Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

xtts/tokenizer: merge duplicate implementations of preprocess_text #3170

Merged
merged 1 commit into from
Nov 9, 2023
Merged

xtts/tokenizer: merge duplicate implementations of preprocess_text #3170

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 5 additions & 20 deletions TTS/tts/layers/xtts/tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -568,14 +568,16 @@ def check_input_length(self, txt, lang):
print(f"[!] Warning: The text length exceeds the character limit of {limit} for language '{lang}', this might cause truncated audio.")

def preprocess_text(self, txt, lang):
if lang in ["en", "es", "fr", "de", "pt", "it", "pl", "ar", "cs", "ru", "nl", "tr", "zh-cn"]:
if lang in {"ar", "cs", "de", "en", "es", "fr", "hu", "it", "nl", "pl", "pt", "ru", "tr", "zh", "zh-cn"}:
txt = multilingual_cleaners(txt, lang)
if lang == "zh-cn":
if lang in {"zh", "zh-cn"}:
txt = chinese_transliterate(txt)
elif lang == "ja":
txt = japanese_cleaners(txt, self.katsu)
elif lang == "ko":
txt = korean_cleaners(txt)
else:
raise NotImplementedError()
raise NotImplementedError(f"Language '{lang}' is not supported.")
return txt

def encode(self, txt, lang):
Expand All @@ -594,23 +596,6 @@ def decode(self, seq):
txt = txt.replace("[UNK]", "")
return txt

def preprocess_text(self, txt, lang):
if lang in ["en", "es", "fr", "de", "pt", "it", "pl", "zh", "ar", "cs", "ru", "nl", "tr", "hu"]:
txt = multilingual_cleaners(txt, lang)
elif lang == "ja":
if self.katsu is None:
import cutlet

self.katsu = cutlet.Cutlet()
txt = japanese_cleaners(txt, self.katsu)
elif lang == "zh-cn" or lang == "zh":
txt = chinese_transliterate(txt)
elif lang == "ko":
txt = korean_cleaners(txt)
else:
raise NotImplementedError()
return txt

def __len__(self):
return self.tokenizer.get_vocab_size()

Expand Down