Sign inSign up

alphacep/kaldi-en-gpu

By alphacep

•Updated over 3 years ago

Vosk GPU websocket server for fast processing with Nvidia GPU with English model

Image
9

1.7K

alphacep/kaldi-en-gpu repository overview

A websocket server based on Kaldi and Vosk library with English model included. Supports fast decoding on GPU card.

For details see https://github.com/alphacep/vosk-server⁠

Usage:

Start the server

docker run --gpus all -p 2700:2700 alphacep/kaldi-en-gpu

Check the sample code from https://github.com/alphacep/vosk-server/blob/master/websocket/test.py⁠, run

./test.py test16k.wav

You can try with any wav file which has proper format - 8khz 16bit mono PCM. Other formats has to be converted before decoding.

For client samples in other programming languages see https://github.com/alphacep/vosk-server/tree/master/client-samples⁠

Tag summary

Content type

Image

Digest

sha256:2612a03d4…

Size

4.8 GB

Last updated

over 3 years ago

docker pull alphacep/kaldi-en-gpu