Implementation of MAGNeT (Masked Audio Generation using a Single Non-Autoregressive Transformer) in C++ with the tensor library GGML This is a work in progress and not considered production-stable. This project was inspired by encodec.cpp.
Download MAGNeT's weights from huggingface and convert them into the GGUF format.
Ensure that you have the state_dict.bin
as this is MAGNeT's model. Note that compression_dict.bin
is the state dict for EnCodec.
python convert.py --dir-model=/path/to/hf/weights --out-dir=/path/to/gguf/weights
git clone --recurse-submodules https://github.com/schineaj23/magnet.cpp.git
mkdir build
cd build
cmake ..
make
magnet /path/to/gguf/weights
- Inference in FP32
- FP8/INT8 Quantization