lunavox 2.0.0__tar.gz

lunavox-2.0.0/LICENSE

@@ -0,0 +1,241 @@
+Lunavox Project License
+=======================
+
+This project involves both original software code and derivative model weights. 
+The licensing terms are structured as follows:
+
+1. SOFTWARE CODE LICENSE
+------------------------
+The C++ source code, build scripts, and optimization logic original to the 
+Lunavox project are licensed under the MIT License:
+
+MIT License
+
+Copyright (c) 2026 Waiyuk Kwong
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+
+2. MODEL AND DERIVATIVE WORKS LICENSE
+-------------------------------------
+The model weights, configurations, and derivative quantized artifacts (including 
+but not limited to GGUF and ONNX formats) are derived from Qwen3-TTS and are 
+subject to the Apache License, Version 2.0 provided by Alibaba Cloud:
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

lunavox-2.0.0/PKG-INFO

@@ -0,0 +1,208 @@
+Metadata-Version: 2.4
+Name: lunavox
+Version: 2.0.0
+Summary: LunaVox tooling CLI for model setup, conversion, quantization, and build workflows.
+Author: LunaVox Contributors
+License: MIT
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: typer>=0.12.0
+Requires-Dist: rich>=13.7.0
+Requires-Dist: huggingface_hub>=0.24.0
+Provides-Extra: gui
+Requires-Dist: customtkinter>=5.2.0; extra == "gui"
+Requires-Dist: pygame>=2.5.0; extra == "gui"
+Provides-Extra: convert
+Requires-Dist: torch>=2.1; extra == "convert"
+Requires-Dist: torchaudio>=2.1; extra == "convert"
+Requires-Dist: transformers==4.57.6; extra == "convert"
+Requires-Dist: accelerate==1.12.0; extra == "convert"
+Requires-Dist: onnx; extra == "convert"
+Requires-Dist: onnxruntime; extra == "convert"
+Requires-Dist: onnxruntime-tools; extra == "convert"
+Requires-Dist: gguf; extra == "convert"
+Requires-Dist: numpy; extra == "convert"
+Requires-Dist: tqdm; extra == "convert"
+Requires-Dist: safetensors; extra == "convert"
+Requires-Dist: sentencepiece; extra == "convert"
+Requires-Dist: librosa; extra == "convert"
+Requires-Dist: scipy; extra == "convert"
+Requires-Dist: soundfile; extra == "convert"
+Requires-Dist: einops; extra == "convert"
+Requires-Dist: onnxscript; extra == "convert"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.2; extra == "dev"
+Requires-Dist: build>=1.2; extra == "dev"
+Requires-Dist: twine>=5.1; extra == "dev"
+Dynamic: license-file
+
+# 🌌 LunaVox: Qwen3-TTS C++ 高性能推理引擎
+
+![Version](https://img.shields.io/badge/version-2.0.0-blueviolet?style=for-the-badge)
+![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-0078d7?style=for-the-badge&logo=windows&logoColor=white)
+![CoreML](https://img.shields.io/badge/iOS-CoreML-000000?style=for-the-badge&logo=apple&logoColor=white)
+![C++](https://img.shields.io/badge/C++-17-00599C?style=for-the-badge&logo=c%2B%2B)
+[![License](https://img.shields.io/badge/license-MIT-green?style=for-the-badge)](../../LICENSE)
+
+**LunaVox** 是专为 **Qwen3-TTS** 打造的高性能 C++ 推理引擎。它通过精简的架构设计和深度的硬件优化，提供了极致的语音合成速度与灵活性。无论是本地嵌入式设备、桌面应用还是高性能服务器，LunaVox 都能提供稳定、低延迟的 TTS 体感。
+
+---
+
+## 🚀 核心特性
+
+- **轻量级运行**: 仅需 ONNX Runtime 与自定义 Llama 推理库，无需繁重的 Python 环境即可运行。
+- **多语言原生支持**: 引擎链路内置自动语言检测，完美支持 **中、英、日、韩、俄、德、法、意、西、葡** 十种语言。
+- **全模式支持**: 支持 基础合成 (Base)、声音克隆 (Clone)、定制定制声音 (Custom) 及 创意声音设计 (Design)。
+- **现代构建系统**: 全自动工具链识别。支持 Windows (MSVC)、Linux (GCC) 及 macOS (Clang/Apple Silicon)。
+- **跨平台硬件加速**: 深度集成 CUDA (NVIDIA), CoreML/Metal (Apple), DML (DirectX 12) 与 Vulkan 接口。
+
+---
+
+## 🛠️ 环境与构建要求
+
+### 1. 系统环境
+- **Windows**: Windows 10/11 (VS 2022/2025 支持)
+- **Linux**: Ubuntu 22.04+ 或主流发行版 (GCC >= 9.0)
