Where can you use this model in GGUF format? ComfyUI and some Gradio demos only load the full demo?
#1
by
CR2022
- opened
Hi, Where can you use this model in GGUF format? ComfyUI and some Gradio demos only load the full demo? I have not seen the option yet to use the text to speech of Maya1-TTS with GGUF quantization.
As discussed under https://huggingface.co/mradermacher/maya1-GGUF/discussions/1 you can simply use llama-server to serve this model using an OpenAI compatible API server and then use a python script for prompting the model and converting the resulting audio tokens into an audio stream/audio file. If you need a graphical user interface for this and coding LLM could easily generate one for you.