blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2026-09-04 15:00:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: blackteay:fe25a61f1a92bb9326bbe31912c7da8576e6cabf
Branches Tags
blackteay:main
blackteay:revert-1660-main
blackteay:fast_inference_
blackteay:20250606v2pro
blackteay:20250422v4
blackteay:20250228v3
blackteay:20240821v2
...
compare: blackteay:971cb454f1fb15619af22fa4a0e991b3ae83bab6
Branches Tags
blackteay:main
blackteay:revert-1660-main
blackteay:fast_inference_
blackteay:20250606v2pro
blackteay:20250422v4
blackteay:20250228v3
blackteay:20240821v2

3 Commits
fe25a61f1a ... 971cb454f1

Author SHA1 Message Date
00080000
971cb454f1
Merge c70f091182e76676209295ce51452f5d84df54f1 into 48b1a0169a28582a8984402f82cf438d3bfa6aca 2026-08-21 17:38:58 -05:00
zhifu gao
48b1a0169a
Fix Fun-ASR-Nano Transformers requirement (#2824) 
Signed-off-by: LauraGPT <LauraGPT@users.noreply.github.com>
Co-authored-by: LauraGPT <LauraGPT@users.noreply.github.com>
 2026-08-18 17:16:25 +08:00
0.0
c70f091182 fix: correct type annotation and file encoding for cross-platform support 2026-07-21 11:20:23 +08:00
4 changed files with 4 additions and 4 deletions
Show Stats Expand all files Collapse all files

2
GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py
View File

@ -31,7 +31,7 @@ def get_first(text: str) -> str:
return text
def merge_short_text_in_array(texts: str, threshold: int) -> list:
def merge_short_text_in_array(texts: List[str], threshold: int) -> list:
if (len(texts)) < 2:
return texts
result = []

2
GPT_SoVITS/text/chinese.py
View File

@ -13,7 +13,7 @@ normalizer = lambda x: cn2an.transform(x, "an2cn")
current_file_path = os.path.dirname(__file__)
pinyin_to_symbol_map = {
line.split("\t")[0]: line.strip().split("\t")[1]
for line in open(os.path.join(current_file_path, "opencpop-strict.txt")).readlines()
for line in open(os.path.join(current_file_path, "opencpop-strict.txt"), encoding="utf-8").readlines()
}
import jieba_fast

2
GPT_SoVITS/text/chinese2.py
View File

@ -14,7 +14,7 @@ normalizer = lambda x: cn2an.transform(x, "an2cn")
current_file_path = os.path.dirname(__file__)
pinyin_to_symbol_map = {
line.split("\t")[0]: line.strip().split("\t")[1]
for line in open(os.path.join(current_file_path, "opencpop-strict.txt")).readlines()
for line in open(os.path.join(current_file_path, "opencpop-strict.txt"), encoding="utf-8").readlines()
}
import jieba_fast

2
requirements.txt
View File

@ -18,7 +18,7 @@ g2p_en
torchaudio
modelscope
sentencepiece
transformers>=4.43,<=4.50
transformers>=4.51,<5
peft<0.18.0
chardet
PyYAML