920 Commits

Author SHA1 Message Date
RVC-Boss
fbdab94e17
https://github.com/RVC-Boss/GPT-SoVITS/issues/2308
https://github.com/RVC-Boss/GPT-SoVITS/issues/2308
2025-04-22 10:17:05 +08:00
ChasonJiang
a19f49604f
修复v3传参 (#2309) 2025-04-22 10:10:44 +08:00
RVC-Boss
590c83d766
修复v3推理传参问题 2025-04-22 00:20:33 +08:00
RVC-Boss
7405427a0a
修复v3推理传参问题 2025-04-22 00:16:07 +08:00
ChasonJiang
e0f2818df7
为并行推理版本适配v4 (#2307)
* 适配v4版本

* 适配v4版本

* modified:   GPT_SoVITS/inference_webui_fast.py

* 合并main分支

* fallback config

* modified:   GPT_SoVITS/TTS_infer_pack/TTS.py

* fix bug

* modified:   GPT_SoVITS/TTS_infer_pack/TTS.py

* modified:   GPT_SoVITS/inference_webui_fast.py
2025-04-21 23:20:20 +08:00
RVC-Boss
bc2fe5ec86
适配v4并行推理(还没写完) 2025-04-21 22:45:09 +08:00
RVC-Boss
839ff9ce5b
适配v4并行推理(还没写完) 2025-04-21 22:43:46 +08:00
RVC-Boss
8b394a15bc
support v4 parallel inference
支持v4并行推理
2025-04-21 21:31:12 +08:00
RVC-Boss
ec7ec370ef
训完模自动刷新模型列表
Automatically refresh the model list after training the model.
2025-04-21 21:30:36 +08:00
RVC-Boss
9d481da610
support gpt sovits v4
support gpt sovits v4
2025-04-20 15:14:19 +08:00
RVC-Boss
50e9ba0218
support gpt-sovits v4
support gpt-sovits v4
2025-04-20 14:53:42 +08:00
RVC-Boss
c6cb6b45f3
support gpt-sovits v4
support gpt-sovits v4
2025-04-20 14:53:07 +08:00
RVC-Boss
e0c452f007
support gpt-sovits v4
support gpt-sovits v4
2025-04-20 14:50:28 +08:00
XXXXRT666
b43ae64a1e
Fix Non-functional Project: Add Multi-source Pretrained Model and UVR5 Download, Enable , Colab Compatibility, and FastAPI Optimization (#2300)
* Replace the outdated link and pin dependencies

* Update Colab

* Add Docs

* .

* Update Install.sh, Support multi download source

* .

* modified path

* Add source

* Update URL

* fix bugs

* fix bug

* fix bugs

* Fix colab

* update colab

* Update Docs

* update links
2025-04-20 00:56:42 +08:00
XXXXRT666
c0b46314ca
Support Python 3.11, Clean Docs, and Update Setup (#2290)
* Update Req, Shell Scripts and Docs

* Use half-width punctuation marks

* Update install.sh
2025-04-15 15:42:23 +08:00
XXXXRT666
53cac93589
Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)
* ruff check --fix

* ruff format --line-length 120 --target-version py39

* Change the link for G2PW Model

* update pytorch version and colab
2025-04-07 16:42:47 +08:00
RVC-Boss
9da7e17efe
Add files via upload 2025-04-01 18:44:35 +08:00
RVC-Boss
b0de354c63
Update Changelog_CN.md 2025-04-01 17:21:48 +08:00
RVC-Boss
41090e5a7c
Update g2pw url 2025-04-01 17:15:52 +08:00
RVC-Boss
605b380114
修复模型加载异步逻辑
修复模型加载异步逻辑
2025-04-01 16:50:54 +08:00
RVC-Boss
9f8d455130
支持v3并行推理
support v3 models batch inference
2025-04-01 16:31:48 +08:00
RVC-Boss
7abae557fb
删除加载v3sovits模型缺少enc_q告警
删除加载v3sovits模型缺少enc_q告警
2025-04-01 16:31:15 +08:00
RVC-Boss
6a60e5edb1
v3解锁并行推理;修复模型加载异步逻辑
v3解锁并行推理;修复模型加载异步逻辑
2025-04-01 16:29:52 +08:00
RVC-Boss
28bdff356f
fix https://github.com/RVC-Boss/GPT-SoVITS/issues/2250
fix https://github.com/RVC-Boss/GPT-SoVITS/issues/2250
2025-04-01 10:34:02 +08:00
ChasonJiang
03b662a769
为sovits_v3 适配并行推理 (#2241)
* 为sovits_v3 适配并行推理

* 清理无用代码
2025-03-31 11:56:05 +08:00
XXXXRT666
6c468583c5
Fix dependency-related issues via requirements update (#2236)
* Update requirements.txt

