Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix Punctuation

This commit is contained in:
Eren Gölge 2021-11-19 10:39:21 +01:00
parent ff7c385838
commit d8bdeb8b8f
3 changed files with 32 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
TTS/tts/utils/text/characters.py
View File

@ -101,7 +101,7 @@ class BaseCharacters:
is_unique (bool): is_unique (bool):
Remove duplicates from the provided characters. Defaults to True. Remove duplicates from the provided characters. Defaults to True.
el el
is_sorted (bool): is_sorted (bool):
Sort the characters in alphabetical order. Only applies to `self.characters`. Defaults to True. Sort the characters in alphabetical order. Only applies to `self.characters`. Defaults to True.
""" """
@ -214,7 +214,7 @@ el
def id_to_char(self, idx: int) -> str: def id_to_char(self, idx: int) -> str:
return self._id_to_char[idx] return self._id_to_char[idx]
def print_log(self, level:int=0): def print_log(self, level: int = 0):
""" """
Prints the vocabulary in a nice format. Prints the vocabulary in a nice format.
""" """

7
TTS/tts/utils/text/punctuation.py
View File

@ -91,10 +91,13 @@ class Punctuation:
puncs.append(_PUNC_IDX(match.group(), position)) puncs.append(_PUNC_IDX(match.group(), position))
# convert str text to a List[str], each item is separated by a punctuation # convert str text to a List[str], each item is separated by a punctuation
splitted_text = [] splitted_text = []
for punc in puncs: for idx, punc in enumerate(puncs):
split = text.split(punc.punc) split = text.split(punc.punc)
prefix, suffix = split[0], punc.punc.join(split[1:]) prefix, suffix = split[0], punc.punc.join(split[1:])
splitted_text.append(prefix) splitted_text.append(prefix)
# if the text does not end with a punctuation, add it to the last item
if idx == len(puncs) - 1 and len(suffix) > 0:
splitted_text.append(suffix)
text = suffix text = suffix
return splitted_text, puncs return splitted_text, puncs
@ -126,7 +129,7 @@ class Punctuation:
current = puncs[0] current = puncs[0]
if current.position == PuncPosition.BEGIN: if current.position == PuncPosition.BEGIN:
return cls._restore([current.mark + text[0]] + text[1:], puncs[1:], num) return cls._restore([current.punc + text[0]] + text[1:], puncs[1:], num)
if current.position == PuncPosition.END: if current.position == PuncPosition.END:
return [text[0] + current.punc] + cls._restore(text[1:], puncs[1:], num + 1) return [text[0] + current.punc] + cls._restore(text[1:], puncs[1:], num + 1)

2
TTS/tts/utils/text/tokenizer.py
View File

@ -1,8 +1,8 @@
from typing import Callable, Dict, List, Union from typing import Callable, Dict, List, Union
from TTS.tts.utils.text import cleaners from TTS.tts.utils.text import cleaners
from TTS.tts.utils.text.phonemizers import DEF_LANG_TO_PHONEMIZER, get_phonemizer_by_name
from TTS.tts.utils.text.characters import Graphemes, IPAPhonemes from TTS.tts.utils.text.characters import Graphemes, IPAPhonemes
from TTS.tts.utils.text.phonemizers import DEF_LANG_TO_PHONEMIZER, get_phonemizer_by_name
class TTSTokenizer: class TTSTokenizer: