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

Input feature dimension mismatch #91

Closed star633669 closed 7 years ago

star633669 commented 7 years ago

Hi When I send an audio to server I got an error as follow as

ERROR ([5.2.74~1-dbdd]:DecodableNnetLoopedOnlineBase():decodable-online-looped.cc:45) Input feature dimension mismatch: got 40 but network expects 43

where can change the input dimension to 43? I will appreciate any help

alumae commented 7 years ago

Check that your mfcc-config file, as specified in the configuration YAML file, is compatible with your acoustic model.

star633669 commented 7 years ago

Thank you for your reply. in my mfcc-config file as follow as --use-energy=false --sample-frequency=16000 --num-mel-bins=40 --num-ceps=40 --low-freq=40 --high-freq=-200

which argument I must be modify

alumae commented 7 years ago

Sorry, I don't know the specifics of your acoustic model.