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
338 stars 45 forks source link

[Feature Request] How to run Whisper on the 8550 LE system #53

Closed 32zhuyt closed 1 week ago

32zhuyt commented 2 weeks ago

Hello,

I want to run Whisper on a GPU on an 8550 device.

Now I have downloaded the source code of qai hub and am able to successfully run python3- m pytest -- pyargs qai_hub_models.models.whiser_base_en.demo 、”python 3- m pytest -- pyargs qai_hub_models. models. wheeler_base_en.test” and other commands.

But these commands seem to not be able to see the specific information of converting voice to text. Is there any command that can convert my own audio into text and see the results of GPU operation.

thanks

kory commented 1 week ago

Please record your voice into an audio file. The demo was just updated today (v0.9.0) with the ability to translate any file. You can pass --audio_file as a flag to the demo to make that work.