecinek pięć sekundy.', 'pl'),
+        ("Było 50 żołnierzy.", 'Było pięćdziesiąt żołnierzy.', 'pl'),
+        ("To będzie kosztować 20€ panie.", 'To będzie kosztować dwadzieścia euro panie.', 'pl'),
+        ("To będzie kosztować 20,15€ panie.", 'To będzie kosztować dwadzieścia euro, piętnaście centów panie.', 'pl'),
+        # Arabic
+        ("في الـ 12,5 ثانية.", 'في الـ اثنا عشر  , خمسون ثانية.', 'ar'),
+        ("كان هناك 50 جنديًا.", 'كان هناك خمسون جنديًا.', 'ar'),
+        # ("ستكون النتيجة $20 يا سيد.", 'ستكون النتيجة عشرون دولار يا سيد.', 'ar'), # $ and € are mising from num2words
+        # ("ستكون النتيجة 20€ يا سيد.", 'ستكون النتيجة عشرون يورو يا سيد.', 'ar'),
+        # Czech
+        ("Za 12,5 vteřiny.", 'Za dvanáct celá pět vteřiny.', 'cs'),
+        ("Bylo tam 50 vojáků.", 'Bylo tam padesát vojáků.', 'cs'),
+        ("To bude stát 20€ pane.", 'To bude stát dvacet euro pane.', 'cs'),
+        ("To bude 20.15€ pane.", 'To bude dvacet euro, patnáct centů pane.', 'cs'),
+        # Russian
+        ("Через 12.5 секунды.", 'Через двенадцать запятая пять секунды.', 'ru'),
+        ("Там было 50 солдат.", 'Там было пятьдесят солдат.', 'ru'),
+        ("Это будет 20.15€ сэр.", 'Это будет двадцать евро, пятнадцать центов сэр.', 'ru'),
+        ("Это будет стоить 20€ господин.", 'Это будет стоить двадцать евро господин.', 'ru'),
+        # Dutch
+        ("In 12,5 seconden.", 'In twaalf komma vijf seconden.', 'nl'),
+        ("Er waren 50 soldaten.", 'Er waren vijftig soldaten.', 'nl'),
+        ("Dat wordt dan $20 meneer.", 'Dat wordt dan twintig dollar meneer.', 'nl'),
+        ("Dat wordt dan 20€ meneer.", 'Dat wordt dan twintig euro meneer.', 'nl'),
+        # Chinese (Simplified)
+        ("在12.5秒内", '在十二点五秒内', 'zh'),
+        ("有50名士兵", '有五十名士兵', 'zh'),
+        # ("那将是$20先生", '那将是二十美元先生', 'zh'), currency doesn't work
+        # ("那将是20€先生", '那将是二十欧元先生', 'zh'),
+        # Turkish
+        # ("12,5 saniye içinde.", 'On iki virgül beş saniye içinde.', 'tr'), # decimal doesn't work for TR
+        ("50 asker vardı.", 'elli asker vardı.', 'tr'),
+        ("Bu 1. test", 'Bu birinci test', 'tr'),
+        # ("Bu 100.000,5.", 'Bu yüz bin virgül beş.', 'tr'),
+        # Hungarian
+        ("12,5 másodperc alatt.", 'tizenkettő egész öt tized másodperc alatt.', 'hu'),
+        ("50 katona volt.", 'ötven katona volt.', 'hu'),
+        ("Ez az 1. teszt", 'Ez az első teszt', 'hu'),
+        # Korean
+        ("12.5 초 안에.", '십이 점 다섯 초 안에.', 'ko'),
+        ("50 명의 병사가 있었다.", '오십 명의 병사가 있었다.', 'ko'),
+        ("이것은 1 번째 테스트입니다", '이것은 첫 번째 테스트입니다', 'ko'),
+    ]
+    for a, b, lang in test_cases:
+        out = expand_numbers_multilingual(a, lang=lang)
+        assert out == b, f"'{out}' vs '{b}'"
+
+def test_abbreviations_multilingual():
+    test_cases = [
+        # English
+        ("Hello Mr. Smith.", 'Hello mister Smith.', 'en'),
+        ("Dr. Jones is here.", 'doctor Jones is here.', 'en'),
+        # Spanish
+        ("Hola Sr. Garcia.", 'Hola señor Garcia.', 'es'),
+        ("La Dra. Martinez es muy buena.", 'La doctora Martinez es muy buena.', 'es'),
+        # French
+        ("Bonjour Mr. Dupond.", 'Bonjour monsieur Dupond.', 'fr'),
