Upcoming! WhAM: the Whale Acoustics Model with Orr Paradise
WhAM; Animation by Megan Fenske
March 28 2026, 16:00 GMT/ 12:00 EDT/ 09:00 PDT (4pm GMT/ 12 pm EDT/ 9am PDT)
WhAM: the Whale Acoustics Model
Sperm whales communicate in short sequences of clicks known as codas. In this lecture, Orr Paradise will present WhAM (Whale Acoustics Model), the first transformer-based model capable of generating synthetic sperm whale codas from any audio prompt. WhAM is built by finetuning VampNet, a masked acoustic token model pretrained on musical audio, using 10k coda recordings collected over the past two decades. Through iterative masked token prediction, WhAM generates high-fidelity synthetic codas that preserve key acoustic features of the source recordings. We evaluate WhAM's synthetic codas using Fréchet Audio Distance and through perceptual studies with expert marine biologists. On downstream classification tasks including rhythm, social unit, and vowel classification, WhAM's learned representations achieve strong performance, despite being trained for generation rather than classification. Code and model are available here.
Watch Project CETI’s 2-minute illustrative video on WhAM.
About the speaker
Orr Paradise
Orr Paradise is a member of Project CETI, a non-profit listening project attempting to decipher sperm whale communication.
He is also a postdoctoral fellow at the École polytechnique fédérale de Lausanne (EPFL) researching the theoretical foundations of provably-safe AI systems. He holds a PhD in Computer Science from the University of California, Berkeley.
