Replace all uses of eval() on environment variables and command-line
arguments with safe string comparison. eval() allows arbitrary code
execution when given untrusted input, making it a security risk.
The fix uses .lower() in ("true", "1", "yes") which produces
identical behavior for all valid boolean inputs while preventing
code injection. This pattern is already used in config.py.
Affected files (10 call sites):
- GPT_SoVITS/inference_webui.py (is_share, is_half)
- GPT_SoVITS/inference_webui_fast.py (is_share, is_half)
- GPT_SoVITS/prepare_datasets/1-get-text.py (is_half)
- GPT_SoVITS/prepare_datasets/2-get-hubert-wav32k.py (is_half)
- GPT_SoVITS/prepare_datasets/2-get-sv.py (is_half)
- GPT_SoVITS/prepare_datasets/3-get-semantic.py (is_half)
- tools/uvr5/webui.py (is_half, is_share)
- tools/subfix_webui.py (is_share)
Make Gradio Great Again
附带vs2017下载链接
增加了各种数据集检查,若缺失会弹出warning
修复了warning乱弹的bug
修复了参考音频混合只能上传一条的bug
修复了下载G2PW Model出现import错误的bug
修复了Windows训练无N卡在预处理阶段的报错
