sherpa icon indicating copy to clipboard operation
sherpa copied to clipboard

Published 20 hours ago • verified publisher icon k2-fsa

any plans for faster whisper integration in onnx+triton?

Open haiderasad opened this issue 1 year ago • 2 comments

haiderasad avatar Jan 30 '24 05:01 haiderasad

@haiderasad We have no plan to integrate faster whisper. I recommand to try whisper TensorRT-LLM (https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/whisper), which is the current fastest implementation according to https://github.com/shashikg/WhisperS2T?tab=readme-ov-file#benchmark-and-technical-report.

yuekaizhang avatar Feb 18 '24 06:02 yuekaizhang

See #551. @haiderasad

yuekaizhang avatar Mar 11 '24 06:03 yuekaizhang