Argmax Inc. released WhisperKit v0.2, enabling on-device inference for Apple Watch using Core ML on watchOS. The new version supports real-time operation despite a 5x slowdown compared to M2 Mac due to the unavailability of Neural Engine to apps. Users can contribute to peer-to-peer local inference for Vision Pro.
Whisper running on WatchOS! 🔥 > Powered by WhisperKit by @argmaxinc > Supports up to Whisper base > Leverages Neural Engine ⚡ > Three lines of code ;) > Works real-time! > MIT license Quite amazed by the speed with which Argmax is shipping. Possibly the fastest & reliable… https://t.co/L5utrzIOzv
WhisperKit v0.2 is out! On-device Inference for Apple Watch with WhisperKit shows just how little resources you need on iPhone and Mac: https://t.co/x85DbPkqhI https://t.co/P85oqeuSIC
Wearable Inference with WhisperKit on Vision Pro! - Real-time despite ~5x slowdown compared to M2 Mac since Neural Engine is not available to apps yet - Call for contribution: Peer-to-peer local inference for Vision Pro to delegate to Mac or iPhone https://t.co/amvoEz7nJp
Whisper running on your watch! 🤯 Using WhisperKit by argmax, which uses Core ML on macOS, iOS, watchOS, … Repo: https://t.co/9j60hUZ6KR Models on 🤗: https://t.co/8fQ65H14AZ https://t.co/fhZrSnRznp
Today's WhisperKit v0.2 release supports watchOS! Link in🧵 https://t.co/4RiglqQrVL https://t.co/0Rj60Y4l70