speech-to-speech models
1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Feb 19, 2026 by Neil Zeghidour · across every show →
Everything said about speech-to-speech models, oldest first
Feb 19, 2026 negative
Zeghidour: End-to-end speech models have massive switching costs for upgrades
“One drawback of speech-to-speech models is that since everything is integrated, when you go from a text model to the speech-to-speech model, you need to fine-tune it on speech data. So now it's the cost to switch the underlying text model is extremely high bec…”