git/bark.cpp
1
0
Fork 0
mirror of https://github.com/PABannier/bark.cpp synced 2026-03-09 08:31:26 +01:00
Code Issues Packages Projects Releases Wiki Activity
24 Commits 8 Branches 2 Tags 64 MiB
C++ 75.4%
Python 13.3%
C 8.3%
Swift 1.3%
CMake 1.1%
Other 0.6%
33e705a44b
Go to file
PAB 33e705a44b
DOC Add license file (#25)
2023-07-31 01:06:28 +02:00
.github/workflows FIX Branch name in CI (#21) 2023-07-30 22:29:33 +02:00
.vscode FEAT Add forward pass of fine model (#7) 2023-07-29 15:23:17 +02:00
examples MNT Unit tests tokenizer (#18) 2023-07-30 18:04:07 +02:00
ggml_weights MNT Separated vocab file from other files generated (#22) 2023-07-30 23:21:31 +02:00
scripts feat: add build scripts CMakeLists.txt (#13) 2023-07-29 17:45:32 +02:00
tests MNT Separated vocab file from other files generated (#22) 2023-07-30 23:21:31 +02:00
.gitignore MNT Separated vocab file from other files generated (#22) 2023-07-30 23:21:31 +02:00
bark-util.h feat: add build scripts CMakeLists.txt (#13) 2023-07-29 17:45:32 +02:00
bark.cpp MNT Separated vocab file from other files generated (#22) 2023-07-30 23:21:31 +02:00
bark.h MNT Separated vocab file from other files generated (#22) 2023-07-30 23:21:31 +02:00
build-info.h MNT Add CIs (#20) 2023-07-30 22:26:53 +02:00
CMakeLists.txt MNT Add CIs (#20) 2023-07-30 22:26:53 +02:00
convert.py MNT Separated vocab file from other files generated (#22) 2023-07-30 23:21:31 +02:00
encodec.cpp feat: add build scripts CMakeLists.txt (#13) 2023-07-29 17:45:32 +02:00
encodec.h working loading weights 2023-07-09 10:32:36 +02:00
ggml.c working convert_pt_to_ggml script 2023-07-08 15:54:41 +02:00
ggml.h working convert_pt_to_ggml script 2023-07-08 15:54:41 +02:00
LICENSE DOC Add license file (#25) 2023-07-31 01:06:28 +02:00
Makefile MNT Separated vocab file from other files generated (#22) 2023-07-30 23:21:31 +02:00
README.md DOC Remove MacBook from README (#24) 2023-07-31 01:04:08 +02:00

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.

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