pyctcdecode icon indicating copy to clipboard operation
pyctcdecode copied to clipboard

Published 20 hours ago • verified publisher icon kensho-technologies

Any support for GPU ?

Open thangld201 opened this issue 2 years ago • 1 comments

I notice that doing inference with language model on large amount of texts can be quite slow. In particular, it took me 11 minutes to decode around 4600 lines of text. I wonder if pyctcdecode supports using GPU for acceleration ? At the moment, I see that the model's using CPU only, making it hard for batch decoding and such.

thangld201 avatar Jun 11 '22 01:06 thangld201

@lopez86 Could you help me ?

thangld201 avatar Jun 11 '22 01:06 thangld201