update readme

2026-05-11 16:23:38 +08:00
parent a14b9e1e90
commit 8f1cbbbf8d
4 changed files with 30 additions and 45 deletions
@@ -38,17 +38,10 @@ aha is a high-performance, cross-platform AI inference engine built with Rust an
 | **Embedding** | Qwen3-Embedding, all-MiniLM-L6-v2 |
 | **Reranker** | Qwen3-Reranker |

-
-## 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
-
 ## Changelog
+### 2026-05-11
+- add Moss-TTS-Nano，its performance is worse than the original Python version
+
 ### 2026-05-09
 - merge pr/eastgold15/46, add aha-ui

@@ -61,21 +54,16 @@ aha is a high-performance, cross-platform AI inference engine built with Rust an
 ### 2026-04-16
 - fix FireRedVAD fsmn cache bug

-### 2026-04-15
- add FireRedVAD
-
-### 2026-04-10
- fix LiquidAI/LFM2.5-VL-450M chat_template load bug
-
-### 2026-04-08
- add VoxCPM2
-
-### 0.2.5 (2026-04-06)
- add qwen3-embedding/qwen3-reranker/all-minilm-l6-v2
-
-
 **[View full changelog](docs/changelog.md)** →

+## 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

 ## Quick Start

@@ -32,21 +32,15 @@ aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理
 | **视觉** | Qwen2.5-VL, Qwen3-VL, Qwen3.5 <br> LFM2.5-VL, LFM2-VL |
 | **OCR** | DeepSeek-OCR, DeepSeek-OCR-2, PaddleOCR-VL,  <br>PaddleOCR-VL1.5, Hunyuan-OCR, GLM-OCR |
 | **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR |
-| **TTS** | VoxCPM, VoxCPM1.5, VoxCPM2 |
+| **TTS** | VoxCPM, VoxCPM1.5, VoxCPM2, Moss-TTS-Nano |
 | **图像** | RMBG-2.0 (背景移除) |
 | **嵌入** | Qwen3-Embedding, all-MiniLM-L6-v2 |
 | **重排序** | Qwen3-Reranker |

-## 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
-
 ## 更新日志
+### 2026-05-11
+- 添加Moss-TTS-Nano，该模型比较小，计算误差影响较大，效果比python原版差
+
 ### 2026-05-09
 - 合并 pr/eastgold15/46, 添加 aha-ui

@@ -59,21 +53,18 @@ aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理
 ### 2026-04-16
 - 修复 FireRedVAD fsmn 缓存问题

-### 2026-04-15
- 添加 FireRedVAD
-
-### 2026-04-10
- 修复 LiquidAI/LFM2.5-VL-450M chat_template 加载bug
-
-### 2026-04-08
- 添加 VoxCPM2
-
-### 0.2.5 (2026-04-06)
- 添加 qwen3-embedding/qwen3-reranker/all-minilm-l6-v2
-
 **[查看完整更新日志](docs/changelog.zh-CN.md)** →


+## 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
+
 ## 快速开始

 ### 安装
@@ -5,6 +5,9 @@ All notable changes to aha will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

+### 2026-05-11
+- add Moss-TTS-Nano，its performance is worse than the original Python version
+
 ### 2026-05-09
 - merge pr/eastgold15/46, add aha-ui

@@ -5,6 +5,9 @@
 格式基于 [Keep a Changelog](https://keepachangelog.com/zh-CN/1.0.0/)，
 本项目遵循 [语义化版本](https://semver.org/lang/zh-CN/spec/v2.0.0.html)。

+### 2026-05-11
+- 添加Moss-TTS-Nano，该模型比较小，计算误差影响较大，效果比python原版差
+
 ### 2026-05-09
 - 合并 pr/eastgold15/46, 添加 aha-ui