star633669

In nnet2 when the utterance was longer than 20s kaldi split recognition result, Can I reduce the utterance duration to 10s and then split it? or split it with silence?

Decoding with nnet3 LSTM

3

Hi, I want to use nnet3 model instead of nnet2. So, How should I modify the configuration from "librispeech_english_nnet2.yaml" file? Could you provide simple settings? I will appreciate any help,...

upload .wav file

1

I want to upload a .wav file to the recognize how can I do to approach? I will appreciate any help, Thanks

Build in ubuntu 16.04

6

dear all, ## after call ./build.sh I have got the errors rnnlm.cc:448:22: error: ‘isnan’ was not declared in this scope if (isnan(entropy) || isinf(entropy) || !(ratio >= bad_ratio)) { ^...

I try to run tedlium example, but I get a problem. It does not work when training process. ========Network Training with the 110-Hour Set========= steps/train_ctc_parallel.sh --add-deltas true --num-sequence 20 --frame-num-limit...