search

alumae / kaldi-gstreamer-server

Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
BSD 2-Clause "Simplified" License
1.07k stars 341 forks source link

nnet3 model #114

Open satell opened 6 years ago

satell commented 6 years ago

do you know where can I found a ready and trained nnet3 model to use with your server?

nhua6456 commented 6 years ago

The Aspire model is nnet3 trained. You can find it on kaldi's site.

RicWg commented 3 years ago

http://kaldi-asr.org/models/m11 is good too.

jichaoqun commented 3 years ago

when I use the M11 that how the .yaml file should to build? the models don`t have ivector_extractor files? what can I do ?