* Create constraints.txt

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* pyopenjtalk and onnx fix

* Update requirements.txt

* Update requirements.txt

* Update install.sh

* update shell install.sh

* update docs

* Update Install.sh

* fix bugs

* Update .gitignore

* Update .gitignore

* Update install.sh

* Update install.sh

* Update extra-req.txt

* Update requirements.txt
2025-03-31 11:27:12 +08:00
RVC-Boss
ee4a466f79
Update patched_mha_with_cache.py 2025-03-26 17:39:19 +08:00
C3EZ
b65ea9181e
更新对amd显卡的支持 (#2076)
* Added the instruction for AMD GPU in English

* Added the instruction for AMD GPU in Chinese

* Update install.sh, now it will check wether user are using cuda or rocm

* 恢复原来的readme,已经更新了install.sh

* 恢复中文readme

* 将n卡的判断条件由nvcc改成nvidia-smi
2025-03-26 16:04:13 +08:00
RVC-Boss
c0ce55a132
Update my_utils.py 2025-03-26 15:32:43 +08:00
RVC-Boss
13573a1b06
fix torch.load 2025-03-26 15:22:01 +08:00
lishq
fef65d40fe
fix: prevent concurrent access to BERT model with thread lock (#2165)
Added thread lock to protect get_phones_and_bert method from potential race conditions during concurrent access. This addresses issue #1844 where multiple threads accessing the BERT model simultaneously could cause data inconsistency or crashes.

Co-authored-by: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com>
2025-03-26 15:03:36 +08:00
zzz
b0e465eb72
feat: 添加导出 v3 的 script (#2208)
* feat: 添加导出 v3 的 script

* Fix: 由于 export_torch_script_v3 的改动,v2 现在需要传入 top_k
2025-03-26 14:50:55 +08:00
RVC-Boss
f1332ff53a
Update README.md 2025-03-26 14:49:48 +08:00
RVC-Boss
b88bd391fc
Update README.md 2025-03-26 14:46:29 +08:00
RVC-Boss
4635cb4293
Update README.md 2025-03-26 14:46:21 +08:00
RVC-Boss
86e6dea694
Update README.md 2025-03-26 14:46:14 +08:00
RVC-Boss
d7c24e9ac9
Update README.md 2025-03-26 14:46:04 +08:00
RVC-Boss
6c1c1bb72a
Update README.md huggingface url
Update README.md huggingface url
2025-03-26 14:45:06 +08:00
KamioRinn
265586990c
更新G2PWModel下载链接 (#2219)
* update G2PWModel download url

* update G2PWModel download url
2025-03-26 14:35:52 +08:00
ChasonJiang
7394dc7b0c
为api_v2和inference_webui_fast适配V3版本 (#2188)
* modified:   GPT_SoVITS/TTS_infer_pack/TTS.py
	modified:   GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py
	modified:   GPT_SoVITS/inference_webui_fast.py

* 适配V3版本

* api_v2.py和inference_webui_fast.py的v3适配

* 修改了个远古bug,增加了更友好的提示信息

* 优化webui

* 修改为正确的path

* 修复v3 lora模型的载入问题

* 修复读取tts_infer.yaml文件时遇到的编码不匹配的问题
2025-03-26 14:34:51 +08:00
ChasonJiang
165882d64f
修复多余的注释导致的bug (#2158) 2025-03-05 18:22:01 +08:00
RVC-Boss
271db6a4de
fix torch.inference_mode()RuntimeError:Inplace update to inference tensor outside InferenceMode is not allowed.
fix torch.inference_mode()RuntimeError:Inplace update to inference tensor outside InferenceMode is not allowed.
2025-03-05 18:07:47 +08:00
ChasonJiang
053a356ffe
修复gpt的padding mask的问题 (#2153)
* 修复gpt的padding mask的问题

* rollback tts_config
2025-03-05 17:14:43 +08:00
KamioRinn
fe2f04bdb8
API for V3 (#2154) 2025-03-05 17:13:46 +08:00
ChasonJiang
6dd2f72090
更改gpt并行推理时的mask策略为padding left (#2144)
* 更改gpt并行推理时的mask策略为padding left,使batch_infer更接近于naive_infer
减少冗余操作并使用torch_sdpa,以提升推理速度

* rollback tts_infer.yaml
2025-03-04 16:45:37 +08:00
KamioRinn
959a2ddbeb
Matching fast_langdetect update (#2140) 2025-03-04 14:10:58 +08:00
Fridemn
bb8a8efeca
fix: 修复 Linux 一键安装脚本执行失败问题 (#2142)
安装 pyopenjtalk 库时不仅要保证 gcc 版本不高于 14,同时在执行 pip install -r requirements.txt 前需要保证环境变量中更新刚刚安装的 gcc/g++/cmake。
因此在安装三者后补充了设置环境变量,并且用 hash -r 确保生效
2025-03-04 14:10:37 +08:00
RVC-Boss
df33574a26
修复超分后音量超过1写错了的bug
修复超分后音量超过1写错了的bug
2025-03-01 19:17:03 +08:00
Fridemn
4fd57b0ea7
修复 Linux 无法编译 pyopenjtalk (#2127) 20250228v3 2025-02-28 22:21:34 +08:00
RVC-Boss
118c2bed68
Update Changelog_CN.md 2025-02-28 16:53:33 +08:00