High-performance inference of Meta's Encodec deep learning based audio codec model:
- Plain C/C++ implementation without dependencies using ggml
The entire implementation of the model is contained in 3 source files:
Tensor operations: ggml.h / ggml.c Inference: encodec.h / encodec.cpp Utils operations: encoder.h / encoder.cpp
- Support of 24Khz model
- Support of 48Khz model
- Encodec's language model support
- Mixed F16 / F32 precision
- 4-bit / 8-bit quantization support
- Add Encodec's original language model
- Support of 48khz model
- The core tensor operations are implemented in C (ggml.h / ggml.c)
- The encoder-decoder architecture and the high-level C-style API are implemented in C++ (encodec.h / encodec.cpp)
- Sample usage is demonstrated in main.cpp