Fact · Speech recognition
Qualcomm's Hugging Face page says its repository holds pre-exported Whisper Tiny model files optimized for Qualcomm devices.
Checked against its source on October 17, 2026
In the source's own words
“This repository contains pre-exported model files optimized for Qualcomm® devices.”
Whisper-Tiny: Optimized for Qualcomm Devices, Qualcomm AI Hub, on Hugging Face, n.d., Page introduction, Option 2 section.
Open the original- What it measures
- Qualcomm AI Hub publishes this export of OpenAI's Whisper Tiny. The page says it was optimized for edge inference, with its attention layers replaced for speed on device.
- What it does not show
- Describes a Qualcomm export of Whisper Tiny, the smallest Whisper model. It is not a Qualcomm model, and the export does not change Whisper's training or its languages.