Vendor page
Whisper-Tiny: Optimized for Qualcomm Devices
Qualcomm AI Hub, on Hugging Face, n.d.
Read the originalRead on October 17, 2026
- What it is
- Qualcomm's model card for a pre-exported Whisper Tiny model, built for Qualcomm chips. It describes the edge-optimized architecture, the 30-second input window and the devices the model is compiled for.
- How much weight it carries
- Published by the chip maker that sells the optimized build. It describes its own export, so it is reliable on what the export does, and it does not measure accuracy against other systems.
Facts taken from this source
- Qualcomm's page for its Whisper Tiny build says the model transcribes audio clips up to 30 seconds long.
“capable of accurately transcribing audio clips up to 30 seconds long” (Model description, first paragraph)
- Qualcomm's Hugging Face page says its repository holds pre-exported Whisper Tiny model files optimized for Qualcomm devices.
“This repository contains pre-exported model files optimized for Qualcomm® devices.” (Page introduction, Option 2 section)