/uis_rnn_for_speaker_diarization

speaker_diarization done on toy dataset and tested on timit dataset

Primary LanguageJupyter Notebook

UIS-RNN: Speaker_Diarization

please open ipynb file this is the pipeline of whole speaker diarization process and contains code of all other files in the repo in a specific order

IF YOU WANT TO RUN THE FILE then - you should have a kaggle.json file

if you do not have go through the points below

  • 1 go to your kaggle acount
  • 2 go to 'my account' button
  • 3 scroll down and you will se a button of create api token download it
  • 4 when you run the ipynb file in the first cell upload you json file

if you encounter an error before uploading the json rerun the cell and then upload this all is done because this help you to download the timit dataset. after that clone this repo and run the ipynb file in google colab. you can download the toy dataset from here

after downloading the toy_dataset upload these to your google drive