added japanese preprocessor for tokenizer

tortoise/utils/tokenizer.py

@@ -172,9 +172,12 @@ DEFAULT_VOCAB_FILE = os.path.join(os.path.dirname(os.path.realpath(__file__)), '
 
 class VoiceBpeTokenizer:
     def __init__(self, vocab_file=DEFAULT_VOCAB_FILE, preprocess=None):
-        if preprocess is None:
         with open(vocab_file, 'r', encoding='utf-8') as f:
           vocab = json.load(f)
+
+        self.language = vocab['model']['language'] if 'language' in vocab['model'] else None
+
+        if preprocess is None:
           self.preprocess = 'pre_tokenizer' in vocab and vocab['pre_tokenizer']
         else:
             self.preprocess = preprocess
@@ -182,6 +185,19 @@ class VoiceBpeTokenizer:
             self.tokenizer = Tokenizer.from_file(vocab_file)
 
     def preprocess_text(self, txt):
+        if self.language == 'ja':
+          import pykakasi
+
+          kks = pykakasi.kakasi()
+          results = kks.convert(txt)
+          words = []
+
+          for result in results:
+            words.append(result['kana'])
+
+          txt = " ".join(words)
+          txt = basic_cleaners(txt)
+        else:
           txt = english_cleaners(txt)
         return txt