bark.cpp
bark.cpp copied to clipboard
Suno AI's Bark model in C/C++ for fast text-to-speech
hi there, i'm not pretty sure if it a bug or i missed something in my quantization process but this is the result i have running the q4_0 model ...
This PR translates Bark to a CoreML model
Can Bark.cpp support acceleration with AMD GPU with ROCM?
Hello, Thank you for this! Can u please compile ur project like other cpp ai such as stable diffusion cpp? so we only can download the exe from release and...
This PR allows users to use the Metal (MacOS) and cuBLAS backend by: - [x] Exposing the `n_gpu_layers` parameter in the CLI - [ ] Using the Metal backend in...
Metal
I tried to ``` cmake -DGGML_METAL=ON .. cmake --build . --config Release ``` but it is still only using CPU instead of Mac GPU
Something similar to what's done in Whisper.cpp: https://github.com/ggerganov/whisper.cpp/blob/b0c3cbf2e851cf232e432b590dcc514a689ec028/whisper.h#L561-L562
``` user@steambox:~/ai/bark.cpp$ ./build/examples/main/main -m ./ggml_weights/bark_weights-f16.bin -em ./ggml_weights/encodec_weights-f16.bin -t 16 -p "I _LOVE_ your shirt!" -o message2.wav __ __ / /_ ____ ______/ /__ _________ ____ / __ \/ __ `/...