blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2026-05-20 17:48:12 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,055 Commits 3 Branches 4 Tags
Commit Graph

40 Commits

Author SHA1 Message Date
baicai-1145
c94de2f2cb Enhance TTS audio processing with improved resampling and profiling metrics 
Refactor the audio preparation workflow to utilize torchaudio for resampling, replacing librosa for better performance. Introduce a caching mechanism for resampling transforms and update the PrepareRefSemanticBatchWorker to include detailed timing metrics for profiling. Additionally, implement a new CPU limiter for managing resource allocation during audio processing. These changes improve the efficiency and maintainability of the TTS system.
 2026-03-13 16:45:00 +08:00
baicai-1145
bc1f3f32de Enhance audio processing in TTS framework with resampling and profiling improvements 
Add resampling capabilities using torchaudio to prepare reference audio at 16kHz, replacing librosa for better performance. Introduce a caching mechanism for resampling transforms to optimize resource usage. Update batch processing methods to include timing metrics for profiling, enhancing the ability to monitor and improve performance in the TTS system. This update improves the maintainability and efficiency of audio preparation workflows.
 2026-03-13 02:03:25 +08:00
baicai-1145
17cb2e5acf Implement G2PW processing enhancements in TTS framework 
Add support for G2PW processing in the TTS system by introducing new methods and classes for handling G2PW segments. Update PrepareCoordinator to manage G2PW worker threads and integrate G2PW profiling into the existing framework. Enhance text preprocessing to identify segments requiring G2PW and streamline the resolution of these segments. This update improves the overall performance and maintainability of the TTS system by optimizing the handling of Chinese text processing.
 2026-03-12 23:04:39 +08:00
baicai-1145
5cf68a91d3 Add g2pw submodule and enhance TTS processing with AsyncStageGate 
Introduce a new submodule for g2pw and implement AsyncStageGate in PrepareCoordinator to manage concurrent task inflight limits. Update PrepareTextCpuWorker and PrepareRefSemanticBatchWorker to support asynchronous task submission and completion notifications. Enhance profiling capabilities in TTS to track g2pw processing times, improving overall performance and maintainability of the TTS system.
 2026-03-12 23:03:33 +08:00
baicai-1145
6a822b28c3 Enhance TTS API with improved request handling and asynchronous processing 
Refactor api_v2.py and api_v3.py to update sampling parameters and weight paths for better clarity and support for v3/v4 vocoders. Introduce new methods in PrepareCoordinator for handling empty text features and improve profiling capabilities. Additionally, update unified engine components to streamline audio processing and state management, enhancing overall performance and maintainability of the TTS system.
 2026-03-12 01:27:19 +08:00
baicai-1145
69ac7f9027 Integrate UnifiedTTSEngine into TTS API for improved audio processing and control. Refactor tts_handle and control endpoints to utilize the new engine, enhancing error handling and response management. Update set_refer_audio and set_gpt_weights endpoints to return payloads from the engine, streamlining audio configuration processes. 2026-03-10 06:59:28 +08:00
baicai-1145
827d6ea47c Refactor TTS and scheduler components to enhance text processing and batching capabilities. Introduce PrepareCoordinator for managing text feature preparation asynchronously, and update SchedulerDebugWorker to support new finalize task management. Implement batch processing in PrepareBertBatchWorker with improved admission control and profiling metrics. Add text CPU preprocessing utilities for better text segmentation and normalization. 2026-03-10 06:58:53 +08:00
baicai-1145
845b181360 Implement batch processing for BERT and reference semantic tasks in TTS. Introduce StageLimiter for managing concurrent processing and enhance the TTS class with new methods for handling audio and semantic extraction. Update profiling metrics for better performance tracking during inference. 2026-03-09 05:19:28 +08:00
baicai-1145
d245eb169c Refactor T2S scheduler and inference handling to improve attention mask management and memory tracking. Update T2SRunningRequest and T2SActiveBatch classes to include optional key padding masks. Introduce new benchmarking tools for API performance and memory usage analysis, enhancing overall system efficiency. 2026-03-09 01:42:04 +08:00
baicai-1145
dc37b0b9ef Add WebAPI documentation and implement TTS API with endpoints for text-to-speech inference, control commands, and model switching. Enhance TTS class with methods for extracting prompt semantics and reference audio specifications. Introduce a scheduler prototype for managing T2S requests. 2026-03-09 00:22:59 +08:00
baicai-1145
30a4557d8d Implement last inference statistics tracking in Text2SemanticDecoder and enhance TTS class with prompt semantic extraction. This includes methods for setting and retrieving inference stats, as well as improvements to audio processing and feature extraction in TTS. 2026-03-08 23:08:27 +08:00
ChasonJiang
abe984395c
对齐gpt topk默认采样参数 (#2696) 2025-12-19 16:05:36 +08:00
ChasonJiang
36b3231c6f
bug fix (#2689) 2025-12-15 14:23:06 +08:00
ChasonJiang
92ab59c553
更细粒度的流式推理模式 (#2671) 
* 更好的流式推理模式

