SOTA Open Source TTS
Optimize Documents for Windows (#266)
spicysamadc8c83444440
diff --git a/docs/assets/figs/VS_1.jpg b/docs/assets/figs/VS_1.jpgnew file mode 100644index 0000000..41a3f69Binary files /dev/null and b/docs/assets/figs/VS_1.jpg differdiff --git a/docs/en/index.md b/docs/en/index.mdindex b6cde07..8875c54 100644--- a/docs/en/index.md+++ b/docs/en/index.md@@ -26,54 +26,67 @@ This codebase is released under the `BSD-3-Clause` license, and all models are r- GPU Memory: 4GB (for inference), 16GB (for fine-tuning)- System: Linux, Windows-~~We recommend Windows users to use WSL2 or docker to run the codebase, or use the integrated environment developed by the community.~~-## Windows SetupWindows professional users may consider WSL2 or Docker to run the codebase.Non-professional Windows users can consider the following methods to run the codebase without a Linux environment (with model compilation capabilities aka `torch.compile`):-0. Extract the project zip file.-1. Click `install_env.bat` to install the environment.-- 1. You can decide whether to use a mirror site for downloading by editing the `USE_MIRROR` item in `install_env.bat`.- 2. The default is `preview`, using a mirror site and the latest development version of torch (the only way to activate the compilation method).- 3. `false` uses the original site to download the environment. `true` uses the mirror site to download the stable version of torch and other environments.--2. (Optional, this step is to activate the model compilation environment)-- 1. Use the following links to download the `LLVM` compiler.-- - [LLVM-17.0.6 (original site download)](https://huggingface.co/fishaudio/fish-speech-1/resolve/main/LLVM-17.0.6-win64.exe?download=true)- - [LLVM-17.0.6 (mirror site download)](https://hf-mirror.com/fishaudio/fish-speech-1/resolve/main/LLVM-17.0.6-win64.exe?download=true)- - After downloading `LLVM-17.0.6-win64.exe`, double-click to install, choose the appropriate installation location, and most importantly, check `Add Path to Current User` to add the environment variable.- - Confirm the installation is complete.-- 2. Download and install the Microsoft Visual C++ Redistributable Package to resolve potential .dll missing issues.- - [MSVC++ 14.40.33810.0 download](https://aka.ms/vs/17/release/vc_redist.x64.exe)--3. Double-click `start.bat` to enter the Fish-Speech training and inference configuration WebUI page.-- - Want to go directly to the inference page? Edit the `API_FLAGS.txt` in the project root directory, and modify the first three lines as follows:-- ```text- --infer- # --api- # --listen ...- ...- ```-- - Want to start the API server? Edit the API_FLAGS.txt in the project root directory, and modify the first three lines as follows:-- ```text- # --infer- --api- --listen ...- ...- ```--4. (Optional) Double-click run_cmd.bat to enter the conda/python command line environment of this project.+<ol>+ <li>Unzip the project package.