search

quic / ai-hub-models

The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
https://aihub.qualcomm.com
BSD 3-Clause "New" or "Revised" License
481 stars 76 forks source link

[Feature Request] Whisper Small.En Quantized #81

Open Carl-2008 opened 3 months ago

Carl-2008 commented 3 months ago

How to export Whisper small.En quantization model? For example, the int8 quantified version .

mestrona-3 commented 3 months ago

Hi @Carl-2008, we don't have a quantized version of Whisper on AI Hub Models currently. We have this on our backlog. We are also working on generic quantization recipes to share with our developer community. Stay tuned!

Carl-2008 commented 3 months ago

Thanks, looking forward to it.