Kaldi speech recognition toolkit
Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.
Questions tagged [kaldi]
113 questions
0
votes
0 answers
How to follow a filepath specified within a text file on Cygwin?
I'm trying to run some Kaldi examples after I have compiled it on Cygwin, however, when the directory is specified in a file, Cygwin can't follow it. For example, I am trying to run the following in Cygwin terminal:
steps/make_mfcc.sh
This…
Ivan Novikov
- 558
- 6
- 13
0
votes
0 answers
Kaldi-for-Dummies Tutorial -- run.sh script throwing "no such files in directory" error while Preparing Acoustic Data
I am trying to replicate http://kaldi-asr.org/doc/kaldi_for_dummies.html to get started onto an Automatic Speech Recognition solution i am trying to develop. I followed all the instructions within this Tutorial and then finally ran run.sh script.…
Nitin shukla
- 57
- 10
0
votes
0 answers
trouble installing a protocol-buffer known as SentencePiece too, to alleviate the open vocabulary problems in neural machine translation
im trying to install a protocol-buffer known as SentencePiece too, to alleviate the open vocabulary problems in neural machine translation .
I used this command as suggested on github documentation :
sudo apt-get install cmake build-essential…
Houssem Bzi
- 79
- 2
- 12
0
votes
1 answer
I have a word or sentence ,Is there any way/open-source package to find the probability that user has spoken that word
I have a word /sentence ,Is there any way/open-source package to find the probability that user has spoken that word / sentence
thiran509
- 11
- 2
0
votes
0 answers
Error while configuring pytorch-kaldi on Linux Mint 19.1 cinnamon
I am trying to configure Pytorch-Kaldi on a Linux Mint cinnamon 19.1.
I can not solve this error :
ZOE ERROR (from hmm-info): error opening HMM file ((null)/HMM/models)
ZOE library version 2013-02-16
Houssem Bzi
- 79
- 2
- 12
0
votes
1 answer
Kaldi - Mini librispeech - decode own file
I have started to work with Kaldi and have managed to train the mini librispeech files which took quite a while without any GPU.
Now I have got a small WAV file and I would need to figure out how to decode this file with Kaldi. Which decode file do…
Andi Maier
- 914
- 3
- 9
- 28
0
votes
2 answers
Kaldi's objects explained in layman's term
I am trying to understand the internal workings of Kaldi, however is having trouble understanding the technical details of kaldi's doc.
I want to have a high-level understanding of various objects first in order to help digest what is presented. I…
kkawabat
- 1,530
- 1
- 14
- 37
0
votes
2 answers
Reconcile links and pathfiles for the Kaldi recipes
I'm using the Kaldi toolset for speech recognition from a computer in which I don't have the rights to modify the contents of the install in /var/kaldi. The directory contains a folder of scripts that are provided as a sample of utilisation, the…
maja
- 697
- 5
- 18
0
votes
1 answer
BrokenPipeError while Running TIMIT example on Kaldi
I am trying to install and run the Kaldi TIMIT example.
i.e. ./run.sh in the kaldi/egs/timit/s5 directory:
I get the error:
fstcompile: error while loading shared libraries: libfstscript.so.10: cannot open shared object file: No such file or…
Rafael
- 651
- 13
- 30
0
votes
0 answers
CMake Error, following variables set to NOTFOUND
So im trying to install kaldi-GOP, when i run build.sh this error pops up
[root@localhost kaldi-gop]# ./build.sh
utils/check_dependencies.sh: all OK.
CMake Error: The following variables are used in this project, but they are set to NOTFOUND.
Please…
Another Juan
- 1
- 1
- 4
0
votes
1 answer
Docker container performance degredation
I am running a very resource intensive application (Kaldi audio transcription) within a Docker container. When comparing with running the same application natively on the host machine, performance is 2 - 3 X worse.
Could anyone shed some light on…
Samy Shehata
- 1
- 2
0
votes
1 answer
The transcription of my audio file stops after 7 seconds
I'm using Kaldi and I have a problem, the transcription of my audio file stops after 7 seconds. There is no error returned by kaldi. An idea of why?
Here is my command line:
sudo /home/kaldi/src/online2bin/online2-wav-nnet3-latgen-faster …
0
votes
2 answers
How to use "tri2a" and "tri2b_mmi" training in kaldi for dummies tutorial?
I have done Kaldi for dummies tutorial with my own custom audio data. In that tutorial they were using Mono alignment and tri1 training method. Can i change it to tri2a/tri2b_mmi training?
Geo George
- 31
- 1
- 4
0
votes
1 answer
Installing Kaldi using Cygwin, error on zlib
I am trying to install kaldi on a windows computer using cygwin.
When I run ./tools/check_dependencies.sh (as requested in the INSTALL file)
I get "zlib is not installed", so I go to the cygwin package list and try to install.
The thing is - there…
user1526112
- 11
- 1
- 2
0
votes
0 answers
Best open source speech recognition API and engine
I am making my speech recognition project for PC(working on Windows 8) and new in this area.The project should have basic functionality like dictation with accuracy in email,notepad etc and should response to local commands of PC.
I am using sphinx4…