</li>+ <li>Click <code>install_env.bat</code> to install the environment.+ <ul>+ <li>You can decide whether to use a mirror site for downloads by editing the <code>USE_MIRROR</code> item in <code>install_env.bat</code>.</li>+ <li><code>USE_MIRROR=false</code> downloads the latest stable version of <code>torch</code> from the original site. <code>USE_MIRROR=true</code> downloads the latest version of <code>torch</code> from a mirror site. The default is <code>true</code>.</li>+ <li>You can decide whether to enable the compiled environment download by editing the <code>INSTALL_TYPE</code> item in <code>install_env.bat</code>.</li>+ <li><code>INSTALL_TYPE=preview</code> downloads the preview version with the compiled environment. <code>INSTALL_TYPE=stable</code> downloads the stable version without the compiled environment.</li>+ </ul>+ </li>+ <li>If step 2 has <code>USE_MIRROR=preview</code>, execute this step (optional, for activating the compiled model environment):+ <ol>+ <li>Download the LLVM compiler using the following links:+ <ul>+ <li><a href="https://huggingface.co/fishaudio/fish-speech-1/resolve/main/LLVM-17.0.6-win64.exe?download=true">LLVM-17.0.6 (original site download)</a></li>+ <li><a href="https://hf-mirror.com/fishaudio/fish-speech-1/resolve/main/LLVM-17.0.6-win64.exe?download=true">LLVM-17.0.6 (mirror site download)</a></li>+ <li>After downloading <code>LLVM-17.0.6-win64.exe</code>, double-click to install it, choose an appropriate installation location, and most importantly, check <code>Add Path to Current User</code> to add to the environment variables.</li>+ <li>Confirm the installation is complete.</li>+ </ul>+ </li>+ <li>Download and install the Microsoft Visual C++ Redistributable package to resolve potential .dll missing issues.+ <ul>+ <li><a href="https://aka.ms/vs/17/release/vc_redist.x64.exe">MSVC++ 14.40.33810.0 Download</a></li>+ </ul>+ </li>+ <li>Download and install Visual Studio Community Edition to obtain MSVC++ build tools, resolving LLVM header file dependencies.+ <ul>+ <li><a href="https://visualstudio.microsoft.com/zh-hans/downloads/">Visual Studio Download</a></li>+ <li>After installing Visual Studio Installer, download Visual Studio Community 2022.</li>+ <li>Click the <code>Modify</code> button as shown below, find the <code>Desktop development with C++</code> option, and check it for download.</li>+ <p align="center">+ <img src="/assets/figs/VS_1.jpg" width="75%">+ </p>+ </ul>+ </li>+ </ol>+ </li>+ <li>Double-click <code>start.bat</code> to enter the Fish-Speech training inference configuration WebUI page.+ <ul>+ <li>(Optional) Want to go directly to the inference page? Edit the <code>API_FLAGS.txt</code> in the project root directory and modify the first three lines as follows:+ <pre><code>--infer+# --api+# --listen ...+...</code></pre>+ </li>+ <li>(Optional) Want to start the API server? Edit the <code>API_FLAGS.txt</code> in the project root directory and modify the first three lines as follows:+ <pre><code># --infer+--api+--listen ...