Update README.md

README.md

@@ -59,13 +59,21 @@ Training high-quality TTS models requires significant GPU resources. If you find
 ```bash
 git clone https://github.com/pnnbao97/VieNeu-TTS.git
 cd VieNeu-TTS
+```
+
+- **Option 1: CPU** (minimal, torch-free) — runs **v3 Turbo via ONNX**
 
-# Install uv (if you haven't)
-# Windows: powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
-# Linux/macOS: curl -LsSf https://astral.sh/uv/install.sh | sh
+ ```bash
+ uv sync
+ ```
+- **Option 2: GPU** — **v3 Turbo (PyTorch) + VieNeu-TTS v2 (GPU)**
 
-# Install dependencies & Run
-uv sync --group gpu
+ ```bash
+ uv sync --group gpu
+ ```
+**Start the Web UI:**
+
+```bash
 uv run vieneu-web
 ```