mirror of
https://github.com/PABannier/bark.cpp
synced 2026-03-06 23:20:57 +01:00
| .vscode | ||
| scripts | ||
| .gitignore | ||
| bark-util.h | ||
| bark.cpp | ||
| bark.h | ||
| build-info.h | ||
| CMakeLists.txt | ||
| convert.py | ||
| encodec.cpp | ||
| encodec.h | ||
| ggml.c | ||
| ggml.h | ||
| Makefile | ||
| README.md | ||
bark.cpp (coming soon!)
Inference of SunoAI's bark model in pure C/C++ using ggml.
Description
The main goal of bark.cpp is to synthesize audio from a textual input with the Bark model using 4-bit quantization on a MacBook.
Bark has essentially 4 components:
- Semantic model to encode the text input
- Coarse model
- Fine model
- Encoder (quantizer + decoder) to generate the waveform from the tokens
Roadmap
- Quantization
- FP16
- Swift package for iOS devices