+        ("Mme. Moreau est absente aujourd'hui.", 'madame Moreau est absente aujourd\'hui.', 'fr'),
+        # German
+        ("Frau Dr. Müller ist sehr klug.", 'Frau doktor Müller ist sehr klug.', 'de'),
+        # Portuguese
+        ("Olá Sr. Silva.", 'Olá senhor Silva.', 'pt'),
+        ("Dra. Costa, você está disponível?", 'doutora Costa, você está disponível?', 'pt'),
+        # Italian
+        ("Buongiorno, Sig. Rossi.", 'Buongiorno, signore Rossi.', 'it'),
+        #("Sig.ra Bianchi, posso aiutarti?", 'signora Bianchi, posso aiutarti?', 'it'), # Issue with matching that pattern
+        # Polish
+        ("Dzień dobry, P. Kowalski.", 'Dzień dobry, pani Kowalski.', 'pl'),
+        ("M. Nowak, czy mogę zadać pytanie?", 'pan Nowak, czy mogę zadać pytanie?', 'pl'),
+        # Czech
+        ("P. Novák", "pan Novák", 'cs'),
+        ("Dr. Vojtěch", "doktor Vojtěch", 'cs'),
+        # Dutch
+        ("Dhr. Jansen", "de heer Jansen", 'nl'),
+        ("Mevr. de Vries", "mevrouw de Vries", 'nl'),
+        # Russian
+        ("Здравствуйте Г-н Иванов.", "Здравствуйте господин Иванов.", 'ru'),
+        ("Д-р Смирнов здесь, чтобы увидеть вас.", "доктор Смирнов здесь, чтобы увидеть вас.", 'ru'),
+        # Turkish
+        ("Merhaba B. Yılmaz.", "Merhaba bay Yılmaz.", 'tr'),
+        ("Dr. Ayşe burada.", "doktor Ayşe burada.", 'tr'),
+        # Hungarian
+        ("Dr. Szabó itt van.", "doktor Szabó itt van.", 'hu'),
+    ]
+
+    for a, b, lang in test_cases:
+        out = expand_abbreviations_multilingual(a, lang=lang)
+        assert out == b, f"'{out}' vs '{b}'"
+
+def test_symbols_multilingual():
+    test_cases = [
+        ("I have 14% battery", "I have 14 percent battery", "en"),
+        ("Te veo @ la fiesta", "Te veo arroba la fiesta", "es"),
+        ("J'ai 14° de fièvre", "J'ai 14 degrés de fièvre", "fr"),
+        ("Die Rechnung beträgt £ 20", "Die Rechnung beträgt pfund 20", "de"),
+        ("O meu email é ana&joao@gmail.com", "O meu email é ana e joao arroba gmail.com", "pt"),
+        ("linguaggio di programmazione C#", "linguaggio di programmazione C cancelletto", "it"),
+        ("Moja temperatura to 36.6°", "Moja temperatura to 36.6 stopnie", "pl"),
+        ("Mám 14% baterie", "Mám 14 procento baterie", "cs"),
+        ("Těším se na tebe @ party", "Těším se na tebe na party", "cs"),
+        ("У меня 14% заряда", "У меня 14 процентов заряда", "ru"),
+        ("Я буду @ дома", "Я буду собака дома", "ru"),
+        ("Ik heb 14% batterij", "Ik heb 14 procent batterij", "nl"),
+        ("Ik zie je @ het feest", "Ik zie je bij het feest", "nl"),
+        ("لدي 14% في البطارية", "لدي 14 في المئة في البطارية", "ar"),
+        ("我的电量为 14%", "我的电量为 14 百分之", "zh"),
+        ("Pilim %14 dolu.", "Pilim yüzde 14 dolu.", "tr"),
+        ("Az akkumulátorom töltöttsége 14%", "Az akkumulátorom töltöttsége 14 százalék", "hu"),
+        ("배터리 잔량이 14%입니다.", "배터리 잔량이 14 퍼센트입니다.", "ko")
+    ]
+
+    for a, b, lang in test_cases:
+        out = expand_symbols_multilingual(a, lang=lang)
+        assert out == b, f"'{out}' vs '{b}'"
+
+if __name__ == "__main__":
+    test_expand_numbers_multilingual()
+    test_abbreviations_multilingual()
+    test_symbols_multilingual()