ASR-on-microsoft-interSpeech-dataset

used Microsoft's InterSpeech dataset(Telugu) from sractch on Kaldi to convert the speech signals to text.

use the run.sh provided. The data is too large to put in github, but is available online.

here is the view link to colab repositorty https://colab.research.google.com/drive/1d0_5WrvULQE69ngwAlkc-blxSJw5hX1- check it here as the file is too large for the repository

Built With

Share this project:

Updates