- Tensorflow.js - Audio recognition using transfer learning
- Simple Audio Recognition
- Pete Warden (2018) Speech Commands: A Dataset for Limited-Vocabulary Speech. arXiv:1804.03209v1
The following is a way to demonstrate examples of this repository.
example_1_word_recognition
: a simple example for word-level audio recognitionexample_2_retrain
: a simple example for retraining a model recognizing the words left, right and noise (blank).
git clone https://github.com/jiankaiwang/word_level_audio_recognition.git
# run the first example
cd example_1_word_recognition
python3 -m http.server
# run the second example
cd example_2_retrain
python3 -m http.server