* 清理无用代码

* modified:   GPT_SoVITS/AR/models/t2s_model.py
	modified:   GPT_SoVITS/TTS_infer_pack/TTS.py
	modified:   GPT_SoVITS/module/models.py

* modified:   GPT_SoVITS/TTS_infer_pack/TTS.py

* modified:   .gitignore
	modified:   GPT_SoVITS/AR/models/t2s_model.py
	modified:   GPT_SoVITS/TTS_infer_pack/TTS.py
	modified:   GPT_SoVITS/module/models.py

* modified:   GPT_SoVITS/AR/models/t2s_model.py
	modified:   GPT_SoVITS/TTS_infer_pack/TTS.py
	modified:   GPT_SoVITS/module/models.py
	modified:   api_v2.py

* modified:   GPT_SoVITS/TTS_infer_pack/TTS.py

* 更正拼写错误

* 支持固定chunk长度的流式推理，优化sola算法

* 修复api_v2的ogg格式传输问题
 2025-11-28 21:12:41 +08:00
ChasonJiang
b9211657d8
优化TTS_Config的代码逻辑 (#2536) 
* 优化TTS_Config的代码逻辑

* 在载入vits权重之后保存tts_config
 2025-07-18 11:54:40 +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
XXXXRT666
6fdc67ca83
Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464) 
* Update Install.sh

* Format Code

* Delete dev null

* Update README, Support Dark Mode in CSS/JS
 2025-06-17 15:21:36 +08:00
YYuX-1145
dd2b9253aa
Update TTS.py (#2450) 2025-06-11 10:28:42 +08:00
Jialiang Zhu
035dcbad03
Fix AttributeError when prompt_cache['refer_spec'][0] is a tuple (#2428) 
Co-authored-by: tzrain <tz_rain@foxmail.com>
 2025-06-05 10:55:21 +08:00
RVC-Boss
584fcae9a5
support sovits v2Pro v2ProPlus 
support sovits v2Pro v2ProPlus
 2025-06-04 15:25:52 +08:00
RVC-Boss
92819d0b31
support sovits v2Pro v2ProPlus 
support sovits v2Pro v2ProPlus
 2025-06-04 15:19:20 +08:00
XXXXRT666
d5e479dad6
Introduce Docker and Windows CI Workflow, Pre-commit Formatting, and Language Resource Auto-Download (#2351) 
* Docker Auto-Build Workflow

* Rename

* Update

* Fix Bugs

* Disable Progress Bar When workflows triggered

* Fix Wget

* Fix Bugs

* Fix Bugs

* Update Wget

* Update Workflows

* Accelerate Docker Image Building

* Fix Install.sh

* Add Skip-Check For Action Runner

* Fix Dockerfile

* .

* .

* .

* .

* Delete File in Runner

* Add Sort

* Delete More Files

* Delete More

* .

* .

* .

