tuna2134/sbv2-v2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Fix japanese.py (#151)

Browse Source 
* Fix japanese.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
OedoSoldier
2023-11-06 06:41:41 +08:00
committed by GitHub
parent 6d0d7774e8
commit 0dbe362c83
2 changed files with 9 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
text/japanese.py
View File

@@ -54,7 +54,9 @@ def text2kata(text: str) -> str:
res = []
for parts in parsed:
word, yomi = replace_punctuation(parts["string"]), parts["pron"].replace("’", "")
word, yomi = replace_punctuation(parts["string"]), parts["pron"].replace(
"’", ""
)
if yomi:
if re.match(_MARKS, yomi):
if len(word) > 1:
@@ -85,7 +87,9 @@ def text2sep_kata(text: str) -> (list, list):
res = []
sep = []
for parts in parsed:
word, yomi = replace_punctuation(parts["orig"]), parts["pron"].replace("’", "")
word, yomi = replace_punctuation(parts["string"]), parts["pron"].replace(
"’", ""
)
if yomi:
if re.match(_MARKS, yomi):
if len(word) > 1:
@@ -361,16 +365,7 @@ def align_tones(phones, tones):
return res
import pykakasi
kks = pykakasi.kakasi()
def g2p(norm_text):
result = kks.convert(norm_text)
norm_text = ""
for i in result:
norm_text += i["hira"]
sep_text, sep_kata, acc = text2sep_kata(norm_text)
sep_tokenized = [tokenizer.tokenize(i) for i in sep_text]
sep_phonemes = handle_long([kata2phoneme(i) for i in sep_kata])