+...</code></pre>+ </li>+ </ul>+ </li>+ <li>(Optional) Double-click <code>run_cmd.bat</code> to enter the conda/python command line environment of this project.</li>+</ol>## Linux Setupdiff --git a/docs/zh/index.md b/docs/zh/index.mdindex 355d159..b8da365 100644--- a/docs/zh/index.md+++ b/docs/zh/index.md@@ -26,50 +26,67 @@- GPU 内存: 4GB (用于推理), 16GB (用于微调)- 系统: Linux, Windows-~~我们建议 Windows 用户使用 WSL2 或 docker 来运行代码库, 或者使用由社区开发的整合环境.~~-## Windows 配置Windows 专业用户可以考虑 WSL2 或 docker 来运行代码库。Windows 非专业用户可考虑以下为免 Linux 环境的基础运行方法(附带模型编译功能,即 `torch.compile`):-0. 解压项目压缩包。-1. 点击`install_env.bat`安装环境。- - 可以通过编辑`install_env.bat`的`USE_MIRROR`项来决定是否使用镜像站下载。- - 默认为`preview`, 使用镜像站且使用最新开发版本 torch(唯一激活编译方式)。- - `false`使用原始站下载环境。`true`为从镜像站下载稳定版本 torch 和其余环境。-2. (可跳过,此步为激活编译模型环境)-- 1. 使用如下链接下载`LLVM`编译器。- - [LLVM-17.0.6 (原始站点下载)](https://huggingface.co/fishaudio/fish-speech-1/resolve/main/LLVM-17.0.6-win64.exe?download=true)- - [LLVM-17.0.6 (镜像站点下载)](https://hf-mirror.com/fishaudio/fish-speech-1/resolve/main/LLVM-17.0.6-win64.exe?download=true)- - 下载完`LLVM-17.0.6-win64.exe`后,双击进行安装,选择合适的安装位置,最重要的是勾选`Add Path to Current User`添加环境变量。- - 确认安装完成。- 2. 下载安装`Microsoft Visual C++ 可再发行程序包`, 解决潜在`.dll`丢失问题。- - [MSVC++ 14.40.33810.0 下载](https://aka.ms/vs/17/release/vc_redist.x64.exe)--3. 双击`start.bat`, 进入 Fish-Speech 训练推理配置 WebUI 页面。-- - 想直接进入推理页面?编辑项目根目录下的`API_FLAGS.txt`, 前三行修改成如下格式:-- ```text- --infer- # --api- # --listen ...- ...- ```-- - 想启动 API 服务器?编辑项目根目录下的`API_FLAGS.txt`, 前三行修改成如下格式:-- ```text- # --infer- --api- --listen ...- ...- ```--4. (可选)双击`run_cmd.bat`进入本项目的 conda/python 命令行环境+<ol>+ <li>解压项目压缩包。</li>+ <li>点击 install_env.bat 安装环境。+ <ul>+ <li>可以通过编辑 install_env.bat 的 <code>USE_MIRROR</code> 项来决定是否使用镜像站下载。</li>+ <li><code>USE_MIRROR=false</code> 使用原始站下载最新稳定版 <code>torch</code> 环境。<code>USE_MIRROR=true</code> 为从镜像站下载最新 <code>torch</code> 环境。默认为 <code>true</code>。</li>+ <li>可以通过编辑 install_env.bat 的 <code>INSTALL_TYPE</code> 项来决定是否启用可编译环境下载。</li>+ <li><code>INSTALL_TYPE=preview</code> 下载开发版编译环境。<code>INSTALL_TYPE=stable</code> 下载稳定版不带编译环境。</li>+ </ul>+ </li>+ <li>若第2步 INSTALL_TYPE=preview 则执行这一步(可跳过,此步为激活编译模型环境)+ <ol>+ <li>使用如下链接下载 LLVM 编译器。+ <ul>+ <li><a href="https://huggingface.co/fishaudio/fish-speech-1/resolve/main/LLVM-17.0.6-win64.exe?download=true">LLVM-17.0.6(原站站点下载)</a></li>+ <li><a href="https://hf-mirror.com/fishaudio/fish-speech-1/resolve/main/LLVM-17.0.6-win64.exe?download=true">LLVM-17.0.6(镜像站点下载)</a></li>+ <li>下载完 LLVM-17.0.6-win64.exe 后,双击进行安装,选择合适的安装位置,最重要的是勾选 <code>Add Path to Current User</code> 添加环境变量。</li>+ <li>确认安装完成。</li>+ </ul>+ </li>+ <li>下载安装 Microsoft Visual C++ 可再发行程序包,解决潜在 .dll 丢失问题。+ <ul>+ <li><a href="https://aka.ms/vs/17/release/vc_redist.x64.exe">MSVC++ 14.40.33810.0 下载</a></li>+ </ul>+ </li>+ <li>下载安装 Visual Studio 社区版以获取 MSVC++ 编译工具, 解决 LLVM 的头文件依赖问题。