ggml-org/ggml

New model: AudioCraft for audio generation

Open

#429 opened on Aug 2, 2023

View on GitHub
 (2 comments) (13 reactions) (1 assignee)C++ (14,741 stars) (1,646 forks)auto 404
help wantedmodel

Description

Meta just released their new open-source model AudioCraft consisting of three pieces: MusicGen, AudioGen and Encodec. Given encodec.cpp is already implemented, we should be able to implement it AudioCraft fairly easily with ggml.

I've already opened an issue in bark.cpp and plan to implement it as soon as i'm finished with bark.

Source: https://ai.meta.com/blog/audiocraft-musicgen-audiogen-encodec-generative-ai-audio/

Contributor guide

Tech stack
cpp
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
GitC++
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70
Research direction
Study the existing encodec.cpp implementation and the AudioCraft paper; then implement the model using ggml primitives.