/simpleASR

Primary LanguageJupyter NotebookMIT LicenseMIT

Simple ASR model

  1. Extract features (like MFCC) from the acoustic signal
  2. Feed an ML model (classification or clustering) with the features
  3. Recognize the speech input

Feature extraction

which model is used?

ML model

which model is used?

How to use?

  1. Install the required libraries using the following command:
pip install -r requirements.txt
  1. Run the example in the tutorial notebook named "tutorial.ipynb" or run the python file "run.py" with the following command:
python run.py