bos char addded

utils/text/__init__.py

@@ -43,7 +43,7 @@ def phoneme_to_sequence(text, cleaner_names, language):
     '''
     TODO: This ignores punctuations
     '''
-    sequence = []
+    sequence = [_phonemes_to_id['^']]
     clean_text = _clean_text(text, cleaner_names)
     phonemes = text2phone(clean_text, language)
 #     print(phonemes.replace('|', ''))
@@ -81,7 +81,7 @@ def text_to_sequence(text, cleaner_names):
         List of integers corresponding to the symbols in the text
     '''
     sequence = []
-
+    sequence = [_phonemes_to_id['^']]
     # Check for curly braces and treat their contents as ARPAbet:
     while len(text):
         m = _curly_re.match(text)

utils/text/symbols.py

@@ -9,6 +9,7 @@ from utils.text import cmudict
 
 _pad = '_'
 _eos = '~'
+_bos = '^'
 _characters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!\'(),-.:;? '
 _punctuations = '!\'(),-.:;? '
 _phoneme_punctuations = '.!;:,?'
@@ -24,8 +25,8 @@ _phonemes = sorted(list(set(_phonemes)))
 _arpabet = ['@' + s for s in _phonemes]
 
 # Export all symbols:
-symbols = [_pad, _eos] + list(_characters) + _arpabet
-phonemes = [_pad, _eos] + list(_phonemes) + list(_punctuations)
+symbols = [_pad, _eos, _bos] + list(_characters) + _arpabet
+phonemes = [_pad, _eos, _bos] + list(_phonemes) + list(_punctuations)
 
 if __name__ == '__main__':
     print(" > TTS symbols ")