kaldi-gstreamer-server

kaldi-gstreamer-server copied to clipboard

nnet3 model

3

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

satell

INTEL MKL ERROR: /opt/intel/mkl/lib/intel64/libmkl_avx2.so: undefined symbol: mkl_sparse_optimize_bsr_trsm_i8. Intel MKL FATAL ERROR: Cannot load libmkl_avx2.so or libmkl_def.so.

2

when i do this "python kaldigstserver/worker.py -u ws://localhost:8888/worker/ws/speech -c sample_worker.yaml",I have get this problems: INTEL MKL ERROR: /opt/intel/mkl/lib/intel64/libmkl_avx2.so: undefined symbol: mkl_sparse_optimize_bsr_trsm_i8. Intel MKL FATAL ERROR: Cannot load libmkl_avx2.so or libmkl_def.so....

jichaoqun

Enable Multiple channels listening

1

Hi, I have noticed that at a time only one server, worker and client can run. But I am interested in multiple channels listening and transcribing. Can anyone please help...

Momina12

The following .py programs have error. * kaldigstserver/decoder.py * kaldigstserver/decoder2.py ``` NameError: name 'sys' is not defined ``` That's why I created a patch to fix this. If this error...

averak

No speech input detected

1

Hi,everyone: I use a custom model. After executing start.sh and input audio, system will crash and return "No speech input detected" . And I found some error logs in worker.log...

Johe-cqu

Error when running python kaldigstserver/worker.py on sample chinese

1

Hello everyone, I'm trying to run kaldigstserver/worker.py on the sample chinese model. I get the following error (on python 2.7 and python 3.7) How can this be fixed and why...

RobertLevenbach

I want to output the phone alignment and word alignment information of the input audio. I tried using `do-phone-alignment=true` to yaml config file but there was still no relevant alignment...

YichiHuang

WIP: Python 3, Tornado 6

1

This PR migrates to Pythin 3.5+ and Tornado 6. Python 2.7 is not supported any more. Also, rewrote worker.py to use Tornado's websocket client and got rid of the ws4py...

alumae

Websocket closed when decode long audio files

3

Hello, I was doing decode with the kaldinnet2onlinedecoder. When I test some long audio such as the bill_gates-TED.mp3 or other audio longer than 1 min, Its always show "Audio sent,...

kli017

Using a pre built nnet3 model

9

Hi its one of my first times working with ASR and Kaldi. I got your Server running with the "tedlium_nnet_ms_sp_online" english model. Everything is working fine. (with and without the...

petgel