Merge 539ad38d310d452aa1a08e659d5eac22f843a01d into 2d09bbe63ab6e33656e7d44b76a96e0072ae994b

Update tts_infer.yaml
Update TTS.py
2026-07-25 12:05:13 +08:00 · 2025-07-17 08:30:14 +08:00 · 2025-07-16 15:44:04 +08:00 · 2025-07-16 15:43:26 +08:00 · 2025-07-16 15:42:36 +08:00 · 2025-07-02 15:35:45 +08:00
4 changed files with 2103 additions and 1 deletions
--- a/GPT_SoVITS/TTS_infer_pack/TTS.py
+++ b/GPT_SoVITS/TTS_infer_pack/TTS.py
@ -305,7 +305,7 @@ class TTS_Config:

        assert isinstance(configs, dict)
        version = configs.get("version", "v2").lower()
-        assert version in ["v1", "v2", "v3", "v4", "v2Pro", "v2ProPlus"]
+        assert version in ["v1", "v2", "v3", "v4", "v2pro", "v2proplus"]
        self.default_configs[version] = configs.get(version, self.default_configs[version])
        self.configs: dict = configs.get("custom", deepcopy(self.default_configs[version]))

--- a/GPT_SoVITS/configs/tts_infer.yaml
+++ b/GPT_SoVITS/configs/tts_infer.yaml
@ -1,3 +1,4 @@
+version: v2ProPlus
 custom:
  bert_base_path: GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
  cnhuhbert_base_path: GPT_SoVITS/pretrained_models/chinese-hubert-base
@ -22,6 +23,22 @@ v2:
  t2s_weights_path: GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s1bert25hz-5kh-longer-epoch=12-step=369668.ckpt
  version: v2
  vits_weights_path: GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2G2333k.pth
+v2Pro:
+  bert_base_path: GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
+  cnhuhbert_base_path: GPT_SoVITS/pretrained_models/chinese-hubert-base
+  device: cpu
+  is_half: false
+  t2s_weights_path: GPT_SoVITS/pretrained_models/s1v3.ckpt
+  version: v2Pro
+  vits_weights_path: GPT_SoVITS/pretrained_models/v2Pro/s2Gv2Pro.pth
+v2ProPlus:
+  bert_base_path: GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
+  cnhuhbert_base_path: GPT_SoVITS/pretrained_models/chinese-hubert-base
+  device: cpu
+  is_half: false
+  t2s_weights_path: GPT_SoVITS/pretrained_models/s1v3.ckpt
+  version: v2ProPlus
+  vits_weights_path: GPT_SoVITS/pretrained_models/v2Pro/s2Gv2ProPlus.pth
 v3:
  bert_base_path: GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
  cnhuhbert_base_path: GPT_SoVITS/pretrained_models/chinese-hubert-base
--- a/go-webui-simple-mode.bat
+++ b/go-webui-simple-mode.bat
@ -0,0 +1,2 @@
+runtime\python.exe -I webui_simple.py zh_CN
+pause
--- a/webui_simple.py
+++ b/webui_simple.py
Author	SHA1	Message	Date
Karasukaigan	b60ed0cc2b	Merge 539ad38d310d452aa1a08e659d5eac22f843a01d into 2d09bbe63ab6e33656e7d44b76a96e0072ae994b	2025-07-17 08:30:14 +08:00
RVC-Boss	2d09bbe63a	Update tts_infer.yaml	2025-07-16 15:44:04 +08:00
RVC-Boss	4d8ebf8523	Update TTS.py	2025-07-16 15:43:26 +08:00
jiangsier-xyz	e476b01f30	解决 TTS.py 无法识别真正支持版本 v2Pro、v2ProPlus 的问题 (#2490 ) 同时更新一版默认配置。 Co-authored-by: jiangsier-xyz <jiangsier131@gmail.com>	2025-07-16 15:42:36 +08:00
Karasukaigan	539ad38d31	Merge branch 'RVC-Boss:main' into feat/frontend-usability-enhancements	2025-07-02 15:35:45 +08:00
Karasukaigan	6df7921d56	Merge branch 'RVC-Boss:main' into feat/frontend-usability-enhancements	2025-06-20 00:30:43 +08:00
Karasukaigan	8d212a9255	Merge branch 'RVC-Boss:main' into feat/frontend-usability-enhancements	2025-06-06 19:43:11 +08:00
Karasukaigan	2fb92e74a2	更新WebUI简化版以支持V2Pro 更新了webui_simple.py以支持V2Pro系列模型。	2025-06-06 01:20:45 +08:00
Karasukaigan	be16f387f1	Merge branch 'RVC-Boss:main' into feat/frontend-usability-enhancements	2025-06-05 18:41:42 +08:00
Karasukaigan	7e6a607b9e	Merge branch 'RVC-Boss:main' into feat/frontend-usability-enhancements	2025-06-05 15:47:39 +08:00
Karasukaigan	ab5e8dc0ae	Merge branch 'RVC-Boss:main' into feat/frontend-usability-enhancements	2025-05-31 20:15:19 +08:00
Karasukaigan	b666becb19	撤回对于inference_webui的改动	2025-05-27 22:41:20 +08:00
Karasukaigan	47426d18e7	新增微调训练WebUI简化版用户不再需要多次切换不同的选项卡页面来完成一次微调训练。现在微调训练的所有流程都在同一个页面里，按照从上往下的顺序排好，并且隐藏了非常用的设置项。	2025-05-27 22:22:15 +08:00
Karasukaigan	b8de0ec0ac	Merge branch 'RVC-Boss:main' into feat/frontend-usability-enhancements	2025-05-27 22:11:36 +08:00
Karasukaigan	f20f17c2c0	修复通过Gradio API调用合成语音接口时出现参数类型错误的问题修复通过Gradio API调用合成语音接口`/get_tts_wav`时出现参数类型错误的问题。 ## 报错信息 TypeError: unsupported operand type(s) for /: 'int' and 'str' ## 错误原因 `inference_webui.py`的`get_tts_wav`里并未对传入`sample_steps`的类型进行判断。而由于Gradio在自动生成接口文档时会将`gr.Radio`传入的值判定为字符串，因此如果有用户参考WebUI下面”通过 API 使用“里的说明调用`/get_tts_wav`时，则会因为文档错误导致传参类型错误，从而导致最终的报错。 ## 修复方式通过在`get_tts_wav`开头部分添加对`sample_steps`格式的转换（统一转为int）来解决传参类型错误的问题。	2025-05-16 17:58:56 +08:00