llama-tts
hi,
thank you for sharing this model , can you please tell me what is the correct way to use it with llama-tts , i have used thos commands but without success :
llama-tts -m "D:\tts\OuteTTS\Llama-OuteTTS-1.0-1B-Q8_0.gguf" --tts-speaker-file "D:\tts\OuteTTS\af_heart_5.wav" -p "Hello world"
llama-tts -c 8192 -m Llama-OuteTTS-1.0-1B-Q8_0.gguf -mv WavTokenizer-Large-75-Q5_1.gguf -o D:\tts\OuteTTS\output.wav --tts-speaker-file D:\tts\OuteTTS\en_sample.wav -p "Hello world"
llama-tts -c 8192 -m Llama-OuteTTS-1.0-1B-Q8_0.gguf -mv WavTokenizer-Large-75-Q5_1.gguf -p "Hello world"
it return :
llama_decode: failed to decode, ret = -1
main: llama_decode() failed
Best,
Hi, currently llama.cpp does not have direct support for the new 1.0 version. I've made a WIP PR to add support for the new model: https://github.com/ggml-org/llama.cpp/pull/12794
thank you for your fast replay , so we need to wait :p
Have great day,
Best,