+- **macOS**: Apple Silicon (M1/M2/M3), macOS 12+ (Metal 支持)
+- **编译器**: MSVC (v143/v144)、GCC 10.0+ 或 Apple Clang
+- **构建工具**: CMake 3.16+，建议安装 **Ninja** 提升构建速度
+
+### 2. 依赖库
+- **Python 3.10+**: 用于模型转换和自动化管理。
+- **ONNX Runtime SDK**: 对应平台的 C++ 动态库。
+- **Llama Runtime**: 预编译的后端二进程文件。
+
+---
+
+## 📊 性能评估
+
+下表展示了 LunaVox 在不同后端配置下的平均性能表现。详细报告请参阅 **[Windows 性能评估报告](benchmark/windows_performance.md)**。
+
+| 测试配置 | 平均 RTF | 峰值内存 (RAM) | 显存 (VRAM) | 相对加速比 (Speedup) |
+| :--- | :---: | :---: | :---: | :---: |
+| **Baseline (CPU)** | 5.066 | 5.06 GB | — | 1.00x |
+| **Baseline (GPU)** | 3.788 | 1.59 GB | 2.29 GB | 1.34x |
+| **LunaVox (Full CPU)** | 1.152 | 1.06 GB | — | 4.40x |
+| **LunaVox (CUDA13)** | 0.254 | 1.39 GB | 1.30 GB | 19.94x |
+| **LunaVox (Llama.cpp (Vulkan) / ORT (DML))** | **0.206** | 0.91 GB | 1.05 GB | **24.59x** |
+
+> [!NOTE]
+> - **测试模型**: 基于 **Qwen3-TTS-12Hz-0.6B-Base**，开启声音克隆模式并在使用 `.json` 预计算特征文件作为参考。
+> - **测试环境**: Intel i9-12900K + NVIDIA RTX 3090
+> - **测试标准**: 在 **3 次预热**后，取 **10 次运行**的平均结果。
+
+---
+
+### 3. CLI 工具与依赖安装
+
+```powershell
+# 安装核心推理工具
+pip install lunavox
+```
+
+> [!NOTE]
+> **开发与脚本说明**: LunaVox 已发布至 PyPI，标准用户仅需执行 `pip install lunavox` 即可安装完整工具。若您需要深入研究模型转换、量化流水线或导出 Python 脚本，请切换至 **`dev`** 分支获取最新源码与内部工具。
+
+## 📦 快速上手流程 (One-Key Setup)
+
+LunaVox 推荐使用 `bootstrap` 指令一键完成 **模型拉取、运行库下载、项目构建及交互测试**。
+
+### 1. 自动引导安装 (推荐)
+```powershell
+# 执行全自动引导设置
+lunavox bootstrap
+```
+
+### 2. 本地构建 (从源码)
+如果您需要精细化控制每个步骤，可以运行：
+```powershell
+# 1. 下载预转换模型 (或使用 convert 本地转换原始模型)
+lunavox pull-model
+
+# 2. 下载 C++ 运行库
+lunavox download-libs
+
+# 3. 自动编译项目
+lunavox build --clean
+```
+
+> [!TIP]
+> 更多详细命令和高级参数说明，请参阅 **[LunaVox CLI 指令汇总手册](guide/cli_reference.md)**。
+
+---
+
+## 🧱 运行库依赖 (Libraries)
+
+LunaVox 自动下载 `lib/` 下相应的 ONNX Runtime 与 Llama.cpp。如果您需要针对 CUDA 环境进行精细化配置，请参阅：
+- **[CUDA 12 Windows 依赖指南](install/cuda12_windows.md)**
+- **[CUDA 13 Windows 依赖指南](install/cuda13_windows.md)**
+
+---
+
+
+## 🎙️ 推理测试与模式说明
+
+编译完成后，可执行程序位于 `./build/qwen3-tts-cli.exe`。
+> [!NOTE]
+> - Linux/macOS 系统请使用 `./build/qwen3-tts-cli` 运行。
+> - `--instruct` 仅对 **Custom** 和 **Design** 模式有效（Base 模式下禁用）。
+
+详细教程请参阅：**[CLI 指令使用指南](guide/usage_tutorial.md)**。
+
+### 1. 声音克隆 (Voice Cloning)
+通过参考音频（.wav）或预计算特征（.json）模仿特定音色：
+```bash
+./build/qwen3-tts-cli.exe `
+  -m models/base_small `
+  -r ref/ref_0.6B.json `
+  -t "Okay, fine, I'm just gonna leave this sock monkey here. Goodbye." `
+  -o output/cloned.wav
+```
+
+### 2. 定制化声音 (Custom Voice)
+使用系统内置的发音人 ID：
+```bash
+./build/qwen3-tts-cli.exe `
+  -m models/custom `
+  --speaker Vivian `
+  --instruct "Use angry tone." `
+  -t "She said she would be here by noon." `
+  -o output/custom.wav
+```
+
+### 3. 声音设计 (Voice Design)
+使用描述设计声音
+```bash
+.\build\qwen3-tts-cli.exe `
+  -m models/design `
+  -t "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!" `
+  --instruct "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice."
+  -o output/out.wav `
+
+---
+
+## 📈 性能监控与日志
+
+- **详细统计**: 运行命令时添加 `--stats-json report.json` 即可获取 RTF（实时率）和内存占用分析。
+- **日志查看**: 所有的构建和运行输出均实时记录在 `../../logs/latest.log` 中。
+- **线程控制**: 使用 `-j` 参数（默认 4）调整 CPU 线程使用。
+
+---
+
+## 📜 更多信息
+
+有关运行时详细配置及设计准则，请参阅:
+- **[LunaVox CLI 指令汇总手册](guide/cli_reference.md)**
+- **[运行时技术规范与约束](technical/runtime_specs.md)**
+- **[合成链路编码器需求分析](technical/synthesis_pathway.md)**
+
+---
+
+## 🙏 致谢
+
+本项目深受以下开源项目的启发或基于其成果：
+
+- **[Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS)**: 提供强大的 base 模型权重与原始架构设计。
+- **[onnxruntime](https://github.com/microsoft/onnxruntime)**: 驱动高性能音频解码后端。
+- **[llama.cpp](https://github.com/ggml-org/llama.cpp)**: 驱动 LLM 序列预测核心。

