Meta just released MusicGen, a simple and controllable model for music generation
MusicGen is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods like MusicLM, MusicGen doesn't not require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. By introducing a small delay between the codebooks, can predict them in parallel, thus having only 50 auto-regressive steps per second of audio
try out the @Gradio demo: https://t.co/1UvsU6UTzS
Models on @huggingface: https://t.co/7uTFxSdhQa
github: https://t.co/d23lrVLhlE
Don't quit -- unite! For the next 24 hours:
- If you follow me, I'll follow you back.
- If you already follow me, RT and I'll follow back!
Let's do this! #FBR
This is my amicus brief in Moore v. Harper, the test of the so-called independent state legislature theory at the Supreme Court. You have to be polite at SCOTUS, but here are my unfiltered thoughts. Frankly, this theory is nuts. 1/4
https://t.co/Np9KuoUdcT
New Episode on The Poetry of Impact!
@andrealeezucker & Aaron Lee on Unlocking Love & Presence.
Too many insights to share from this episode here, so just go have a listen yourself! You'll feel inspired and energized to live your best life...
https://t.co/43ESX2fuwr
New Episode on The Poetry of Impact!
@andrealeezucker & Aaron Lee on Unlocking Love & Presence.
Too many insights to share from this episode here, so just go have a listen yourself! You'll feel inspired and energized to live your best life...
https://t.co/43ESX2fuwr
You can't oppose Big Tech while killing all the alternatives to it, @SenatorCardin. Please represent me, your constituent, by voting YES on the Wyden #Cryptocurrency amendment and NO on Warner's amendment. #DontKillCrypto via @fightfortheftr https://t.co/p0anWD23u9