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

Update tokenizer.py #60

Closed
wants to merge 4 commits into from
Closed

Update tokenizer.py #60

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
283f3a1
Update tokenizer.py
Jul 18, 2024
0aa827a
Update tokenizer.py
Jul 18, 2024
6176cf0
Update README.md
Jul 18, 2024
0195454
Update README.md
Jul 18, 2024
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
28 changes: 26 additions & 2 deletions TTS/tts/layers/xtts/tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,6 +233,12 @@ def split_sentence(text, lang, text_split_length=250):
# Korean doesn't typically use abbreviations in the same way as Latin-based scripts.
]
],
"hi": [
(re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
for x in [
# Hindi doesn't typically use abbreviations in the same way as Latin-based scripts.
]
],
}


Expand Down Expand Up @@ -429,6 +435,18 @@ def expand_abbreviations_multilingual(text, lang="en"):
("°", " 도 "),
]
],
"hi": [
(re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
for x in [
("&", " और "),
("@", " ऐट दी रेट "),
("%", " प्रतिशत "),
("#", " हैश "),
("$", " डॉलर "),
("£", " पाउंड "),
("°", " डिग्री "),
]
],
}


Expand All @@ -454,6 +472,7 @@ def expand_symbols_multilingual(text, lang="en"):
"tr": re.compile(r"([0-9]+)(\.|inci|nci|uncu|üncü|\.)"),
"hu": re.compile(r"([0-9]+)(\.|adik|edik|odik|edik|ödik|ödike|ik)"),
"ko": re.compile(r"([0-9]+)(번째|번|차|째)"),
"hi": re.compile(r"([0-9]+)(st|nd|rd|th)") # To check
}
_number_re = re.compile(r"[0-9]+")
_currency_re = {
Expand Down Expand Up @@ -505,6 +524,7 @@ def _expand_currency(m, lang="en", currency="USD"):
"tr": ", ",
"hu": ", ",
"ko": ", ",
"hi": ", ",
}

if amount.is_integer():
Expand Down Expand Up @@ -644,7 +664,7 @@ def check_input_length(self, txt, lang):
)

def preprocess_text(self, txt, lang):
if lang in {"ar", "cs", "de", "en", "es", "fr", "hu", "it", "nl", "pl", "pt", "ru", "tr", "zh", "ko"}:
if lang in {"ar", "cs", "de", "en", "es", "fr", "hu", "it", "nl", "pl", "pt", "ru", "tr", "zh", "ko", "hi"}:
txt = multilingual_cleaners(txt, lang)
if lang == "zh":
txt = chinese_transliterate(txt)
Expand All @@ -653,7 +673,7 @@ def preprocess_text(self, txt, lang):
elif lang == "ja":
txt = japanese_cleaners(txt, self.katsu)
elif lang == "hi":
# @manmay will implement this
# Currently Hindi_Cleaner isn't implemented, use basic_cleaners instead
txt = basic_cleaners(txt)
else:
raise NotImplementedError(f"Language '{lang}' is not supported.")
Expand Down Expand Up @@ -777,6 +797,9 @@ def test_expand_numbers_multilingual():
("12.5 초 안에.", "십이 점 다섯 초 안에.", "ko"),
("50 명의 병사가 있었다.", "오십 명의 병사가 있었다.", "ko"),
("이것은 1 번째 테스트입니다", "이것은 첫 번째 테스트입니다", "ko"),
# Hindi
("12.5 सेकंड में।", "साढ़े बारह सेकंड में।", "hi"),
("50 सैनिक थे।", "पचास सैनिक थे।", "hi"),
]
for a, b, lang in test_cases:
out = expand_numbers_multilingual(a, lang=lang)
Expand Down Expand Up @@ -846,6 +869,7 @@ def test_symbols_multilingual():
("Pilim %14 dolu.", "Pilim yüzde 14 dolu.", "tr"),
("Az akkumulátorom töltöttsége 14%", "Az akkumulátorom töltöttsége 14 százalék", "hu"),
("배터리 잔량이 14%입니다.", "배터리 잔량이 14 퍼센트입니다.", "ko"),
("मेरे पास 14% बैटरी है।", "मेरे पास चौदह प्रतिशत बैटरी है।", "hi"),
]

for a, b, lang in test_cases:
Expand Down
Loading