IBL News | New York
Meta this week shared details on AudioCraft, a single open-source code base for music, sound, compression & generation of high-quality, realistic audio from text.
AudioCraft consists of three models: MusicGen, AudioGen, and EnCodec.
• MusicGen, trained with Meta-owned and specifically licensed music, generates music from text-based user inputs. [See Demo]
• AudioGen, which was trained on public sound effects, generates audio from text-based user inputs.
• EnCodec decoder allows for higher quality music generation with fewer artifacts.
Meta’s pre-trained AudioGen model lets users generate environmental sounds and sound effects like a dog barking, cars honking, or footsteps on a wooden floor.
The models are available for research purposes and to further people’s understanding of the technology.
“We’re excited to give researchers and practitioners access so they can train their own models with their own datasets for the first time and help advance the state of the art,” said Meta in a blog post.
Today we’re sharing details on AudioCraft, a new family of generative AI models built for generating high-quality, realistic audio & music from text. AudioCraft is a single code base that works for music, sound, compression & generation — all in the same place.
More details ⬇️
— Meta AI (@MetaAI) August 2, 2023
Open sourcing AudioCraft: Generative AI for audio made simple and available to all
blog: https://t.co/OzsYE32PlD
musicgen demo: https://t.co/EcED3yU87wAudioCraft consists of three models: MusicGen, AudioGen, and EnCodec. MusicGen, which was trained with Meta-owned and… pic.twitter.com/gjAT2FY7e1
— AK (@_akhaliq) August 2, 2023
The open source models arena
I try not to post too much about open models until we reach a point where there will no longer be any debate about if they are at the level of closed models.
So let’s make it brief.
—-
LLaMA 2The open models arena heated up last week with the… pic.twitter.com/BfXEb9CPfx
— Yam Peleg (@Yampeleg) July 30, 2023
