Automatic Speech Recognition (ASR)
Automatic Speech Recognition (or speech-to-text) systems transform speech into their corresponding text form, typically in the form of a word sequence
website: https://kaldi-asr.org/
Author : Suraj Durgesht
- Install Subversion
sudo apt-get install subversion
- Install Dependent Libraries
sudo apt-get install libblas-*
sudo apt-get install automake
sudo apt-get install libtool-*
sudo apt-get install libatlas-*
sudo apt-get install zlib1g-dev
sudo apt-get install g++-multilib
sudo apt-get install flac
- Installation via GitHub
git clone https://github.com/kaldi-asr/kaldi.git
cd kaldi/
cat INSTALL
cd tools/
cat INSTALL
make
- Check out dependencies
extras/check_dependencies.sh
nproc
- Install a language modeling toolkit IRSTLM
extras/install_irstlm.sh
- Instructions in kaldi/src/INSTALL.
cat INSTALL
./configure
make depend -j 4
make -j 4