Meta AI has released a new text to music model called MusicGen that can synthesize music audio given text or melody prompt. It is claimed to be better than existing models such as Google’s MusicLM. MusicGen is a single-stage transformer language model that operates over several streams of compressed discrete music representation. It has three tiers of capacity: 300M, 1.5B, and 3B parameters.
▼ Link(s) From Today’s Video:
✩ Meta AI’s MusicGen:
✩ Github for MusicGen:
✩ Google Music LM Paper:
✩ Google AI Test Kitchen:
► MattVidPro Website:
► MattVidPro Discord:
► Follow Me on Twitter:
————————————————-
▼ Extra Links of Interest:
✩ AI LINKS MASTER LIST:
✩ Lemon Gallery:
✩ General AI Playlist:
✩ AI I use to edit videos:
✩ Second Channel:
————————————————-
Thanks for watching Matt Video Productions! I make all sorts of videos here on Youtube! Technology, Tutorials, and Reviews! Enjoy Your stay here, and subscribe!
All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them.
————————————————-
► Business Contact: [email protected]
source