* Add Pre-Commit Hook
Update Docker

* Add Code Spell Check

* [pre-commit.ci] trigger

* [pre-commit.ci] trigger

* [pre-commit.ci] trigger

* Fix Bugs

* .

* Disable Progress Bar and Logs while using GitHub Actions

* .

* .

* Fix Bugs

* update conda

* fix bugs

* Fix Bugs

* fix bugs

* .

* .

* Quiet Installation

* fix bugs

* .

* fix bug

* .

* Fix pre-commit.ci and Docker

* fix bugs

* .

* Update Docker & Pre-Commit

* fix  bugs

* Update Req

* Update Req

* Update OpenCC

* update precommit

* .

* Update .pre-commit-config.yaml

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

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

* Update Docs and fix bugs

* Fix \

* Fix MacOS

* .

* test

* .

* Add Tag Alias

* .

* fix bugs

* fix bugs

* make image smaller

* update pre-commit config

* .

* .

* fix bugs

* use miniconda

* Fix Wrong Path

* .

* debug

* debug

* revert

* Fix Bugs

* Update Docs, Add Dict Auto Download in install.sh

* update docker_build

* Update Docs for Install.sh

* update docker docs about architecture

* Add Xcode-Commandline-Tool Installation

* Update Docs

1. Add Missing VC17
2. Modufied the Order of FFmpeg Installation and Requirements Installation
3. Remove Duplicate FFmpeg

* Fix Wrong Cuda Version

* Update TESTED ENV

* Add PYTHONNOUSERSITE(-s)

* Fix Wrapper

* Update install.sh For Robustness

* Ignore .git

* Preload CUDNN For Ctranslate2

* Remove Gradio Warnings

* Update Colab

* Fix OpenCC Problems

* Update Win DLL Strategy

* Fix Onnxruntime-gpu NVRTC Error

* Fix Path Problems

* Add Windows Packages Workflow

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* .

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* Fix Path

* Fix Path

* Enable Logging

* Set 7-Zip compression level to maximum (-mx=9)

* Use Multithread in ONNX Session

* Fix Tag Bugs

* Add Time

* Add Time

* Add Time

* Compress More

* Copy DLL to Solve VC Runtime DLL Missing Issues

* Expose FFmpeg Errors, Copy Only Part of Visual C++ Runtime

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* WIP

* WIP

* WIP

* Update build_windows_packages.ps1

* Update install.sh

* Update build_windows_packages.ps1

* Update docker-publish.yaml

* Update install.sh

* Update Dockerfile

* Update docker_build.sh

* Update miniconda_install.sh

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update Colab-WebUI.ipynb

* Update Colab-Inference.ipynb

* Update docker-compose.yaml

* 更新 build_windows_packages.ps1

* Update install.sh

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2025-05-26 10:45:14 +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
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
839ff9ce5b
适配v4并行推理（还没写完） 2025-04-21 22:43:46 +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
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
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
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
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
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
RVC-Boss
a68e3c4354
Update TTS.py 2025-02-27 22:14:51 +08:00
StaryLan
15cbd1b673
Update Documentation (#2032) 
* add exception handling

* Fill in the missing content

* remove GB code

* Simplify i18n text and remove trailing spaces

* ignore v3 model dir

* Update Changelog

* Fix encoding
 2025-02-12 11:27:35 +08:00
ChasonJiang
f35f6e9b5e
优化tts_config代码逻辑 (#1538) 
* 优化tts_config

* fix

* 优化报错提示

* 优化报错提示
 2024-08-29 00:33:07 +08:00
XXXXRT666
7dac47ca95
chores (#1528) 
* chores

* ...

* Add files via upload

* ...

* remove gradio warnings

* Update inference_webui.py

Fix inference_cli issue
 2024-08-23 17:47:27 +08:00
ChasonJiang
2a9512a63e
修改文档 (#1521) 2024-08-23 17:43:40 +08:00
ChasonJiang
52c50c6c81
All in one! 合并main分支和fast_inference_分支 (#1490) 
* 合并main分支和fast_inference_分支

* 修复一些bug
 2024-08-20 22:19:04 +08:00