+ <ul>+ <li><a href="https://visualstudio.microsoft.com/zh-hans/downloads/">Visual Studio 下载</a></li>+ <li>安装好Visual Studio Installer之后,下载Visual Studio Community 2022</li>+ <li>如下图点击<code>修改</code>按钮,找到<code>使用C++的桌面开发</code>项,勾选下载</li>+ <p align="center">+ <img src="/assets/figs/VS_1.jpg" width="75%">+ </p>+ </ul>+ </li>+ </ol>+ </li>+ <li>双击 start.bat, 进入 Fish-Speech 训练推理配置 WebUI 页面。+ <ul>+ <li>(可选) 想直接进入推理页面?编辑项目根目录下的 <code>API_FLAGS.txt</code>, 前三行修改成如下格式:+ <pre><code>--infer+# --api+# --listen ...+...</code></pre>+ </li>+ <li>(可选) 想启动 API 服务器?编辑项目根目录下的 <code>API_FLAGS.txt</code>, 前三行修改成如下格式:+ <pre><code># --infer+--api+--listen ...+...</code></pre>+ </li>+ </ul>+ </li>+ <li>(可选)双击 <code>run_cmd.bat</code> 进入本项目的 conda/python 命令行环境</li>+</ol>## Linux 配置diff --git a/install_env.bat b/install_env.batindex f0968fa..e9d1bd4 100644--- a/install_env.bat+++ b/install_env.bat@@ -1,9 +1,10 @@@echo offchcp 65001-set USE_MIRROR=preview+set USE_MIRROR=trueset INSTALL_TYPE=preview-echo use_mirror = %USE_MIRROR%+echo "USE_MIRROR: %USE_MIRROR%"+echo "INSTALL_TYPE: %INSTALL_TYPE%"setlocal enabledelayedexpansioncd /D "%~dp0"@@ -124,11 +125,14 @@ if "!INSTALL_TYPE!" == "preview" (set "packages=!packages! triton_windows")-set "HF_ENDPOINT=https://hf-mirror.com"-if "!USE_MIRROR!" == "false" (- set "HF_ENDPOINT=https://huggingface.co"+set "HF_ENDPOINT=https://huggingface.co"+set "no_proxy="+if "!USE_MIRROR!" == "true" (+ set "HF_ENDPOINT=https://hf-mirror.com"+ set "no_proxy=localhost, 127.0.0.1, 0.0.0.0")echo "HF_ENDPOINT: !HF_ENDPOINT!"+echo "NO_PROXY: !no_proxy!"set "install_packages="for %%p in (%packages%) do (@@ -138,47 +142,17 @@ for %%p in (%packages%) do ())-if not "!install_packages!"=="" (echo.echo Installing: !install_packages!-for %%p in (!install_packages!) do (- if "!USE_MIRROR!"=="true" (- if "%%p"=="torch" (- %PIP_CMD% install torch --index-url https://mirror.sjtu.edu.cn/pytorch-wheels/cu121 --no-warn-script-location- ) else if "%%p"=="torchvision" (- %PIP_CMD% install torchvision --index-url https://mirror.sjtu.edu.cn/pytorch-wheels/cu121 --no-warn-script-location- ) else if "%%p"=="torchaudio" (- %PIP_CMD% install torchaudio --index-url https://mirror.sjtu.edu.cn/pytorch-wheels/cu121 --no-warn-script-location- ) else if "%%p"=="openai-whisper" (- %PIP_CMD% install -i https://pypi.tuna.tsinghua.edu.cn/simple openai-whisper --no-warn-script-location- ) else if "%%p"=="fish-speech" (- %PIP_CMD% install -e . -i https://pypi.tuna.tsinghua.edu.cn/simple- )- )-- if "!USE_MIRROR!"=="false" (- if "%%p"=="torch" (- %PIP_CMD% install torch==2.4.0.dev20240427+cu121 --index-url https://download.pytorch.org/whl/nightly/cu121 --no-warn-script-location- ) else if "%%p"=="torchvision" (- %PIP_CMD% install torchvision==0.19.0.dev20240428+cu121 --index-url https://download.pytorch.org/whl/nightly/cu121 --no-warn-script-location- ) else if "%%p"=="torchaudio" (- %PIP_CMD% install torchaudio==2.2.0.dev20240427+cu121 --index-url https://download.pytorch.org/whl/nightly/cu121 --no-warn-script-location- ) else if "%%p"=="openai-whisper" (- %PIP_CMD% install openai-whisper --no-warn-script-location- ) else if "%%p"=="fish-speech" (- %PIP_CMD% install -e .