Skip to main content

Featured Post

AMD to invest $400 million in India by 2028: Here’s what we know

US chipmaker Advanced Micro Devices said on Friday it will invest around $400 million in India over the next five years and will build its largest design center in the tech hub of Bengaluru. AMD’s announcement was made by its Chief Technology Officer Mark Papermaster at an annual semiconductor conference that started Friday in Prime Minister Narendra Modi’s home state of Gujarat. Other speakers at the flagship event include Foxconn Chairman Young Liu and Micron CEO Sanjay Mehrotra. Despite being a late entrant, the Modi government has been courting investments into India’s nascent chip sector to establish its credentials as a chipmaking hub. AMD said it will open its new design centre campus in Bengaluru by end of this year and create 3,000 new engineering roles within five years. “Our India teams will continue to play a pivotal role in delivering the high-performance and adaptive solutions that support AMD customers worldwide,” Papermaster said. The new 500,000-square-foot (55,5...

Meta releases AI-powered music generator: Here’s how it works

Meta (formerly Facebook) has released its AI-powered music generator called ‘MusicGen’, which will turn text description and melody into audio.

The company also released the code and models for open research, reproducibility, and the music community.

“We present MusicGen: A simple and controllable music generation model. MusicGen can be prompted by both text and melody. We release code (MIT) and models (CC-BY NC) for open research, reproducibility, and for the music community,” tweeted Felix Kreuk, Research Engineer at Meta AI research.

“MusicGen is built on top of the EnCodec audio tokenizer. Unlike prior work, MusicGen is a single-stage transformerLM which uses an efficient token interleaving patterns, hence eliminates the need for cascading several models (e.g., hierarchically or upsampling),” he added.

Moreover, the company said that MusicGen was trained on 20,000 hours of music, including 10,000 “high-quality” licenced music tracks and 3,90,000 instrument-only tracks from the ShutterStock and Pond5 stock media libraries.

However, Meta isn’t the first to offer an AI-powered music generator tool.

In May, Google released ‘MusicLM’ — a new experimental AI tool that can generate high-fidelity music in any genre given a text description.

The tool was first announced in January this year and is now available to the public.

The text-to-music AI tool is available in the AI Test Kitchen app on the web, Android or iOS.

–IANS

The post Meta releases AI-powered music generator: Here’s how it works appeared first on Techlusive.



from Techlusive https://ift.tt/zxGZWL8
via IFTTT

Comments