Orpheus-GGUF

Orpheus-TTS inference using python bindings for llama.cpp.

Installation

Clone the repo:

git clone https://github.com/zuellni/orpheus-gguf
cd orpheus-gguf

Create a venv:

python -m venv venv
venv\scripts\activate # windows
source venv/bin/activate # linux

Install torch:

pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu126

Install llama-cpp-python:

pip install llama-cpp-python -C cmake.args="-DGGML_CUDA=1;-DGGML_CUDA_F16=1;-DGGML_CUDA_FA_ALL_QUANTS=1"

See the instructions in the original repo if this fails.

Install other requirements:

pip install -r requirements.txt