lunavox-2.0.0/README.md

@@ -0,0 +1,169 @@
+# 🌌 LunaVox: Qwen3-TTS C++ 高性能推理引擎
+
+![Version](https://img.shields.io/badge/version-2.0.0-blueviolet?style=for-the-badge)
+![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-0078d7?style=for-the-badge&logo=windows&logoColor=white)
+![CoreML](https://img.shields.io/badge/iOS-CoreML-000000?style=for-the-badge&logo=apple&logoColor=white)
+![C++](https://img.shields.io/badge/C++-17-00599C?style=for-the-badge&logo=c%2B%2B)
+[![License](https://img.shields.io/badge/license-MIT-green?style=for-the-badge)](../../LICENSE)
+
+**LunaVox** 是专为 **Qwen3-TTS** 打造的高性能 C++ 推理引擎。它通过精简的架构设计和深度的硬件优化，提供了极致的语音合成速度与灵活性。无论是本地嵌入式设备、桌面应用还是高性能服务器，LunaVox 都能提供稳定、低延迟的 TTS 体感。
+
+---
+
+## 🚀 核心特性
+
+- **轻量级运行**: 仅需 ONNX Runtime 与自定义 Llama 推理库，无需繁重的 Python 环境即可运行。
+- **多语言原生支持**: 引擎链路内置自动语言检测，完美支持 **中、英、日、韩、俄、德、法、意、西、葡** 十种语言。
+- **全模式支持**: 支持 基础合成 (Base)、声音克隆 (Clone)、定制定制声音 (Custom) 及 创意声音设计 (Design)。
+- **现代构建系统**: 全自动工具链识别。支持 Windows (MSVC)、Linux (GCC) 及 macOS (Clang/Apple Silicon)。
+- **跨平台硬件加速**: 深度集成 CUDA (NVIDIA), CoreML/Metal (Apple), DML (DirectX 12) 与 Vulkan 接口。
+
+---
+
+## 🛠️ 环境与构建要求
+
+### 1. 系统环境
+- **Windows**: Windows 10/11 (VS 2022/2025 支持)
+- **Linux**: Ubuntu 22.04+ 或主流发行版 (GCC >= 9.0)
+- **macOS**: Apple Silicon (M1/M2/M3), macOS 12+ (Metal 支持)
+- **编译器**: MSVC (v143/v144)、GCC 10.0+ 或 Apple Clang
+- **构建工具**: CMake 3.16+，建议安装 **Ninja** 提升构建速度
+
+### 2. 依赖库
+- **Python 3.10+**: 用于模型转换和自动化管理。
+- **ONNX Runtime SDK**: 对应平台的 C++ 动态库。
+- **Llama Runtime**: 预编译的后端二进程文件。
+
+---
+
+## 📊 性能评估
+
+下表展示了 LunaVox 在不同后端配置下的平均性能表现。详细报告请参阅 **[Windows 性能评估报告](benchmark/windows_performance.md)**。
+
+| 测试配置 | 平均 RTF | 峰值内存 (RAM) | 显存 (VRAM) | 相对加速比 (Speedup) |
+| :--- | :---: | :---: | :---: | :---: |
+| **Baseline (CPU)** | 5.066 | 5.06 GB | — | 1.00x |
+| **Baseline (GPU)** | 3.788 | 1.59 GB | 2.29 GB | 1.34x |
+| **LunaVox (Full CPU)** | 1.152 | 1.06 GB | — | 4.40x |
+| **LunaVox (CUDA13)** | 0.254 | 1.39 GB | 1.30 GB | 19.94x |
+| **LunaVox (Llama.cpp (Vulkan) / ORT (DML))** | **0.206** | 0.91 GB | 1.05 GB | **24.59x** |
+
+> [!NOTE]
+> - **测试模型**: 基于 **Qwen3-TTS-12Hz-0.6B-Base**，开启声音克隆模式并在使用 `.json` 预计算特征文件作为参考。
+> - **测试环境**: Intel i9-12900K + NVIDIA RTX 3090
+> - **测试标准**: 在 **3 次预热**后，取 **10 次运行**的平均结果。
+
+---
+
+### 3. CLI 工具与依赖安装
+
+```powershell
+# 安装核心推理工具
+pip install lunavox
+```
+
+> [!NOTE]
