Amol Bole

Getting completely wrong result for my nnet2 model

2

Hi all, I build my own nnet2 acoustic model and trying to test with gui-demo.py but getting completely (100%) wrong result. For same model while building got 15% WER. I...

No speech error for browser

1

Everything is fine but getting error while running in mozila Firefox, I am using it on ubuntu 16.04 LTS. I gave access to microphone and I tested microphone in other...

I want to stop recording after detection of 2 seconds silence. Can anyone help me in this?

Getting error for my own model

2

ERROR (fcgi-nnet3-decoder[5.5.268~1-f9828]:DecodableNnetLoopedOnlineBase():decodable-online-looped.cc:50) Ivector feature dimension mismatch: got -1 but network expects 100 [ Stack-Trace: ] kaldi::MessageLogger::LogMessage() const kaldi::MessageLogger::LogAndThrow::operator=(kaldi::MessageLogger const&) kaldi::nnet3::DecodableNnetLoopedOnlineBase::DecodableNnetLoopedOnlineBase(kaldi::nnet3::DecodableNnetSimpleLoopedInfo const&, kaldi::OnlineFeatureInterface*, kaldi::OnlineFeatureInterface*) kaldi::SingleUtteranceNnet3DecoderTpl::SingleUtteranceNnet3DecoderTpl(kaldi::LatticeFasterDecoderConfig const&, kaldi::TransitionModel const&, kaldi::nnet3::DecodableNnetSimpleLoopedInfo const&, fst::Fst...

How to train for new keyword?

3

Dear @vineeths96 Thank you for awesome recipe. I have few questions 1) How to train for new keyword? 2) How to tune hyper parameter? 3) How to display position (at...

I have used the octave for voice conversion but getting **high error rate**. we have converted **female voice** to test on model, which is **trained on male voice**. Before conversion...

Error whille running make...

9

I have installed libfvadproperly, I am having latest kaldi but getting following error while running make in KaldiBasedSpeakerVerification/src. I have provided the correct locations in makefile. amol@amol-HP-406-G1-MT:/media/amol/data/libfvad/KaldiBasedSpeakerVerification/src$ make g++ -std=c++11...