Instructions to use MoYoYoTech/VoiceDialogue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MoYoYoTech/VoiceDialogue with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="MoYoYoTech/VoiceDialogue") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MoYoYoTech/VoiceDialogue", dtype="auto") - llama-cpp-python
How to use MoYoYoTech/VoiceDialogue with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="MoYoYoTech/VoiceDialogue", filename="assets/models/llm/qwen/Qwen3-8B-Q6_K.gguf", )
llm.create_chat_completion( messages = "\"The answer to the universe is 42\"" )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use MoYoYoTech/VoiceDialogue with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf MoYoYoTech/VoiceDialogue:Q6_K # Run inference directly in the terminal: llama cli -hf MoYoYoTech/VoiceDialogue:Q6_K
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf MoYoYoTech/VoiceDialogue:Q6_K # Run inference directly in the terminal: llama cli -hf MoYoYoTech/VoiceDialogue:Q6_K
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K # Run inference directly in the terminal: ./llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K # Run inference directly in the terminal: ./build/bin/llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K
Use Docker
docker model run hf.co/MoYoYoTech/VoiceDialogue:Q6_K
- LM Studio
- Jan
- Ollama
How to use MoYoYoTech/VoiceDialogue with Ollama:
ollama run hf.co/MoYoYoTech/VoiceDialogue:Q6_K
- Unsloth Studio
How to use MoYoYoTech/VoiceDialogue with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MoYoYoTech/VoiceDialogue to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MoYoYoTech/VoiceDialogue to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for MoYoYoTech/VoiceDialogue to start chatting
- Pi
How to use MoYoYoTech/VoiceDialogue with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf MoYoYoTech/VoiceDialogue:Q6_K
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "MoYoYoTech/VoiceDialogue:Q6_K" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use MoYoYoTech/VoiceDialogue with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf MoYoYoTech/VoiceDialogue:Q6_K
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default MoYoYoTech/VoiceDialogue:Q6_K
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use MoYoYoTech/VoiceDialogue with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf MoYoYoTech/VoiceDialogue:Q6_K
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "MoYoYoTech/VoiceDialogue:Q6_K" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use MoYoYoTech/VoiceDialogue with Docker Model Runner:
docker model run hf.co/MoYoYoTech/VoiceDialogue:Q6_K
- Lemonade
How to use MoYoYoTech/VoiceDialogue with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MoYoYoTech/VoiceDialogue:Q6_K
Run and chat with the model
lemonade run user.VoiceDialogue-Q6_K
List all available models
lemonade list
README: fix model-download instructions for clone install
Browse filesThe repo no longer bundles the ASR model: Qwen3-ASR is now the default
and is downloaded from HuggingFace on first launch. The old README
claimed 'all models bundled via Git LFS, no download needed', which
contradicted the auto-download step and left fresh-clone users stuck.
- Split models into 'bundled via LFS (~12GB)' vs 'Qwen3-ASR auto-
downloaded (~4.4GB) on first run'
- Require + verify Git LFS (clone yields pointer files otherwise)
- Correct first-launch note (4.4GB, prints progress, needs network)
- Add a DMG section for the fully-offline prebuilt installer
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
@@ -54,27 +54,40 @@ VoiceDialogue 是一个基于 Python 的完整语音对话系统,实现了端
|
|
| 54 |
|
| 55 |
### 1. 克隆并安装
|
| 56 |
|
| 57 |
-
>
|
| 58 |
-
>
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