+> **开发与脚本说明**: LunaVox 已发布至 PyPI，标准用户仅需执行 `pip install lunavox` 即可安装完整工具。若您需要深入研究模型转换、量化流水线或导出 Python 脚本，请切换至 **`dev`** 分支获取最新源码与内部工具。
+
+## 📦 快速上手流程 (One-Key Setup)
+
+LunaVox 推荐使用 `bootstrap` 指令一键完成 **模型拉取、运行库下载、项目构建及交互测试**。
+
+### 1. 自动引导安装 (推荐)
+```powershell
+# 执行全自动引导设置
+lunavox bootstrap
+```
+
+### 2. 本地构建 (从源码)
+如果您需要精细化控制每个步骤，可以运行：
+```powershell
+# 1. 下载预转换模型 (或使用 convert 本地转换原始模型)
+lunavox pull-model
+
+# 2. 下载 C++ 运行库
+lunavox download-libs
+
+# 3. 自动编译项目
+lunavox build --clean
+```
+
+> [!TIP]
+> 更多详细命令和高级参数说明，请参阅 **[LunaVox CLI 指令汇总手册](guide/cli_reference.md)**。
+
+---
+
+## 🧱 运行库依赖 (Libraries)
+
+LunaVox 自动下载 `lib/` 下相应的 ONNX Runtime 与 Llama.cpp。如果您需要针对 CUDA 环境进行精细化配置，请参阅：
+- **[CUDA 12 Windows 依赖指南](install/cuda12_windows.md)**
+- **[CUDA 13 Windows 依赖指南](install/cuda13_windows.md)**
+
+---
+
+
+## 🎙️ 推理测试与模式说明
+
+编译完成后，可执行程序位于 `./build/qwen3-tts-cli.exe`。
+> [!NOTE]
+> - Linux/macOS 系统请使用 `./build/qwen3-tts-cli` 运行。
+> - `--instruct` 仅对 **Custom** 和 **Design** 模式有效（Base 模式下禁用）。
+
+详细教程请参阅：**[CLI 指令使用指南](guide/usage_tutorial.md)**。
+
+### 1. 声音克隆 (Voice Cloning)
+通过参考音频（.wav）或预计算特征（.json）模仿特定音色：
+```bash
+./build/qwen3-tts-cli.exe `
+  -m models/base_small `
+  -r ref/ref_0.6B.json `
+  -t "Okay, fine, I'm just gonna leave this sock monkey here. Goodbye." `
+  -o output/cloned.wav
+```
+
+### 2. 定制化声音 (Custom Voice)
+使用系统内置的发音人 ID：
+```bash
+./build/qwen3-tts-cli.exe `
+  -m models/custom `
+  --speaker Vivian `
+  --instruct "Use angry tone." `
+  -t "She said she would be here by noon." `
+  -o output/custom.wav
+```
+
+### 3. 声音设计 (Voice Design)
+使用描述设计声音
+```bash
+.\build\qwen3-tts-cli.exe `
+  -m models/design `
+  -t "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!" `
+  --instruct "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice."
+  -o output/out.wav `
+
+---
+
+## 📈 性能监控与日志
+
+- **详细统计**: 运行命令时添加 `--stats-json report.json` 即可获取 RTF（实时率）和内存占用分析。
+- **日志查看**: 所有的构建和运行输出均实时记录在 `../../logs/latest.log` 中。
+- **线程控制**: 使用 `-j` 参数（默认 4）调整 CPU 线程使用。
+
+---
+
+## 📜 更多信息
+
+有关运行时详细配置及设计准则，请参阅:
+- **[LunaVox CLI 指令汇总手册](guide/cli_reference.md)**
+- **[运行时技术规范与约束](technical/runtime_specs.md)**
+- **[合成链路编码器需求分析](technical/synthesis_pathway.md)**
+
+---
+
+## 🙏 致谢
+
+本项目深受以下开源项目的启发或基于其成果：
+
+- **[Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS)**: 提供强大的 base 模型权重与原始架构设计。
+- **[onnxruntime](https://github.com/microsoft/onnxruntime)**: 驱动高性能音频解码后端。
+- **[llama.cpp](https://github.com/ggml-org/llama.cpp)**: 驱动 LLM 序列预测核心。

lunavox-2.0.0/pyproject.toml

@@ -0,0 +1,60 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "lunavox"
+version = "2.0.0"
+description = "LunaVox tooling CLI for model setup, conversion, quantization, and build workflows."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "MIT" }
+authors = [{ name = "LunaVox Contributors" }]
+dependencies = [
+  "typer>=0.12.0",
+  "rich>=13.7.0",
+  "huggingface_hub>=0.24.0",
+]
+
+[project.optional-dependencies]
+gui = [
+  "customtkinter>=5.2.0",
+  "pygame>=2.5.0",
+]
+convert = [
+  "torch>=2.1",
+  "torchaudio>=2.1",
+  "transformers==4.57.6",
+  "accelerate==1.12.0",
+  "onnx",
+  "onnxruntime",
+  "onnxruntime-tools",
+  "gguf",
+  "numpy",
+  "tqdm",
+  "safetensors",
+  "sentencepiece",
+  "librosa",
+  "scipy",
+  "soundfile",
+  "einops",
+  "onnxscript",
+]
+dev = [
+  "pytest>=8.2",
+  "build>=1.2",
+  "twine>=5.1",
+]
+
+[project.scripts]
+lunavox = "lunavox.cli.main:run"
+
+[tool.setuptools]
+package-dir = { "" = "src" }
+include-package-data = true
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+"lunavox.build" = ["*.json"]

lunavox-2.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+