- )- )-if "!INSTALL_TYPE!"=="preview" (if "%%p"=="torch" (set "WHEEL_FILE=torch-2.4.0.dev20240427+cu121-cp310-cp310-win_amd64.whl"set "URL=!HF_ENDPOINT!/datasets/SpicyqSama007/windows_compile/resolve/main/torch-2.4.0.dev20240427_cu121-cp310-cp310-win_amd64.whl?download=true"set "CHKSUM=b091308f4cb74e63d0323afd67c92f2279d9e488d8cbf467bcc7b939bcd74e0b":TORCH_DOWNLOAD- echo "%CD%\!WHEEL_FILE!"+ echo "%CD%\!WHEEL_FILE!"if not exist "%CD%\!WHEEL_FILE!" (call curl -Lk "!URL!" --output "!WHEEL_FILE!")@@ -257,7 +231,50 @@ if not "!install_packages!"=="" ())+ )+)+set "install_packages="+for %%p in (%packages%) do (+ %PIP_CMD% show %%p >nul 2>&1+ if errorlevel 1 (+ set "install_packages=!install_packages! %%p"+ )+)++if not "!install_packages!"=="" (+ echo.+ echo Installing: !install_packages!++ for %%p in (!install_packages!) do (+ if "!USE_MIRROR!"=="true" (+ if "%%p"=="torch" (+ %PIP_CMD% install torch --index-url https://mirror.sjtu.edu.cn/pytorch-wheels/cu121 --no-warn-script-location+ ) else if "%%p"=="torchvision" (+ %PIP_CMD% install torchvision --index-url https://mirror.sjtu.edu.cn/pytorch-wheels/cu121 --no-warn-script-location+ ) else if "%%p"=="torchaudio" (+ %PIP_CMD% install torchaudio --index-url https://mirror.sjtu.edu.cn/pytorch-wheels/cu121 --no-warn-script-location+ ) else if "%%p"=="openai-whisper" (+ %PIP_CMD% install -i https://pypi.tuna.tsinghua.edu.cn/simple openai-whisper --no-warn-script-location+ ) else if "%%p"=="fish-speech" (+ %PIP_CMD% install -e . -i https://pypi.tuna.tsinghua.edu.cn/simple+ )+ )++ if "!USE_MIRROR!"=="false" (+ if "%%p"=="torch" (+ %PIP_CMD% install torch --index-url https://download.pytorch.org/whl/nightly/cu121 --no-warn-script-location+ ) else if "%%p"=="torchvision" (+ %PIP_CMD% install torchvision --index-url https://download.pytorch.org/whl/nightly/cu121 --no-warn-script-location+ ) else if "%%p"=="torchaudio" (+ %PIP_CMD% install torchaudio --index-url https://download.pytorch.org/whl/nightly/cu121 --no-warn-script-location+ ) else if "%%p"=="openai-whisper" (+ %PIP_CMD% install openai-whisper --no-warn-script-location+ ) else if "%%p"=="fish-speech" (+ %PIP_CMD% install -e .+ )+ )+))echo Environment Check: Success.diff --git a/start.bat b/start.batindex ceeec00..b08c301 100644--- a/start.bat+++ b/start.bat@@ -1,17 +1,25 @@@echo offchcp 65001-+set USE_MIRROR=trueset PYTHONPATH=%~dp0set PYTHON_CMD=%cd%\fishenv\env\pythonset API_FLAG_PATH=%~dp0API_FLAGS.txt-set no_proxy="localhost, 127.0.0.1, 0.0.0.0"-set HF_ENDPOINT=https://hf-mirror.com+%PYTHON_CMD% .\tools\download_models.pysetlocal enabledelayedexpansion+set "HF_ENDPOINT=https://huggingface.co"+set "no_proxy="+if "%USE_MIRROR%" == "true" (+ set "HF_ENDPOINT=https://hf-mirror.com"+ set "no_proxy=localhost, 127.0.0.1, 0.0.0.0"+)+echo "HF_ENDPOINT: !HF_ENDPOINT!"+echo "NO_PROXY: !no_proxy!"+set "API_FLAGS="set "flags="