01 / preference

30 Mar 2026

I think at least personally prefer the operations, which are the simplest, and so we try to see, can we just add audio as just another head to our regular transformer decode model because that kind of makes it easier for eventual end-to-end modeling of audio text native modeling.

“I think at least personally prefer the operations, which are the simplest, and so we try to see, can we just add audio as just another head to our regular transformer decode model because that kind of makes it easier for eventual end-to-end modeling of audio text native modeling.”

Speaker: Pavan Kumar Reddy
Episode: Mistral: Voxtral TTS, Forge, Leanstral, & what's next for Mistral 4 — w/ Pavan Kumar Reddy & Guillaume Lample
Publisher: Latent Space

What Pavan said.

I think at least personally prefer the operations, which are the simplest, and so we try to see, can we just add audio as just another head to our regular transformer decode model because that kind of makes it easier for eventual end-to-end modeling of audio text native modeling.