Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

doc: demo #23

Merged
merged 2 commits into from
Oct 23, 2023
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 9 additions & 7 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,24 +9,26 @@ High-performance inference of [Meta's Encodec](https://github.com/facebookresear

- Plain C/C++ implementation without dependencies using [ggml](https://github.com/ggerganov/ggml)

The entire implementation of the model is contained in 3 source files:
## Demo

Tensor operations: ggml.h / ggml.c<br/>
Inference: encodec.h / encodec.cpp
Here is a demo of running Encodec on a single M1 MacBook Pro:

https://github.com/PABannier/encodec.cpp/assets/12958149/d11561be-98e9-4504-bba7-86bcc233a499

## Roadmap

- [x] Support of 24Khz model
- [ ] Support of 48Khz model
- [ ] Encodec's language model support
- [x] Mixed F16 / F32 precision

- [ ] 4-bit and 8-bit quantization
- [ ] Metal support
- [ ] cuBLAS support

## Implementation details

- The core tensor operations are implemented in C ([ggml.h](ggml.h) / [ggml.c](ggml.c))
- The encoder-decoder architecture and the high-level C-style API are implemented in C++ ([encodec.h](encodec.h) / [encodec.cpp](encodec.cpp))
- Basic usage is demonstrated in [main.cpp](examples/main)
- Basic usage is demonstrated in [main.cpp](examples/main).


## Usage

Expand Down