feat(xtts): support hindi in tokenizer (#64)

Added proper tokenizer support for Hindi Language which would prevent crash while fine tuning Hindi language.

Co-authored-by: Akshat Bhardwaj <157223825+akshatrocky@users.noreply.github.com>

TTS/tts/layers/xtts/tokenizer.py

@@ -233,6 +233,12 @@ _abbreviations = {
             # Korean doesn't typically use abbreviations in the same way as Latin-based scripts.
         ]
     ],
+    "hi": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            # Hindi doesn't typically use abbreviations in the same way as Latin-based scripts.
+        ]
+    ],
 }
 
 
@@ -429,6 +435,18 @@ _symbols_multilingual = {
             ("°", " 도 "),
         ]
     ],
+    "hi": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " और "),
+            ("@", " ऐट दी रेट "),
+            ("%", " प्रतिशत "),
+            ("#", " हैश "),
+            ("$", " डॉलर "),
+            ("£", " पाउंड "),
+            ("°", " डिग्री "),
+        ]
+    ],
 }
 
 
@@ -454,6 +472,7 @@ _ordinal_re = {
     "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)"),
+    "hi": re.compile(r"([0-9]+)(st|nd|rd|th)"),  # To check
 }
 _number_re = re.compile(r"[0-9]+")
 _currency_re = {
@@ -505,6 +524,7 @@ def _expand_currency(m, lang="en", currency="USD"):
         "tr": ", ",
         "hu": ", ",
         "ko": ", ",
+        "hi": ", ",
     }
 
     if amount.is_integer():
@@ -644,7 +664,7 @@ class VoiceBpeTokenizer:
             )
 
     def preprocess_text(self, txt, lang):
-        if lang in {"ar", "cs", "de", "en", "es", "fr", "hu", "it", "nl", "pl", "pt", "ru", "tr", "zh", "ko"}:
+        if lang in {"ar", "cs", "de", "en", "es", "fr", "hi", "hu", "it", "nl", "pl", "pt", "ru", "tr", "zh", "ko"}:
             txt = multilingual_cleaners(txt, lang)
             if lang == "zh":
                 txt = chinese_transliterate(txt)
@@ -652,9 +672,6 @@ class VoiceBpeTokenizer:
                 txt = korean_transliterate(txt)
         elif lang == "ja":
             txt = japanese_cleaners(txt, self.katsu)
-        elif lang == "hi":
-            # @manmay will implement this
-            txt = basic_cleaners(txt)
         else:
             raise NotImplementedError(f"Language '{lang}' is not supported.")
         return txt
@@ -777,6 +794,9 @@ def test_expand_numbers_multilingual():
         ("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"),
+        # Hindi
+        ("12.5 सेकंड में।", "साढ़े बारह सेकंड में।", "hi"),
+        ("50 सैनिक थे।", "पचास सैनिक थे।", "hi"),
     ]
     for a, b, lang in test_cases:
         out = expand_numbers_multilingual(a, lang=lang)
@@ -846,6 +866,7 @@ def test_symbols_multilingual():
         ("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"),
+        ("मेरे पास 14% बैटरी है।", "मेरे पास चौदह प्रतिशत बैटरी है।", "hi"),
     ]
 
     for a, b, lang in test_cases: