tckm.yan/aha
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore(docs): restructure README files and add Chinese documentation

Browse Source
This commit is contained in:
XiaoYang
2026-02-06 16:39:52 +08:00
parent c582c4cd0a
commit 746dd1491c
3 changed files with 314 additions and 327 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.en.md
-228
View File
@@ -1,228 +0,0 @@
<p align="center">
<img src="assets/img/logo.png" alt="aha logo" width="100"/>
</p>
<p align="center">
<!-- <a href="https://github.com/jhqxxx/aha/releases">
<img src="https://img.shields.io/github/v/release/jhqxxx/aha" alt="GitHub release (latest by date)">
</a>
<a href="https://github.com/jhqxxx/aha/actions">
<img src="https://img.shields.io/github/actions/workflow/status/jhqxxx/aha/ci.yml" alt="GitHub Actions Workflow Status">
</a> -->
<a href="https://github.com/jhqxxx/aha/blob/main/LICENSE">
<img src="https://img.shields.io/github/license/jhqxxx/aha" alt="GitHub License">
</a>
<a href="https://github.com/jhqxxx/aha/stargazers">
<img src="https://img.shields.io/github/stars/jhqxxx/aha" alt="GitHub Stars">
</a>
<a href="https://github.com/jhqxxx/aha/issues">
<img src="https://img.shields.io/github/issues/jhqxxx/aha" alt="GitHub Issues">
</a>
</p>
<p align="center">
<a href="README.md">简体中文</a> | <strong>English</strong>
</p>
# aha
**Lightweight AI Inference Engine — All-in-one Solution for Text, Vision, Speech, and OCR**
aha is a high-performance, cross-platform AI inference engine built with Rust and the Candle framework. It brings state-of-the-art AI models to your local machine—no API keys, no cloud dependencies, just pure, fast AI running directly on your hardware.
## Changelog
### v0.2.0 (2026-02-05)
- Added Qwen3-ASR speech recognition model
### v0.1.9 (2026-01-31)
- Added CLI `list` subcommand to show supported models
- Added CLI subcommand structure support (`cli`, `serv`, `download`, `run`)
- Fixed Qwen3VL thinking startswith bug
- Fixed `aha run` multiple inputs bug
### v0.1.8 (2026-01-17)
- Added Qwen3 text model support
- Added Fun-ASR-Nano-2512 speech recognition model
- Fixed ModelScope Fun-ASR-Nano model load error
- Updated audio resampling with rubato
### v0.1.7 (2026-01-07)
- Added GLM-ASR-Nano-2512 speech recognition model
- Merged Metal (GPU) support for Apple Silicon
- Added dynamic home directory and model download script
**[View full changelog](docs/changelog.md)** →
## Quick Start
### Installation
```bash
git clone https://github.com/jhqxxx/aha.git
cd aha
cargo build --release
```
**Optional Features:**
```bash
# CUDA (NVIDIA GPU acceleration)
cargo build --release --features cuda
# Metal (Apple GPU acceleration for macOS)
cargo build --release --features metal
# Flash Attention (faster inference)
cargo build --release --features flash-attn
# FFmpeg (multimedia processing)
cargo build --release --features ffmpeg
# Combine multiple features
cargo build --release --features "cuda,flash-attn"
```
### CLI Quick Reference
```bash
# List all supported models
aha list
# Download model only
aha download -m qwen3asr-0.6b
# Download model and start service
aha -m qwen3asr-0.6b
# Run inference directly (without starting service)
aha run -m qwen3asr-0.6b -i "audio.wav"
# Start service only (model already downloaded)
aha serv -m qwen3asr-0.6b -p 10100
```
### Chat
```bash
aha serv -m qwen3-0.6b -p 10100
```
Then use the unified (OpenAI-compatible) API:
```bash
curl http://localhost:10100/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-0.6b",
"messages": [{"role": "user", "content": "Hello!"}]
}
'
```
### Supported Models
| Category | Models |
|----------|--------|
| **Text** | Qwen3, MiniCPM4 |
| **Vision** | Qwen2.5-VL, Qwen3-VL |
| **OCR** | DeepSeek-OCR, Hunyuan-OCR, PaddleOCR-VL |
| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR |
| **Audio** | VoxCPM, VoxCPM1.5 |
| **Image** | RMBG-2.0 (background removal) |
## Documentation
| Document | Description |
|----------|-------------|
| [Getting Started](docs/getting-started.md) | First steps with aha |
| [Installation](docs/installation.md) | Detailed installation guide |
| [CLI Reference](docs/cli.md) | Command-line interface |
| [API Documentation](docs/api.md) | Library & REST API |
| [Supported Models](docs/supported-models.md) | Available AI models |
| [Concepts](docs/concepts.md) | Architecture & design |
| [Development](docs/development.md) | Contributing guide |
| [Changelog](docs/changelog.md) | Version history |
## Why aha?
- **🚀 High-Performance Inference** - Powered by Candle framework for efficient tensor computation and model inference
- **🔧 Unified Interface** — One tool for text, vision, speech, and OCR
- **📦 Local-First** — All processing runs locally, no data leaves your machine
- **🎯 Cross-Platform** — Works on Linux, macOS, and Windows
- **⚡ GPU Accelerated** — Optional CUDA support for faster inference
- **🛡️ Memory Safe** — Built with Rust for reliability
- **🧠 Attention Optimization** - Optional Flash Attention support for optimized long sequence processing
## Development
### Using aha as a Library
> cargo add aha
```bash
# VoxCPM example
use aha::models::voxcpm::generate::VoxCPMGenerate;
use aha::utils::audio_utils::save_wav;
use anyhow::Result;
fn main() -> Result<()> {
let model_path = "xxx/openbmb/VoxCPM-0.5B/";
let mut voxcpm_generate = VoxCPMGenerate::init(model_path, None, None)?;
let generate = voxcpm_generate.generate(
"The sun is shining bright, flowers smile at me, birds say early early early".to_string(),
None,
None,
2,
100,
10,
2.0,
false,
6.0,
)?;
let _ = save_wav(&generate, "voxcpm.wav")?;
Ok(())
}
```
### Extending New Models
- Create new model file in src/models/
- Export in src/models/mod.rs
- Add support for CLI model inference in src/exec/
- Add tests and examples in tests/
## Features
- High-performance inference via Candle framework
- Multi-modal model support (vision, language, speech)
- Clean, easy-to-use API design
- Minimal dependencies, compact binaries
- Flash Attention support for long sequences
- FFmpeg support for multimedia processing
## License
Apache-2.0 &mdash; See [LICENSE](LICENSE) for details.
## Acknowledgments
- [Candle](https://github.com/huggingface/candle) - Excellent Rust ML framework
- All model authors and contributors
---
<p align="center">
<sub>Built with ❤️ by the aha team</sub>
</p>
<p align="center">
<sub>We're continuously expanding our model support. Contributions are welcome!</sub>
</p>
<p align="center">
<sub>If this project helps you, please consider giving us a ⭐ Star!</sub>
</p>
README.md
+87 -96
View File
@@ -1,14 +1,8 @@
<p align="center"> <p align="center">
<img src="assets/img/logo.png" alt="aha logo" width="100"/> <img src="assets/img/logo.png" alt="aha logo" width="120"/>
</p> </p>
<p align="center"> <p align="center">
<!-- <a href="https://github.com/jhqxxx/aha/releases">
<img src="https://img.shields.io/github/v/release/jhqxxx/aha" alt="GitHub release (latest by date)">
</a>
<a href="https://github.com/jhqxxx/aha/actions">
<img src="https://img.shields.io/github/actions/workflow/status/jhqxxx/aha/ci.yml" alt="GitHub Actions Workflow Status">
</a> -->
<a href="https://github.com/jhqxxx/aha/blob/main/LICENSE"> <a href="https://github.com/jhqxxx/aha/blob/main/LICENSE">
<img src="https://img.shields.io/github/license/jhqxxx/aha" alt="GitHub License"> <img src="https://img.shields.io/github/license/jhqxxx/aha" alt="GitHub License">
</a> </a>
@@ -21,42 +15,42 @@
</p> </p>
<p align="center"> <p align="center">
<a href="README.en.md">English</a> | <strong>简体中文</a> <a href="README.zh-CN.md">简体中文</a> | <strong>English</strong>
</p> </p>
# aha # aha
**轻量 AI 推理引擎 —— 文本、视觉、语音与 OCR 一站式解决方案** **Lightweight AI Inference Engine — All-in-one Solution for Text, Vision, Speech, and OCR**
aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理引擎。将最先进的 AI 模型带到您的本地机器——无需 API 密钥，无需云依赖，纯粹、快速的 AI 直接在您的硬件上运行。 aha is a high-performance, cross-platform AI inference engine built with Rust and the Candle framework. It brings state-of-the-art AI models to your local machine—no API keys, no cloud dependencies, just pure, fast AI running directly on your hardware.
## 更新日志 ## Changelog
### v0.2.0 (2026-02-05) ### v0.2.0 (2026-02-05)
- 新增 Qwen3-ASR 语音识别模型 - Added Qwen3-ASR speech recognition model
### v0.1.9 (2026-01-31) ### v0.1.9 (2026-01-31)
- 新增 CLI `list` 子命令，显示支持的模型 - Added CLI `list` subcommand to show supported models
- 新增 CLI 子命令结构支持（`cli`、`serv`、`download`、`run`） - Added CLI subcommand structure support (`cli`, `serv`, `download`, `run`)
- 修复 Qwen3VL thinking startswith bug - Fixed Qwen3VL thinking startswith bug
- 修复 `aha run` 多输入 bug - Fixed `aha run` multiple inputs bug
### v0.1.8 (2026-01-17) ### v0.1.8 (2026-01-17)
- 新增 Qwen3 文本模型支持 - Added Qwen3 text model support
- 新增 Fun-ASR-Nano-2512 语音识别模型 - Added Fun-ASR-Nano-2512 speech recognition model
- 修复 ModelScope Fun-ASR-Nano 模型加载错误 - Fixed ModelScope Fun-ASR-Nano model load error
- 使用 rubato 更新音频重采样 - Updated audio resampling with rubato
### v0.1.7 (2026-01-07) ### v0.1.7 (2026-01-07)
- 新增 GLM-ASR-Nano-2512 语音识别模型 - Added GLM-ASR-Nano-2512 speech recognition model
- 合并 Metal (GPU) 支持，适用于 Apple Silicon - Merged Metal (GPU) support for Apple Silicon
- 新增动态主目录和模型下载脚本 - Added dynamic home directory and model download script
**[查看完整更新日志](docs/changelog.zh-CN.md)** → **[View full changelog](docs/changelog.md)** →
## 快速开始 ## Quick Start
### 安装 ### Installation
```bash ```bash
git clone https://github.com/jhqxxx/aha.git git clone https://github.com/jhqxxx/aha.git
@@ -64,104 +58,104 @@ cd aha
cargo build --release cargo build --release
``` ```
**可选特性：** **Optional Features:**
```bash ```bash
# CUDA (NVIDIA GPU 加速) # CUDA (NVIDIA GPU acceleration)
cargo build --release --features cuda cargo build --release --features cuda
# Metal (Apple GPU 加速，适用于 macOS) # Metal (Apple GPU acceleration for macOS)
cargo build --release --features metal cargo build --release --features metal
# Flash Attention (更快推理) # Flash Attention (faster inference)
cargo build --release --features flash-attn cargo build --release --features flash-attn
# FFmpeg (多媒体处理) # FFmpeg (multimedia processing)
cargo build --release --features ffmpeg cargo build --release --features ffmpeg
# 组合多个特性 # Combine multiple features
cargo build --release --features "cuda,flash-attn" cargo build --release --features "cuda,flash-attn"
``` ```
### CLI 快速参考 ### CLI Quick Reference
```bash ```bash
# 列出所有支持的模型 # List all supported models
aha list aha list
# 仅下载模型 # Download model only
aha download -m qwen3asr-0.6b aha download -m qwen3asr-0.6b
# 下载模型并启动服务 # Download model and start service
aha -m qwen3asr-0.6b aha -m qwen3asr-0.6b
# 直接运行推理（无需启动服务） # Run inference directly (without starting service)
aha run -m qwen3asr-0.6b -i "audio.wav" aha run -m qwen3asr-0.6b -i "audio.wav"
# 仅启动服务（模型已下载） # Start service only (model already downloaded)
aha serv -m qwen3asr-0.6b -p 10100 aha serv -m qwen3asr-0.6b -p 10100
``` ```
### 对话 ### Chat
```bash ```bash
aha serv -m qwen3-0.6b -p 10100 aha serv -m qwen3-0.6b -p 10100
``` ```
然后使用统一(兼容 OpenAI)的 API： Then use the unified (OpenAI-compatible) API:
```bash ```bash
curl http://localhost:10100/chat/completions \ curl http://localhost:10100/chat/completions \
-H "Content-Type: application/json" \ -H "Content-Type: application/json" \
-d '{ -d '{
"model": "qwen3-0.6b", "model": "qwen3-0.6b",
"messages": [{"role": "user", "content": "你好！"}] "messages": [{"role": "user", "content": "Hello!"}]
}' }
'
``` ```
### Supported Models
### 支持的模型 | Category | Models |
|----------|--------|
| 类别 | 模型 | | **Text** | Qwen3, MiniCPM4 |
|------|------| | **Vision** | Qwen2.5-VL, Qwen3-VL |
| **文本** | Qwen3, MiniCPM4 |
| **视觉** | Qwen2.5-VL, Qwen3-VL |
| **OCR** | DeepSeek-OCR, Hunyuan-OCR, PaddleOCR-VL | | **OCR** | DeepSeek-OCR, Hunyuan-OCR, PaddleOCR-VL |
| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR | | **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR |
| **音频** | VoxCPM, VoxCPM1.5 | | **Audio** | VoxCPM, VoxCPM1.5 |
| **图像** | RMBG-2.0 (背景移除) | | **Image** | RMBG-2.0 (background removal) |
## 文档 ## Documentation
| 文档 | 描述 | | Document | Description |
|------|------| |----------|-------------|
| [快速入门](docs/getting-started.zh-CN.md) | aha 入门指南 | | [Getting Started](docs/getting-started.md) | First steps with aha |
| [安装指南](docs/installation.zh-CN.md) | 详细安装说明 | | [Installation](docs/installation.md) | Detailed installation guide |
| [CLI 参考](docs/cli.zh-CN.md) | 命令行界面 | | [CLI Reference](docs/cli.md) | Command-line interface |
| [API 文档](docs/api.zh-CN.md) | 库与 REST API | | [API Documentation](docs/api.md) | Library & REST API |
| [支持的模型](docs/supported-models.zh-CN.md) | 可用的 AI 模型 | | [Supported Models](docs/supported-models.md) | Available AI models |
| [核心概念](docs/concepts.zh-CN.md) | 架构与设计 | | [Concepts](docs/concepts.md) | Architecture & design |
| [开发指南](docs/development.zh-CN.md) | 贡献指南 | | [Development](docs/development.md) | Contributing guide |
| [更新日志](docs/changelog.zh-CN.md) | 版本历史 | | [Changelog](docs/changelog.md) | Version history |
## 为什么选择 aha？ ## Why aha?
- **🚀 高性能推理** - 基于 Candle 框架，提供高效的张量计算和模型推理 - **🚀 High-Performance Inference** - Powered by Candle framework for efficient tensor computation and model inference
- **🔧 统一接口** — 一个工具搞定文本、视觉、语音和 OCR - **🔧 Unified Interface** — One tool for text, vision, speech, and OCR
- **📦 本地优先** — 所有处理在本地运行，数据不离境 - **📦 Local-First** — All processing runs locally, no data leaves your machine
- **🎯 跨平台** — 支持 Linux、macOS 和 Windows - **🎯 Cross-Platform** — Works on Linux, macOS, and Windows
- **⚡ GPU 加速** — 可选 CUDA 支持以获得更快推理 - **⚡ GPU Accelerated** — Optional CUDA support for faster inference
- **🛡️ 内存安全** — Rust 构建，稳定可靠 - **🛡️ Memory Safe** — Built with Rust for reliability
- **🧠 注意力优化** - 可选 Flash Attention 支持，优化长序列处理 - **🧠 Attention Optimization** - Optional Flash Attention support for optimized long sequence processing
## 开发 ## Development
### aha 作为库使用 ### Using aha as a Library
> cargo add aha > cargo add aha
```bash ```bash
# VoxCPM示例 # VoxCPM example
use aha::models::voxcpm::generate::VoxCPMGenerate; use aha::models::voxcpm::generate::VoxCPMGenerate;
use aha::utils::audio_utils::save_wav; use aha::utils::audio_utils::save_wav;
use anyhow::Result; use anyhow::Result;
@@ -172,7 +166,7 @@ fn main() -> Result<()> {
let mut voxcpm_generate = VoxCPMGenerate::init(model_path, None, None)?; let mut voxcpm_generate = VoxCPMGenerate::init(model_path, None, None)?;
let generate = voxcpm_generate.generate( let generate = voxcpm_generate.generate(
"太阳当空照，花儿对我笑，小鸟说早早早".to_string(), "The sun is shining bright, flowers smile at me, birds say early early early".to_string(),
None, None,
None, None,
2, 2,
@@ -188,43 +182,40 @@ fn main() -> Result<()> {
} }
``` ```
### Extending New Models
### 扩展新的模型 - Create new model file in src/models/
- Export in src/models/mod.rs
- Add support for CLI model inference in src/exec/
- Add tests and examples in tests/
- 在src/models/创建新模型文件 ## Features
- 在src/models/mod.rs中导出
- 在src/exec/中添加支持cli运行模型推理
- 在tests/中添加测试和示例
- High-performance inference via Candle framework
- Multi-modal model support (vision, language, speech)
- Clean, easy-to-use API design
- Minimal dependencies, compact binaries
- Flash Attention support for long sequences
- FFmpeg support for multimedia processing
## 特性 ## License
- 基于 Candle 框架的高性能推理 Apache-2.0 &mdash; See [LICENSE](LICENSE) for details.
- 多模态模型支持（视觉、语言、语音）
- 简洁易用的 API 设计
- 最小化依赖，紧凑的二进制文件
- Flash Attention 支持长序列处理
- FFmpeg 支持多媒体处理
## 许可证 ## Acknowledgments
Apache-2.0 &mdash; 详见 [LICENSE](LICENSE) - [Candle](https://github.com/huggingface/candle) - Excellent Rust ML framework
- All model authors and contributors
## 致谢
- [Candle](https://github.com/huggingface/candle) - 优秀的 Rust 机器学习框架
- 所有模型作者和贡献者
--- ---
<p align="center"> <p align="center">
<sub>由 aha 团队用 ❤️ 构建</sub> <sub>Built with ❤️ by the aha team</sub>
</p> </p>
<p align="center"> <p align="center">
<sub>我们持续扩展支持的模型列表，欢迎贡献！</sub> <sub>We're continuously expanding our model support. Contributions are welcome!</sub>
</p> </p>
<p align="center"> <p align="center">
<sub>如果这个项目对你有帮助，请给我们一个 ⭐ Star！</sub> <sub>If this project helps you, please consider giving us a ⭐ Star!</sub>
</p> </p>
README.zh-CN.md
+224
View File
@@ -0,0 +1,224 @@
<p align="center">
<img src="assets/img/logo.png" alt="aha logo" width="120"/>
</p>
<p align="center">
<a href="https://github.com/jhqxxx/aha/blob/main/LICENSE">
<img src="https://img.shields.io/github/license/jhqxxx/aha" alt="GitHub License">
</a>
<a href="https://github.com/jhqxxx/aha/stargazers">
<img src="https://img.shields.io/github/stars/jhqxxx/aha" alt="GitHub Stars">
</a>
<a href="https://github.com/jhqxxx/aha/issues">
<img src="https://img.shields.io/github/issues/jhqxxx/aha" alt="GitHub Issues">
</a>
</p>
<p align="center">
<a href="README.md">English</a> | <strong>简体中文</strong>
</p>
# aha
**轻量 AI 推理引擎 —— 文本、视觉、语音与 OCR 一站式解决方案**
aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理引擎。将最先进的 AI 模型带到您的本地机器——无需 API 密钥，无需云依赖，纯粹、快速的 AI 直接在您的硬件上运行。
## 更新日志
### v0.2.0 (2026-02-05)
- 新增 Qwen3-ASR 语音识别模型
### v0.1.9 (2026-01-31)
- 新增 CLI `list` 子命令，显示支持的模型
- 新增 CLI 子命令结构支持（`cli`、`serv`、`download`、`run`）
- 修复 Qwen3VL thinking startswith bug
- 修复 `aha run` 多输入 bug
### v0.1.8 (2026-01-17)
- 新增 Qwen3 文本模型支持
- 新增 Fun-ASR-Nano-2512 语音识别模型
- 修复 ModelScope Fun-ASR-Nano 模型加载错误
- 使用 rubato 更新音频重采样
### v0.1.7 (2026-01-07)
- 新增 GLM-ASR-Nano-2512 语音识别模型
- 合并 Metal (GPU) 支持，适用于 Apple Silicon
- 新增动态主目录和模型下载脚本
**[查看完整更新日志](docs/changelog.zh-CN.md)** →
## 快速开始
### 安装
```bash
git clone https://github.com/jhqxxx/aha.git
cd aha
cargo build --release
```
**可选特性：**
```bash
# CUDA (NVIDIA GPU 加速)
cargo build --release --features cuda
# Metal (Apple GPU 加速，适用于 macOS)
cargo build --release --features metal
# Flash Attention (更快推理)
cargo build --release --features flash-attn
# FFmpeg (多媒体处理)
cargo build --release --features ffmpeg
