|
Hello, I got this new text to speech model in safetensors format. I'm wondering, is it possible to use this model format with audio.cpp? If not, is there any guidance on how to convert this model type into a gguf format so that I can use it? |
Answered by
0xShug0
Sep 1, 2026
Replies: 1 comment
|
Yes, but: (1) It depends on the model impl. If a model supports safetensor layout, you may use safetensor (2) We no longer maintain safetensor support. So the safetensor support in a model could be just a placeholder and may not work correctly. You can check the gguf.md doc for gguf conversion. Or using ready-to-use ggufs from https://huggingface.co/audio-cpp/audio.cpp-gguf |
0 replies
Answer selected by
0xShug0
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Yes, but: (1) It depends on the model impl. If a model supports safetensor layout, you may use safetensor (2) We no longer maintain safetensor support. So the safetensor support in a model could be just a placeholder and may not work correctly.
You can check the gguf.md doc for gguf conversion. Or using ready-to-use ggufs from https://huggingface.co/audio-cpp/audio.cpp-gguf