```bash
|
| 61 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
git clone https://huggingface.co/MoYoYoTech/VoiceDialogue
|
| 63 |
cd VoiceDialogue
|
| 64 |
|
| 65 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
pip install uv
|
| 67 |
uv venv
|
| 68 |
source .venv/bin/activate
|
| 69 |
|
| 70 |
WHISPER_COREML=1 CMAKE_ARGS="-DGGML_METAL=on" uv sync
|
| 71 |
|
| 72 |
-
# 安装额外依赖
|
| 73 |
uv pip install kokoro-onnx # kokoro-onnx(英文 TTS)
|
| 74 |
uv pip install numpy==1.26.4 # 固定 numpy 版本
|
| 75 |
```
|
| 76 |
|
| 77 |
> 📖 需要更详细的步骤?请查阅 [安装指南](docs/installation.md),其中包含系统要求和常见问题。
|
|
|
|
|
|
|
| 78 |
|
| 79 |
### 2. 启动图形界面(推荐)
|
| 80 |
|
|
@@ -89,7 +102,8 @@ python main.py --mode api
|
|
| 89 |
- 点击右下角 **⚙️ 设置**,选择**麦克风、回音消除、识别语言、音色**,也可切换**中 / 英界面语言**;
|
| 90 |
- 点击 **「开始对话」**,即可与 AI 实时语音对话,**字幕会实时显示**。
|
| 91 |
|
| 92 |
-
> 首次启动会自动下载 Qwen3-ASR 模型(约
|
|
|
|
| 93 |
|
| 94 |
### 3. 命令行模式(CLI)
|
| 95 |
|
|
@@ -111,6 +125,20 @@ python main.py --input-device <设备索引>
|
|
| 111 |
|
| 112 |
> 详细使用方法请参考 [配置指南](docs/configuration.md) 和 [API 服务指南](docs/api-guide.md)。
|
| 113 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
## 📚 文档导航
|
| 115 |
|
| 116 |
- 📖 **[安装指南](docs/installation.md)**: 详细的安装步骤和系统要求。
|
|
|
|
| 54 |
|
| 55 |
### 1. 克隆并安装
|
| 56 |
|
| 57 |
+
> **模型分两部分**:
|
| 58 |
+
> - **随仓库下载(约 12GB,Git LFS)**:大语言模型、语音合成、参考音色等。
|
| 59 |
+
> - **首次启动自动下载(约 4.4GB)**:语音识别引擎 **Qwen3-ASR**,由程序在第一次运行时从 HuggingFace 拉取并缓存到 `~/.cache/huggingface`,之后无需重复下载。
|
| 60 |
+
>
|
| 61 |
+
> ⚠️ **必须先安装 [Git LFS](https://git-lfs.com)**,否则克隆下来的模型只是几百字节的占位指针,应用无法启动。
|
| 62 |
|
| 63 |
```bash
|
| 64 |
+
# 1) 安装并初始化 Git LFS(只需一次)
|
| 65 |
+
brew install git-lfs # 如未安装 Homebrew,见 https://git-lfs.com
|
| 66 |
+
git lfs install
|
| 67 |
+
|
| 68 |
+
# 2) 克隆项目(包含约 12GB 模型,体积较大,请耐心等待)
|
| 69 |
git clone https://huggingface.co/MoYoYoTech/VoiceDialogue
|
| 70 |
cd VoiceDialogue
|
| 71 |
|
| 72 |
+
# 3) 校验模型确实拉取成功(应显示 GB 级大小,而非 100+ 字节)
|
| 73 |
+
# 若显示很小,说明 Git LFS 未生效,执行:git lfs pull
|
| 74 |
+
ls -lh assets/models/llm/qwen/Qwen3-8B-Q6_K.gguf
|
| 75 |
+
|
| 76 |
+
# 4) 安装依赖(推荐使用 uv)
|
| 77 |
pip install uv
|
| 78 |
uv venv
|
| 79 |
source .venv/bin/activate
|
| 80 |
|
| 81 |
WHISPER_COREML=1 CMAKE_ARGS="-DGGML_METAL=on" uv sync
|
| 82 |
|
| 83 |
+
# 5) 安装额外依赖
|
| 84 |
uv pip install kokoro-onnx # kokoro-onnx(英文 TTS)
|
| 85 |
uv pip install numpy==1.26.4 # 固定 numpy 版本
|
| 86 |
```
|
| 87 |
|
| 88 |
> 📖 需要更详细的步骤?请查阅 [安装指南](docs/installation.md),其中包含系统要求和常见问题。
|
| 89 |
+
>
|
| 90 |
+
> 💡 想免去克隆与下载?直接下载打包好的 **DMG 安装包**(已内置全部模型,完全离线即开即用),见下方[「直接安装(DMG)」](#-直接安装dmg)。
|
| 91 |
|
| 92 |
### 2. 启动图形界面(推荐)
|
| 93 |
|
|
|
|
| 102 |
- 点击右下角 **⚙️ 设置**,选择**麦克风、回音消除、识别语言、音色**,也可切换**中 / 英界面语言**;
|
| 103 |
- 点击 **「开始对话」**,即可与 AI 实时语音对话,**字幕会实时显示**。
|
| 104 |
|
| 105 |
+
> **首次启动较慢,属正常现象**:程序会自动下载 Qwen3-ASR 模型(约 4.4GB,需联网,下载进度会打印在终端)并转换一次 TTS 权重格式。全部完成后才会就绪,整个过程约几分钟(取决于网速);之后每次启动只需数十秒。
|
| 106 |
+
> 若终端长时间停在下载步骤,请检查网络是否能访问 `huggingface.co`。
|
| 107 |
|
| 108 |
### 3. 命令行模式(CLI)
|
| 109 |
|
|
|
|
| 125 |
|
| 126 |
> 详细使用方法请参考 [配置指南](docs/configuration.md) 和 [API 服务指南](docs/api-guide.md)。
|
| 127 |
|
| 128 |
+
## 💾 直接安装(DMG)
|
| 129 |
+
|
| 130 |
+
不想克隆仓库、配置环境的用户,可以直接使用打包好的 **DMG 安装包**:**全部模型已内置(含 Qwen3-ASR),完全离线、即开即用,无需任何下载**。
|
| 131 |
+
|
| 132 |
+
- 适用机型:**仅 Apple Silicon(M 系列芯片)**,约 14GB。
|
| 133 |
+
- 安装包请向团队获取(暂未放到公开 Releases)。
|
| 134 |
+
|
| 135 |
+
安装步骤:
|
| 136 |
+
|
| 137 |
+
1. 双击打开 DMG,将 **Voice Dialogue** 拖入 **Applications**。
|
| 138 |
+
2. 首次打开因安装包**未签名**,会被 macOS 拦截。请**右键点击应用图标 → 选择「打开」**,在弹窗中再次点击「打开」即可(直接双击只会提示“已损坏/无法验证”,属正常现象)。
|
| 139 |
+
- 也可在 **系统设置 → 隐私与安全性** 中点击「仍要打开」。
|
| 140 |
+
3. 启动后等待模型加载(约 1 分钟),随后浏览器会自动进入对话界面。
|
| 141 |
+
|
| 142 |
## 📚 文档导航
|
| 143 |
|
| 144 |
- 📖 **[安装指南](docs/installation.md)**: 详细的安装步骤和系统要求。
|