# 组合多个特性
cargo build --release --features "cuda,flash-attn"
```
### CLI 快速参考
```bash
# 列出所有支持的模型
aha list
# 仅下载模型
aha download -m qwen3asr-0.6b
# 下载模型并启动服务
aha -m qwen3asr-0.6b
# 直接运行推理（无需启动服务）
aha run -m qwen3asr-0.6b -i "audio.wav"
# 仅启动服务（模型已下载）
aha serv -m qwen3asr-0.6b -p 10100
```
### 对话
```bash
aha serv -m qwen3-0.6b -p 10100
```
然后使用统一(兼容 OpenAI)的 API：
```bash
curl http://localhost:10100/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-0.6b",
"messages": [{"role": "user", "content": "你好！"}]
}'
```
### 支持的模型
| 类别 | 模型 |
|------|------|
| **文本** | Qwen3, MiniCPM4 |
| **视觉** | Qwen2.5-VL, Qwen3-VL |
| **OCR** | DeepSeek-OCR, Hunyuan-OCR, PaddleOCR-VL |
| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano,Qwen3-ASR |
| **音频** | VoxCPM, VoxCPM1.5 |
| **图像** | RMBG-2.0 (背景移除) |
## 文档
| 文档 | 描述 |
|------|------|
| [快速入门](docs/getting-started.zh-CN.md) | aha 入门指南 |
| [安装指南](docs/installation.zh-CN.md) | 详细安装说明 |
| [CLI 参考](docs/cli.zh-CN.md) | 命令行界面 |
| [API 文档](docs/api.zh-CN.md) | 库与 REST API |
| [支持的模型](docs/supported-models.zh-CN.md) | 可用的 AI 模型 |
| [核心概念](docs/concepts.zh-CN.md) | 架构与设计 |
| [开发指南](docs/development.zh-CN.md) | 贡献指南 |
| [更新日志](docs/changelog.zh-CN.md) | 版本历史 |
## 为什么选择 aha？
- **🚀 高性能推理** - 基于 Candle 框架，提供高效的张量计算和模型推理
- **🔧 统一接口** — 一个工具搞定文本、视觉、语音和 OCR
- **📦 本地优先** — 所有处理在本地运行，数据不离境
- **🎯 跨平台** — 支持 Linux、macOS 和 Windows
- **⚡ GPU 加速** — 可选 CUDA 支持以获得更快推理
- **🛡️ 内存安全** — Rust 构建，稳定可靠
- **🧠 注意力优化** - 可选 Flash Attention 支持，优化长序列处理
## 开发
### aha 作为库使用
> cargo add aha
```bash
# VoxCPM示例
use aha::models::voxcpm::generate::VoxCPMGenerate;
use aha::utils::audio_utils::save_wav;
use anyhow::Result;
fn main() -> Result<()> {
let model_path = "xxx/openbmb/VoxCPM-0.5B/";
let mut voxcpm_generate = VoxCPMGenerate::init(model_path, None, None)?;
let generate = voxcpm_generate.generate(
"太阳当空照，花儿对我笑，小鸟说早早早".to_string(),
None,
None,
2,
100,
10,
2.0,
false,
6.0,
)?;
let _ = save_wav(&generate, "voxcpm.wav")?;
Ok(())
}
```
### 扩展新的模型
- 在src/models/创建新模型文件
- 在src/models/mod.rs中导出
- 在src/exec/中添加支持cli运行模型推理
- 在tests/中添加测试和示例
## 特性
- 基于 Candle 框架的高性能推理
- 多模态模型支持（视觉、语言、语音）
- 简洁易用的 API 设计
- 最小化依赖，紧凑的二进制文件
- Flash Attention 支持长序列处理
- FFmpeg 支持多媒体处理
## 许可证
Apache-2.0 &mdash; 详见 [LICENSE](LICENSE)
## 致谢
- [Candle](https://github.com/huggingface/candle) - 优秀的 Rust 机器学习框架
- 所有模型作者和贡献者
---
<p align="center">
<sub>由 aha 团队用 ❤️ 构建</sub>
</p>
<p align="center">
<sub>我们持续扩展支持的模型列表，欢迎贡献！</sub>
</p>
<p align="center">
<sub>如果这个项目对你有帮助，请给我们一个 ⭐ Star！</sub>
</p>