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

Remove duplicate code from xtts.tokenizer

This commit is contained in:
Aarni Koskela 2023-09-27 00:54:19 +03:00
parent da8b6bbce1
commit 59f85a7122
1 changed files with 0 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
TTS/tts/layers/xtts/tokenizer.py
View File

@ -171,17 +171,6 @@ def multilingual_cleaners(text, lang):
return text return text
def english_cleaners(text):
"""Pipeline for English text, including number and abbreviation expansion."""
text = convert_to_ascii(text)
text = lowercase(text)
text = expand_numbers(text)
text = expand_abbreviations(text)
text = collapse_whitespace(text)
text = text.replace('"', "")
return text
def remove_extraneous_punctuation(word): def remove_extraneous_punctuation(word):
replacement_punctuation = {"{": "(", "}": ")", "[": "(", "]": ")", "`": "'", "—": "-", "—": "-", "`": "'", "ʼ": "'"} replacement_punctuation = {"{": "(", "}": ")", "[": "(", "]": ")", "`": "'", "—": "-", "—": "-", "`": "'", "ʼ": "'"}
replace = re.compile( replace = re.compile(
@ -195,32 +184,6 @@ def remove_extraneous_punctuation(word):
return word return word
def expand_numbers(text):
return normalize_numbers(text)
def lowercase(text):
return text.lower()
_whitespace_re = re.compile(r"\s+")
def collapse_whitespace(text):
return re.sub(_whitespace_re, " ", text)
def convert_to_ascii(text):
return unidecode(text)
def basic_cleaners(text):
"""Basic pipeline that lowercases and collapses whitespace without transliteration."""
text = lowercase(text)
text = collapse_whitespace(text)
return text
def arabic_cleaners(text): def arabic_cleaners(text):
text = lowercase(text) text = lowercase(text)
text = collapse_whitespace(text) text = collapse_whitespace(text)